fix(web_search): send only the agent's query to Exa search

Exa /search is a neural search endpoint, not a chat model, so prepending
the Perplexity system prompt made Exa match the prompt's own vocabulary
(Kali, OWASP, apt, NIST) instead of the query. The system prompt stays
on the Perplexity path where it is a chat system message; the Exa
summary instruction is unchanged.

.pre-commit-config.yaml

@@ -1,3 +1,6 @@
+# Built viewer bundles are generated output, not hand-edited source.
+exclude: ^strix/interface/viewer/static/assets/
+
 repos:
   # Ruff for fast linting and formatting
   - repo: https://github.com/astral-sh/ruff-pre-commit
@@ -9,21 +12,18 @@ repos:
       - id: ruff-format
         name: ruff-format
 
-  # MyPy for static type checking
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.17.1
+  # MyPy for static type checking. Runs the project's own mypy from the uv
+  # environment (`make dev-install`) so it sees the same dependencies and
+  # stubs as `make check-all`.
+  - repo: local
     hooks:
       - id: mypy
-        additional_dependencies: [
-          types-requests,
-          types-python-dateutil,
-          pydantic,
-          fastapi,
-          pytest,
-          hatchling,
-          "openai-agents[litellm]>=0.19.0,<0.20",
-        ]
-        args: [--install-types, --non-interactive]
+        name: mypy
+        entry: uv run mypy
+        language: system
+        types_or: [python, pyi]
+        files: ^(strix|tests)/
+        require_serial: true
 
   # Built-in hooks for basic file checks
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -62,5 +62,6 @@ ci:
   autoupdate_branch: ""
   autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
   autoupdate_schedule: weekly
-  skip: []
+  # pre-commit.ci cannot run `language: system` hooks; mypy runs via `make check-all`.
+  skip: [mypy]
   submodules: false

AGENTS.md

@@ -28,7 +28,7 @@ Target-specific workflows built on the same engine:
 - **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control.
   ```bash
   curl -sSL https://strix.ai/install | bash        # install
-  export STRIX_LLM="openai/gpt-5.4"                 # any LiteLLM model id
+  export STRIX_LLM="openrouter/z-ai/glm-5.3"        # any LiteLLM model id
   export LLM_API_KEY="<key>"
   strix -n -t ./ --scan-mode quick --max-budget 10  # headless scan; always use -n
   ```
@@ -38,13 +38,25 @@ Target-specific workflows built on the same engine:
 
 - **Managed cloud (app.strix.ai):** no Docker, no LLM key, no local install; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Use it when local infra isn't available.
   ```bash
-  # token from Settings → API Access; register the target as an asset, then:
-  curl -sS https://app.strix.ai/api/v1/scans -H "Authorization: Bearer $STRIX_API_TOKEN" \
-    -H "Content-Type: application/json" -d '{"engagement_type":"live_test","domain_ids":["<uuid>"]}'
+  strix cloud login --scopes scans:read scans:write uploads:write billing:read
+  strix cloud domains add --domain example.com --asset-type web_app
+  strix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait
+  strix cloud scans start --source . --dry-run --show-files --json  # review + capture source.archive_sha256
+  SOURCE_SHA256="<reviewed source.archive_sha256>"
+  strix cloud scans start --source . --approve-sha256 "$SOURCE_SHA256" --wait
+  strix cloud vulns list --severity critical
+  strix cloud billing topup --credits 20 --yes  # explicit approval after exit code 5
   ```
-  - API docs: https://docs.app.strix.ai (OpenAPI: https://docs.app.strix.ai/openapi.json).
+  - Account setup runs from the CLI too: `strix cloud workspaces list|create|use` (`workspace` is an alias and `use` accepts a displayed number, name, or ID), `strix cloud session scopes|scopes set`, `strix cloud org members invite`, `strix cloud billing subscribe --plan strix_cloud`, `strix cloud billing portal`, `strix cloud integrations install github`, and `strix cloud domains verify <id>`. Workspace switching preserves the server-side profile and can never widen past the login ceiling; ordinary switches do not reprompt. The last four end at a person: the command prints a link or a DNS record for the user to open or add, and it never completes the payment, installation, or DNS change for them.
+  - Every REST operation has a `strix cloud <resource> <verb>` command. Run `strix cloud` to list them. Output is JSON when stdout is not a terminal (or with `--json`), and there are no prompts without a TTY. Binary downloads are the exception: redirect raw bytes intentionally, or combine `--output FILE --json` for structured download metadata. Exit codes: `0` success, `1` error, `2` usage, `4` auth or plan limit, `5` payment required. `--token` or `STRIX_API_TOKEN` is a stateless override and never replaces stored auth; set `--workspace-id`/`STRIX_WORKSPACE_ID` for an override CLI session. `--data` adds extra request fields as JSON, and accepts `@file` or `-` for standard input.
+  - Local source uploads require `uploads:write`. For an agent/CI handoff, review `scans start --source . --dry-run --show-files --json`, capture `source.archive_sha256`, then rerun with the same `--source`, `--exclude`, and `--include-*` selection flags plus `--approve-sha256 HASH`. A changed snapshot is rejected. `--yes` approves only the snapshot built in that invocation, so reserve it for a deliberate human or one-shot approval rather than a digest-bound two-step handoff.
+  - Git ignores, hidden files, `.git`, symlinks, dependency/build output, secret-like filenames, and nested archives are excluded by default; `.strixignore` and `--exclude` narrow the manifest further (a trailing `/` excludes a directory subtree). Limits: 20,000 files, 25 MiB/file, 250 MiB expanded, 50 MiB compressed. Source-only infers `code_review`; source plus a domain infers `live_test`.
+  - The temporary local archive is always removed. A staged upload is deleted after a definitive rejection, but retained when a network error, `5xx`, malformed success response, or interruption leaves the scan launch ambiguous. JSON reports its `upload_id` with `launch_outcome_unknown: true`, or with `cleanup_unknown: true` when automatic deletion cannot be confirmed. Check `scans list` before retrying; if no scan is linked, run `uploads delete UPLOAD_ID`.
+  - Non-Enterprise scans consume the scope estimate (a default-tier source-only review currently starts at 60 credits); Enterprise scans are plan-included. A rejected launch does not consume credits.
+  - Human output is compact and numbered; non-TTY output and `--json` retain full records. Enable tab completion with `source <(strix completions zsh)` (or `bash`), or `strix completions fish | source`.
+  - The REST API works directly too: https://docs.app.strix.ai (OpenAPI: https://docs.app.strix.ai/openapi.json).
 
-- CLI docs index for LLMs: https://docs.strix.ai/llms.txt (full: https://docs.strix.ai/llms-full.txt).
+- CLI docs index for LLMs: https://docs.strix.ai/llms.txt (full: https://docs.strix.ai/llms-full.txt). Managed API docs for LLMs: https://docs.app.strix.ai/llms.txt.
 - Only scan targets the user is authorized to test.
 
 ## Contributing to this repo

CONTRIBUTING.md

@@ -31,7 +31,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g
 
 3. **Configure your LLM provider**
    ```bash
-   export STRIX_LLM="openai/gpt-5.4"
+   export STRIX_LLM="openrouter/z-ai/glm-5.3"
    export LLM_API_KEY="your-api-key"
    ```
 

README.md

@@ -17,6 +17,9 @@
 <a href="https://strix.ai"><img src="https://img.shields.io/badge/Website-strix.ai-f0f0f0?style=for-the-badge&logoColor=000000" alt="Website"></a>
 [![](https://dcbadge.limes.pink/api/server/strix-ai)](https://discord.gg/strix-ai)
 
+<a href="https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=badge_cloud"><img src="https://img.shields.io/badge/Strix%20Cloud-app.strix.ai-2b9246?style=for-the-badge&logoColor=white" alt="Strix Cloud"></a>
+<a href="https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=badge_demo"><img src="https://img.shields.io/badge/Try%20Strix%20Enterprise-555555?style=for-the-badge&logoColor=white" alt="Try Strix Enterprise"></a>
+
 <a href="https://deepwiki.com/usestrix/strix"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 <a href="https://github.com/usestrix/strix"><img src="https://img.shields.io/github/stars/usestrix/strix?style=flat-square" alt="GitHub Stars"></a>
 <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-3b82f6?style=flat-square" alt="License"></a>
@@ -34,7 +37,7 @@
 
 
 > [!TIP]
-> **New!** Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - [Get started with no setup required](https://app.strix.ai).
+> **New!** Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - [Get started with no setup required](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=tip_ci).
 
 ---
 
@@ -82,7 +85,7 @@ Strix are autonomous AI penetration testing agents that act just like real hacke
 curl -sSL https://strix.ai/install | bash
 
 # Configure your AI provider
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 
 # Run your first security assessment
@@ -94,9 +97,17 @@ strix --target ./app-directory
 
 ---
 
-## ☁️ Strix Platform
+## Ways to Run Strix
 
-Try the Strix full-stack penetration testing platform at **[app.strix.ai](https://app.strix.ai)** - sign up for free, connect your repos and domains, and launch a pentest in minutes.
+- **Open Source** - free, runs locally with Docker and your own LLM key. [Quick Start](https://docs.strix.ai/quickstart)
+- **Strix Cloud** - no setup, validated findings, one-click autofix, and PR reviews. [Run a pentest →](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=table_cloud)
+- **Enterprise** - SSO, compliance-ready reports, VPC or self-hosted deployment. [Try Strix Enterprise →](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=table_demo)
+
+---
+
+## ☁️ Strix Cloud
+
+Try the Strix full-stack penetration testing platform at **[app.strix.ai](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=cloud_heading)** - sign up for free, connect your repos and domains, and launch a pentest in minutes.
 
 - **Validated findings with PoCs** - every vulnerability includes a working proof-of-concept exploit and reproduction steps
 - **One-click autofix** - AI-generated security patches as ready-to-merge pull requests
@@ -104,7 +115,13 @@ Try the Strix full-stack penetration testing platform at **[app.strix.ai](https:
 - **DevSecOps integrations** - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines
 - **Continuous learning** - AI that builds on past findings, adapts to your codebase, and reduces false positives over time
 
-[**Start your first pentest →**](https://app.strix.ai)
+[**Run a pentest →**](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=cloud_cta)
+
+## 🏢 Enterprise
+
+Get the same Strix experience with enterprise-grade controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support and SLA, custom deployment options (VPC or self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment.
+
+[**Try Strix Enterprise →**](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=enterprise_cta)
 
 ---
 
@@ -116,7 +133,9 @@ Strix is agent-ready. Give Claude Code, Cursor, Codex, or any [SKILL.md-compatib
 npx skills add usestrix/strix
 ```
 
-This installs nine skills: **penetration-testing-with-strix** (run headless scans and read results), **managed-pentesting-with-strix** (drive the managed [app.strix.ai](https://app.strix.ai) platform via REST — no local Docker or LLM key), **fix-security-vulnerabilities-with-strix** (remediate + re-scan to verify), **ci-security-scanning-with-strix** (PR scanning in CI), plus target-specific workflows: **application-security-testing**, **web-app-penetration-testing**, **api-security-testing**, **owasp-top-10-testing**, and **find-security-vulnerabilities-in-code**. Agents can run Strix two ways with the same engine — the open-source CLI locally, or the managed cloud when there's no local infra — and read [`AGENTS.md`](AGENTS.md) for a quick reference, [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) for the CLI docs, and [docs.app.strix.ai](https://docs.app.strix.ai) for the API.
+This installs nine skills for running pentests, fixing findings, and CI scanning, against code, web apps, APIs, and the OWASP Top 10. Agents can use the local CLI or the managed cloud with the same engine.
+
+See [`AGENTS.md`](AGENTS.md) for the quick reference, [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) for the CLI, and [docs.app.strix.ai](https://docs.app.strix.ai) for the API.
 
 ---
 
@@ -172,18 +191,9 @@ strix view my-run-name
 strix view --host 0.0.0.0 --port 8080 --no-open
 ```
 
-`strix view` starts a lightweight local server (bound to `127.0.0.1` on a random port) and opens your browser to a private, tokened link. Nothing leaves your machine: the dashboard reads the run's files straight off disk, with no cloud account or upload required. The UI ships prebuilt with Strix, so there is no extra install and no JS build step.
+The dashboard shows the findings, a live map of the agent team, and past runs. Nothing leaves your machine, and the UI ships prebuilt. `strix view` binds to `127.0.0.1` and prints a tokened link that grants access to the run, so share it carefully.
 
-Use `--host 0.0.0.0` to make the viewer reachable from other machines. Replace `0.0.0.0` in the printed URL with the server's reachable IP or hostname. The token in that URL grants access to the selected run's scan data, history, and steering, so only share it with trusted users and restrict the port with your firewall. Requests without the token-derived session cannot read run data.
-
-### What's in the dashboard
-
-- **Overview**: run status, target, and a severity breakdown of everything found so far.
-- **Vulnerabilities**: each validated finding with its severity, details, and reproduction steps.
-- **Agent graph**: a live map of the multi-agent team, showing which agent is doing what.
-- **Steering**: send instructions to a live scan from the browser to redirect the agents mid-run.
-- **History**: browse past runs on this machine and jump between them.
-- **Reports**: generate a shareable report and email it to yourself or your team.
+See the [viewer documentation](https://docs.strix.ai/usage/viewer) for the options and for reaching the viewer from another machine.
 
 ---
 
@@ -209,18 +219,9 @@ having to discover them by crawling. Pair the spec with the live base URL so the
 agent knows where to send traffic:
 
 ```bash
-# OpenAPI / Swagger file (.json / .yaml)
+# OpenAPI / Swagger file, Postman export, or a live collection by id
 strix --target ./openapi.yaml --target https://api.your-app.com
-
-# Postman collection export
-strix --target ./collection.postman_collection.json --target https://api.your-app.com
-
-# Postman collection pulled live by id (no manual export)
-export POSTMAN_API_KEY="PMAK-..."
-strix --target postman://<collection-uuid>
-
-# ...with a Postman environment to resolve {{baseUrl}} / token variables
-strix --target "postman://<collection-uuid>?env=<environment-uuid>"
+strix --target postman://<collection-uuid> --target https://api.your-app.com
 ```
 
 
@@ -235,20 +236,10 @@ strix -t https://github.com/org/app -t https://your-app.com
 
 # Targets from a file, one target per non-empty, non-comment line
 strix --target-list ./targets.txt
-
-# White-box source-aware scan (local repository)
-strix --target ./app-directory --scan-mode standard
-
-# Focused testing with custom instructions
-strix --target api.your-app.com --instruction "Focus on business logic flaws and IDOR vulnerabilities"
-
-# Provide detailed instructions through file (e.g., rules of engagement, scope, exclusions)
-strix --target api.your-app.com --instruction-file ./instruction.md
-
-# Force PR diff-scope against a specific base branch
-strix -n --target ./ --scan-mode quick --scope-mode diff --diff-base origin/main
 ```
 
+See the [CLI reference](https://docs.strix.ai/usage/cli) for every option, including scan modes, diff scope, instruction files, and budgets.
+
 ### Headless Mode
 
 Run Strix programmatically without interactive UI using the `-n/--non-interactive` flag - perfect for servers and automated jobs. The CLI prints real-time vulnerability findings and the final report before exiting. Exits with non-zero code when vulnerabilities are found.
@@ -287,63 +278,55 @@ jobs:
 ```
 
 > [!TIP]
-> In CI pull request runs, Strix automatically scopes quick reviews to changed files.
-> If diff-scope cannot resolve, ensure checkout uses full history (`fetch-depth: 0`) or pass
-> `--diff-base` explicitly.
+> In CI pull request runs, Strix automatically scopes quick reviews to changed files, which is why the
+> checkout above fetches full history. See the
+> [CI/CD documentation](https://docs.strix.ai/integrations/github-actions) for the details.
 
 ### Configuration
 
 ```bash
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 
 # Optional
 export LLM_API_BASE="your-api-base-url"  # if using a local model, e.g. Ollama, LMStudio
-export PERPLEXITY_API_KEY="your-api-key"  # for search capabilities
-export STRIX_REASONING_EFFORT="high"  # control thinking effort (default: high, quick scan: medium)
 ```
 
 > [!NOTE]
 > Strix automatically saves your configuration to `~/.strix/cli-config.json`, so you don't have to re-enter it on every run.
+> See the [configuration reference](https://docs.strix.ai/advanced/configuration) for every environment variable.
 
 #### Sign in with a ChatGPT subscription
 
 Instead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscription:
 
 ```bash
-strix auth login chatgpt      # sign in with your ChatGPT account
-
+strix auth login chatgpt             # sign in with your ChatGPT account
 export STRIX_LLM="chatgpt/gpt-5.4"   # chatgpt/<model> runs on the subscription
-strix --target ./app-directory
-
-strix auth status             # show the active sign-in
-strix auth logout             # forget the sign-in
+strix auth status                    # show the active sign-in, or logout to forget it
 ```
 
-#### Sign in with an OpenCode subscription
+#### Use the managed platform: `strix cloud`
 
-You can also run Strix on [OpenCode Zen](https://opencode.ai/docs/zen/) credits or an [OpenCode Go](https://opencode.ai/docs/go/) subscription:
+Run scans on [app.strix.ai](https://app.strix.ai) from the terminal, without Docker or an LLM key:
 
 ```bash
-strix auth login opencode     # paste your API key from opencode.ai/auth
-
-export STRIX_LLM="opencode/claude-sonnet-5"   # opencode/<model> runs on Zen credits
-export STRIX_LLM="opencode-go/kimi-k3"        # opencode-go/<model> runs on the Go subscription
-strix --target ./app-directory
+strix cloud login                                  # browser sign-in, one credential per install
+strix cloud scans start --source . --yes --wait    # scan local code, approving the upload
+strix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait
+strix cloud vulns list --severity critical
 ```
 
+Every [REST API](https://docs.app.strix.ai) operation has a matching `strix cloud <resource> <verb>` command. Run `strix cloud` to list the resources, and add `help` to a resource to list its verbs. Output is JSON when stdout is not a terminal or when you pass `--json`. Binary downloads are the exception: redirect the raw bytes, or combine `--output FILE --json` for download metadata.
+
+See the [cloud CLI documentation](https://docs.strix.ai/cloud/cli) for scopes, workspaces, billing, and source-upload options.
+
 #### Connect your own MCP servers
 
-Strix can connect to Model Context Protocol (MCP) servers you list and expose their tools to the agent during a run. Create `~/.strix/mcp-servers.json` with a JSON list of servers. Each entry is either a local `stdio` server that Strix launches as a subprocess, or a remote `http` server:
+Strix can connect to Model Context Protocol (MCP) servers you list and expose their tools to the agent during a run. Create `~/.strix/mcp-servers.json` with a JSON list of local `stdio` servers or remote `http` servers:
 
 ```json
 [
-  {
-    "name": "local_fs",
-    "transport": "stdio",
-    "command": "npx",
-    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
-  },
   {
     "name": "github",
     "transport": "http",
@@ -354,20 +337,19 @@ Strix can connect to Model Context Protocol (MCP) servers you list and expose th
 ]
 ```
 
-Each server's tools are namespaced by `name` (for example `local_fs_read_file`). Omit `allowed_tools` to expose every tool the server offers, or set it to a list to restrict which tools the agent can call. The file is optional, and a server that fails to connect is skipped without failing the run. You can point Strix at a different file with `STRIX_MCP_CONFIG`.
+Each server's tools are namespaced by `name`, for example `github_list_issues`. See the [MCP documentation](https://docs.strix.ai/integrations/mcp) for the full schema, tool filtering, and `stdio` servers.
 
 **Recommended models for best results:**
 
+- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (the default pick)
 - [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`
 - [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) - `anthropic/claude-sonnet-4-6`
 - [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3-pro-preview`
+- [DeepSeek V4 Pro](https://platform.deepseek.com) - `deepseek/deepseek-v4-pro`
+- [Moonshot Kimi K3](https://platform.kimi.ai) - `moonshot/kimi-k3`
 
 See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.
 
-## Enterprise Pentesting
-
-Get the same Strix experience with [enterprise-grade](https://strix.ai/demo) controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support & SLA, custom deployment options (VPC/self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment. [Learn more](https://strix.ai/demo).
-
 ## Documentation
 
 Full documentation is available at **[docs.strix.ai](https://docs.strix.ai)** - including detailed guides for usage, CI/CD integrations, skills, and advanced configuration.

docs/advanced/configuration.mdx

@@ -8,7 +8,7 @@ Configure Strix using environment variables or a config file.
 ## LLM Configuration
 
 <ParamField path="STRIX_LLM" type="string" required>
-  Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
+  Model name in LiteLLM format (e.g., `openrouter/z-ai/glm-5.3`, `openai/gpt-5.4`).
 </ParamField>
 
 <ParamField path="LLM_API_KEY" type="string">
@@ -80,6 +80,22 @@ affecting the agents that do the actual testing.
   API key for Perplexity AI. Enables real-time web search during scans for OSINT and vulnerability research.
 </ParamField>
 
+<ParamField path="EXA_API_KEY" type="string">
+  API key for Exa. Enables real-time web search through the Exa `/search` endpoint. Exa also powers the `web_get_contents` tool, which fetches the full text of a page through the Exa `/contents` endpoint. This is the preferred web search provider.
+</ParamField>
+
+<ParamField path="STRIX_WEB_SEARCH_PROVIDER" default="auto" type="string">
+  Web search provider: `auto`, `perplexity`, or `exa`. With `auto`, Strix uses Exa when `EXA_API_KEY` is set, and Perplexity otherwise. Set an explicit provider to pin one when you configure both keys.
+</ParamField>
+
+<ParamField path="STRIX_EXA_SEARCH_TYPE" default="auto" type="string">
+  Exa search mode: `auto`, `fast`, `instant`, `deep-lite`, `deep`, or `deep-reasoning`. Lower modes return results faster. Higher modes plan across more steps and take more time. This setting applies only to the Exa provider.
+</ParamField>
+
+<ParamField path="STRIX_EXA_NUM_RESULTS" default="5" type="integer">
+  Number of Exa results to return, from `1` to `100`. Each result includes a title, a URL, and a short security-focused summary. To read a full page, the agent calls `web_get_contents` with the result URL. This setting applies only to the Exa provider.
+</ParamField>
+
 <ParamField path="POSTMAN_API_KEY" type="string">
   Postman API key (`PMAK-…`). Enables fetching Postman collections by id as a target (`postman://<collection-uid>`), and Postman environments (`postman://<collection-uid>?env=<environment-uid>`) to resolve collection variables. Not needed when passing a local collection export file.
 </ParamField>
@@ -145,7 +161,7 @@ strix --target ./app --config /path/to/config.json
 ```json
 {
   "env": {
-    "STRIX_LLM": "openai/gpt-5.4",
+    "STRIX_LLM": "openrouter/z-ai/glm-5.3",
     "LLM_API_KEY": "sk-...",
     "STRIX_REASONING_EFFORT": "high"
   }
@@ -156,10 +172,11 @@ strix --target ./app --config /path/to/config.json
 
 ```bash
 # Required
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="sk-..."
 
-# Optional: Enable web search
+# Optional: Enable web search (Exa preferred, Perplexity supported)
+export EXA_API_KEY="..."
 export PERPLEXITY_API_KEY="pplx-..."
 
 # Optional: Custom timeouts

docs/cloud/cli.mdx

@@ -0,0 +1,103 @@
+---
+title: "Cloud CLI"
+description: "Drive app.strix.ai from the terminal with strix cloud"
+---
+
+The `strix cloud` commands drive the managed platform ([app.strix.ai](https://app.strix.ai)) from the terminal. You do not need Docker or an LLM key.
+
+## Sign In
+
+Sign in once with the browser device flow. The sign-in creates your account and workspace on first use, and it stores a personal API token in `~/.strix/platform-auth.json`.
+
+```bash
+strix cloud login                         # browser approval, then workspace and scope profile
+strix cloud login --workspace "My Team"   # select a workspace by name or ID
+strix cloud whoami                        # local account and workspace status
+strix cloud session                       # verify the remote session and consent ceiling
+strix cloud logout                        # revoke remotely, then remove the local token
+```
+
+A browser sign-in creates one reusable credential for each CLI installation. A second sign-in on the same installation replaces the secret instead of adding another key. `strix cloud logout` revokes the server session before it deletes the local token. Use `--local-only` when you cannot reach the server.
+
+## Scopes
+
+The default **Recommended** preset covers normal scan work, local source uploads, workspace switching, and user-approved credit top-ups. It excludes credential creation, so request `tokens:write` when you need it.
+
+```bash
+strix cloud login --scopes scans:read scans:write uploads:write billing:read
+strix cloud login --scope-profile minimal   # also accepts recommended or full
+strix cloud session scopes                  # granted scopes and the login ceiling
+strix cloud session scopes set minimal      # narrow without another browser sign-in
+```
+
+A workspace switch keeps the credential and its expiry, preserves the server-side scope preference, and caps access by the target role. A switch can never exceed the login consent ceiling. Each process pins the workspace it started with, so a concurrent switch fails safely instead of sending a stale command to another organization.
+
+## Commands
+
+Every operation of the [REST API](https://docs.app.strix.ai) has a matching command in the form `strix cloud <resource> <verb>`.
+
+```bash
+strix cloud                                   # list all resources
+strix cloud scans                             # run the safe default (scans list)
+strix cloud scans help                        # list the verbs of a resource
+strix cloud domains add --domain example.com --asset-type web_app
+strix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait
+strix cloud vulns list --severity critical
+strix cloud credits                           # credit balance
+```
+
+Write commands take request fields as flags. Every write command also accepts one JSON object with `--data`:
+
+```bash
+strix cloud scans start --data '{"engagement_type":"code_review"}'   # literal JSON
+strix cloud scans start --data @request.json                         # read a file
+cat request.json | strix cloud scans start --data -                  # read standard input
+```
+
+`--token` and `STRIX_API_TOKEN` are stateless overrides for a single command, and they never replace the stored sign-in. Pair a CLI-session override with `--workspace-id` or `STRIX_WORKSPACE_ID`.
+
+## Workspaces And Account Setup
+
+```bash
+strix cloud workspaces list                       # numbered list; workspace is also accepted
+strix cloud workspaces create --name "My Team"    # needs admin and organizations:write
+strix cloud workspaces use 2                      # switch by list number, exact name, or ID
+strix cloud billing topup --credits 20 --yes      # approve an agent payment after HTTP 402
+strix cloud billing subscribe --plan strix_cloud  # opens the hosted checkout page
+strix cloud billing portal                        # opens the billing portal
+strix cloud integrations install github           # opens the app installation page
+strix cloud domains verify <domain-id>            # prints the DNS record to add
+```
+
+The last four commands end at a person. Strix creates the link, opens the browser for an interactive terminal, and always prints the URL. The user enters the card, approves the installation, or adds the DNS record. Pass `--no-browser` to print the URL only.
+
+## Output And Exit Codes
+
+The commands work for people and for agents. Terminal output favors names, branches, lifecycle states, and numbered selectors. Redirected output, and `--json`, preserve the complete machine-readable record.
+
+- Human lists keep the selectors that follow-up commands need, and they omit internal organization and user IDs. A selector that is too long for the compact table is repeated losslessly in a copyable block.
+- Paginated lists print the next `--page` or `--offset`. Detail views keep useful prose within a safe terminal bound, so use `--json` for the complete record.
+- Token lists separate API keys from named CLI device sessions.
+- Binary downloads are the exception to JSON output. Redirect the raw bytes on purpose, or use `--output FILE --json` to write the file and receive structured download metadata.
+- There are no prompts when stdin is not a terminal.
+
+Exit codes: `0` success, `1` error, `2` invalid usage, `4` authentication or plan limit, `5` payment required.
+
+## Credits And Plan Limits
+
+Non-Enterprise scans consume the deterministic estimate shown for their scope. A source-only code review at the default `ultra` tier currently starts at 60 credits. Enterprise scans are plan-included and do not consume the credit wallet.
+
+Report downloads need Enterprise, schedules need Pro, and billing writes need an admin token. A plan block exits `4`. An insufficient credit wallet exits `5` without the creation of a scan and without a charge.
+
+## Local Source Scans
+
+See [Scan Local Source](/cloud/overview#scan-local-source) for the upload approval flow, the exclusion rules, and the size limits.
+
+## Tab Completion
+
+Enable native tab completion once for each shell session:
+
+```bash
+source <(strix completions zsh)       # use bash instead of zsh when appropriate
+strix completions fish | source
+```

docs/cloud/overview.mdx

@@ -35,6 +35,25 @@ Skip the setup. Run Strix in the cloud at [app.strix.ai](https://app.strix.ai).
 2. Connect your repository or enter a target URL
 3. Launch your first scan
 
+## Scan Local Source
+
+Send a local working tree to the managed white-box scanner without connecting a source-control provider:
+
+```bash
+# Review the exact file manifest and capture source.archive_sha256. Nothing is uploaded.
+strix cloud scans start --source . --dry-run --show-files --json
+SOURCE_SHA256="<reviewed source.archive_sha256>"
+
+# Repeat the same source-selection flags and approve that exact snapshot.
+strix cloud scans start --source . --approve-sha256 "$SOURCE_SHA256" --wait
+```
+
+In a Git repository, Strix includes tracked files and untracked files that are not ignored. Hidden files, `.git`, symlinks, dependencies and build output, secret-like filenames, and nested archives are excluded by default. Use `.strixignore` or repeat `--exclude GLOB` for project-specific exclusions. `--include-hidden`, `--include-sensitive`, and `--include-archives` are explicit opt-ins.
+
+The CLI limits individual files, total expanded bytes, archive bytes, and file count. For an agent or CI handoff, repeat the same `--source`, `--exclude`, and `--include-*` flags with `--approve-sha256`; Strix refuses the upload if the rebuilt archive differs from the reviewed digest. `--yes` is a one-invocation approval for the snapshot built at that moment, not a digest-bound two-step approval.
+
+The temporary local archive is always removed. After a definitive launch rejection, Strix also deletes the staged remote upload. If a network error, server error, or interruption makes the launch outcome ambiguous, it retains the upload and reports its ID; check `strix cloud scans list` before retrying, then delete an unlinked upload with `strix cloud uploads delete UPLOAD_ID`.
+
 <Card title="Try Strix Cloud" icon="rocket" href="https://app.strix.ai">
   Run your first pentest in minutes.
 </Card>

docs/contributing.mdx

@@ -33,7 +33,7 @@ description: "Contribute to Strix development"
   </Step>
   <Step title="Configure LLM">
     ```bash
-    export STRIX_LLM="openai/gpt-5.4"
+    export STRIX_LLM="openrouter/z-ai/glm-5.3"
     export LLM_API_KEY="your-api-key"
     ```
   </Step>

docs/docs.json

@@ -25,7 +25,8 @@
             "pages": [
               "usage/cli",
               "usage/scan-modes",
-              "usage/instructions"
+              "usage/instructions",
+              "usage/viewer"
             ]
           },
           {
@@ -35,6 +36,7 @@
               "llm-providers/openai",
               "llm-providers/anthropic",
               "llm-providers/openrouter",
+              "llm-providers/vercel-ai-gateway",
               "llm-providers/vertex",
               "llm-providers/bedrock",
               "llm-providers/azure",
@@ -77,7 +79,8 @@
           {
             "group": "Strix Cloud",
             "pages": [
-              "cloud/overview"
+              "cloud/overview",
+              "cloud/cli"
             ]
           }
         ]

docs/index.mdx

@@ -78,7 +78,7 @@ Strix uses a graph of specialized agents for comprehensive security testing:
 curl -sSL https://strix.ai/install | bash
 
 # Configure
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 
 # Scan

docs/integrations/coding-agents.mdx

@@ -36,13 +36,14 @@ npx skills use usestrix/strix@penetration-testing-with-strix | claude
 Both use the same engine and produce the same validated findings and SARIF, so agents can pick per situation or combine them:
 
 - **Open-source CLI (self-hosted)** — runs locally in a Docker sandbox with your own LLM key. Free, fully local, air-gap capable. Best for local dev loops and full control.
-- **Managed cloud** — runs on Strix's infrastructure via the [app.strix.ai REST API](https://docs.app.strix.ai). No Docker, no LLM key, no local install; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Create an API token under **Settings → API Access**; the `managed-pentesting-with-strix` skill has the full flow.
+- **Managed cloud** — runs on Strix's infrastructure. Drive it with the `strix cloud` CLI (every REST operation has a `strix cloud <resource> <verb>` command) or the [app.strix.ai REST API](https://docs.app.strix.ai) directly. No Docker, no LLM key; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Sign in with `strix cloud login` (browser device sign-in, account created on first use) or create a token in the dashboard under **Settings → API Access**. The `managed-pentesting-with-strix` skill has the full flow.
 
 ## Agent-Friendly Interfaces
 
 Everything an agent needs is machine-readable:
 
 - **Headless CLI** — `strix -n` runs without the TUI and exits with `0` (clean), `1` (error), or `2` (vulnerabilities found).
+- **Cloud CLI** — `strix cloud` prints JSON when stdout is not a terminal (or with `--json`), never prompts without a TTY, and exits with `0` (success), `1` (error), `2` (usage), `4` (authentication required), or `5` (payment required). Credit top-ups pay the Stripe machine-payment challenge with an agent wallet (`strix cloud billing topup --credits N --yes`). Account setup also runs from the CLI: `strix cloud workspaces list|create|use`, `strix cloud org members invite`, `strix cloud billing subscribe`, `strix cloud billing portal`, and `strix cloud integrations install github`. The last three print a hosted link the user opens to finish the payment or approve the installation.
 - **REST API** — the managed platform exposes a documented [OpenAPI](https://docs.app.strix.ai/openapi.json) at `https://app.strix.ai/api/v1` (scans, vulnerabilities, assets, PR reviews, schedules, webhooks) with bearer tokens and scopes.
 - **Structured results** — every run writes `vulnerabilities.json`, `vulnerabilities.csv`, `findings.sarif` (SARIF 2.1.0), and per-finding Markdown under `strix_runs/<run-name>/`; the cloud exposes the same as JSON plus SARIF export.
 - **Budget controls** — `--max-budget` and `--max-turns` give agents hard cost/time caps.

docs/integrations/github-actions.mdx

@@ -37,7 +37,7 @@ Add these secrets to your repository:
 
 | Secret | Description |
 |--------|-------------|
-| `STRIX_LLM` | Model name (e.g., `openai/gpt-5.4`) |
+| `STRIX_LLM` | Model name (e.g., `openrouter/z-ai/glm-5.3`) |
 | `LLM_API_KEY` | API key for your LLM provider |
 
 ## Exit Codes

docs/llm-providers/novita.mdx

@@ -17,6 +17,9 @@ export LLM_API_BASE="https://api.novita.ai/openai"
 
 | Model | Configuration |
 |-------|---------------|
+| GLM-5.3 | `openai/zai-org/glm-5.3` |
+| Kimi K3 | `openai/moonshotai/kimi-k3` |
+| DeepSeek V4 Pro | `openai/deepseek/deepseek-v4-pro` |
 | Kimi K2.5 | `openai/moonshotai/kimi-k2.5` |
 | GLM-5 | `openai/zai-org/glm-5` |
 | MiniMax M2.5 | `openai/minimax/minimax-m2.5` |

docs/llm-providers/openrouter.mdx

@@ -8,7 +8,7 @@ description: "Configure Strix with models via OpenRouter"
 ## Setup
 
 ```bash
-export STRIX_LLM="openrouter/openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="sk-or-..."
 ```
 
@@ -18,9 +18,12 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:
 
 | Model | Configuration |
 |-------|---------------|
+| GLM-5.3 (default) | `openrouter/z-ai/glm-5.3` |
 | GPT-5.4 | `openrouter/openai/gpt-5.4` |
 | Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` |
 | Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` |
+| DeepSeek V4 Pro | `openrouter/deepseek/deepseek-v4-pro` |
+| Kimi K3 | `openrouter/moonshotai/kimi-k3` |
 | GLM-4.7 | `openrouter/z-ai/glm-4.7` |
 
 ## Get API Key

docs/llm-providers/overview.mdx

@@ -9,14 +9,17 @@ Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibi
 
 Set your model and API key:
 
-| Model             | Provider      | Configuration                    |
-| ----------------- | ------------- | -------------------------------- |
-| GPT-5.4           | OpenAI        | `openai/gpt-5.4`                 |
-| Claude Sonnet 4.6 | Anthropic     | `anthropic/claude-sonnet-4-6`    |
-| Gemini 3 Pro      | Google Vertex | `vertex_ai/gemini-3-pro-preview` |
+| Model                | Provider          | Configuration                    |
+| -------------------- | ----------------- | -------------------------------- |
+| GLM-5.3 (default)    | Z.ai (OpenRouter) | `openrouter/z-ai/glm-5.3`        |
+| GPT-5.4              | OpenAI            | `openai/gpt-5.4`                 |
+| Claude Sonnet 4.6    | Anthropic         | `anthropic/claude-sonnet-4-6`    |
+| Gemini 3 Pro         | Google Vertex     | `vertex_ai/gemini-3-pro-preview` |
+| DeepSeek V4 Pro      | DeepSeek          | `deepseek/deepseek-v4-pro`       |
+| Kimi K3              | Moonshot          | `moonshot/kimi-k3`               |
 
 ```bash
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 ```
 
@@ -43,6 +46,9 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
   <Card title="OpenRouter" href="/llm-providers/openrouter">
     Access 100+ models through a single API.
   </Card>
+  <Card title="Vercel AI Gateway" href="/llm-providers/vercel-ai-gateway">
+    Access models from multiple providers through one endpoint.
+  </Card>
   <Card title="Google Vertex AI" href="/llm-providers/vertex">
     Gemini 3 models via Google Cloud.
   </Card>
@@ -62,6 +68,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
 Use LiteLLM's `provider/model-name` format:
 
 ```
+openrouter/z-ai/glm-5.3
 openai/gpt-5.4
 anthropic/claude-sonnet-4-6
 vertex_ai/gemini-3-pro-preview

docs/llm-providers/vercel-ai-gateway.mdx

@@ -0,0 +1,39 @@
+---
+title: "Vercel AI Gateway"
+description: "Configure Strix with models via Vercel AI Gateway"
+---
+
+[Vercel AI Gateway](https://vercel.com/docs/ai-gateway) provides an OpenAI-compatible API for models from multiple providers.
+
+## Setup
+
+Create an [AI Gateway API key](https://vercel.com/docs/ai-gateway/authentication-and-byok), then configure Strix:
+
+```bash
+export STRIX_LLM="openai/anthropic/claude-opus-5"
+export LLM_API_KEY="your-ai-gateway-api-key"
+export LLM_API_BASE="https://ai-gateway.vercel.sh/v1"
+```
+
+The first `openai/` segment tells Strix to use its OpenAI-compatible client. The remaining value is the [AI Gateway model ID](https://vercel.com/docs/ai-gateway/models-and-providers).
+
+## Available Models
+
+Use any language model returned by the AI Gateway models endpoint:
+
+```text
+https://ai-gateway.vercel.sh/v1/models
+```
+
+Prefix its model ID with `openai/` when setting `STRIX_LLM`. For example, the Gateway model ID `anthropic/claude-opus-5` becomes `openai/anthropic/claude-opus-5` in Strix.
+
+## Get API Key
+
+1. Open the [AI Gateway API key settings](https://vercel.com/docs/ai-gateway/authentication-and-byok)
+2. Create an API key
+3. Set the key as `LLM_API_KEY`
+
+## Benefits
+
+- Access models from multiple providers through one endpoint
+- Track Gateway usage and cost in Vercel

docs/quickstart.mdx

@@ -28,12 +28,12 @@ description: "Install Strix and run your first security scan"
 Set your LLM provider:
 
 ```bash
-export STRIX_LLM="openai/gpt-5.4"
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 ```
 
 <Tip>
-For best results, use `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
+For best results, use `openrouter/z-ai/glm-5.3` (the default pick), `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
 </Tip>
 
 ## Run Your First Scan

docs/tools/overview.mdx

@@ -28,6 +28,6 @@ Strix agents use specialized tools to test your applications like a real penetra
 | -------------- | ---------------------------------------- |
 | Python Runtime | Write and execute custom exploit scripts |
 | File Editor    | Read and modify source code              |
-| Web Search     | Real-time OSINT via Perplexity           |
+| Web Search     | Real-time OSINT with Exa or Perplexity   |
 | Notes          | Document findings during the scan        |
 | Reporting      | Generate vulnerability reports with PoCs |

docs/usage/viewer.mdx

@@ -0,0 +1,49 @@
+---
+title: "Local Web Viewer"
+description: "Browse a run in a local dashboard with strix view"
+---
+
+Every scan writes its results to disk as it runs. `strix view` serves those files in a local dashboard, for a live run or a finished one.
+
+```bash
+strix view                                    # the most recent run
+strix view my-run-name                        # a specific run under ./strix_runs
+strix view --host 0.0.0.0 --port 8080 --no-open
+```
+
+The UI ships prebuilt with Strix, so there is no extra install and no JavaScript build step. The dashboard reads the run files straight off disk. Nothing leaves your machine, and you do not need a cloud account.
+
+## Options
+
+<ParamField path="run" type="string">
+  Run name under `./strix_runs`. Defaults to the most recent run.
+</ParamField>
+
+<ParamField path="--host" type="string" default="127.0.0.1">
+  Host to bind to. Use `0.0.0.0` to reach the viewer from other machines.
+</ParamField>
+
+<ParamField path="--port" type="number" default="0">
+  Port to serve on. The default selects an available ephemeral port.
+</ParamField>
+
+<ParamField path="--no-open" type="boolean">
+  Do not open the browser automatically.
+</ParamField>
+
+## What Is In The Dashboard
+
+- **Overview** — run status, target, and a severity breakdown of everything found so far.
+- **Vulnerabilities** — each validated finding with its severity, details, and reproduction steps.
+- **Agent graph** — a live map of the multi-agent team, and what each agent is doing.
+- **Steering** — send instructions to a live scan to redirect the agents during the run. Steering works only in the dashboard the running scan opens. A standalone `strix view` has no live scan to steer.
+- **History** — browse past runs on this machine and move between them. Verify your email address in the dashboard to unlock the other runs.
+- **Reports** — generate a shareable report and send it by email. Verify your email address first.
+
+## Sharing The Link
+
+<Warning>
+  The token in the printed URL grants access to the run data, and to the steering of a live scan. Share it only with trusted users.
+</Warning>
+
+To reach the viewer from another machine, start it with `--host 0.0.0.0` and replace `0.0.0.0` in the printed URL with a reachable IP address or hostname. Restrict the port with your firewall. A request without the token-derived session cannot read run data.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "strix-agent"
-version = "1.5.3"
+version = "1.6.2"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"
@@ -43,6 +43,7 @@ dependencies = [
   "requests>=2.32.0",
   "cvss>=3.2",
   "caido-sdk-client>=0.2.0",
+  "markdown-it-py>=3.0.0",
   "reportlab>=4.0",
   "pypdf>=5.0",
   # Cap <49: 49.x drops the universal2 macOS wheel (arm64-only), which breaks
@@ -229,6 +230,7 @@ ignore = [
 # Test doubles use fixture tokens/passwords and match a callee signature whose
 # args they intentionally ignore.
 "tests/test_viewer_auth.py" = ["S105", "S106", "ARG001"]
+"tests/test_cloud_cli.py" = ["S105", "ARG001"]
 "tests/test_codex_auth.py" = ["S105", "S106", "SLF001"]
 # Hatchling loads the build hook by path, not as an importable package.
 "scripts/tui_sidecar_hook.py" = ["INP001"]
@@ -248,6 +250,7 @@ ignore = [
 # Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a
 # circular dependency with strix.telemetry / strix.interface.viewer.report_pdf.
 "strix/interface/viewer/server.py" = ["N802", "PLC0415"]
+"strix/interface/cloud/payment_proxy.py" = ["N802"]
 # Lazy telemetry import to avoid importing PostHog before the viewer starts.
 "strix/interface/viewer/cli.py" = ["PLC0415"]
 # Lazy imports inside functions to avoid circular dependency with
@@ -308,7 +311,6 @@ ignore = [
 # Heavy inference deps (httpx, openai) imported lazily so auth-status checks
 # don't pull them in.
 "strix/config/codex.py" = ["PLC0415"]
-"strix/config/opencode.py" = ["PLC0415"]
 # Interface utility branches per scope-mode / target-type combination;
 # splitting would obscure the decision tree without simplifying it.
 "strix/interface/utils.py" = ["PLR0912", "BLE001", "PLC0415"]
@@ -412,6 +414,8 @@ known_third_party = ["pydantic", "litellm"]
 # ============================================================================
 
 [tool.bandit]
-exclude_dirs = ["docs", "build", "dist"]
+# Tests are covered by ruff's flake8-bandit rules (see per-file-ignores above),
+# which is where fixture tokens and loopback URL opens are already waived.
+exclude_dirs = ["docs", "build", "dist", "tests"]
 skips = ["B101", "B601", "B404", "B603", "B607"]  # Skip assert, shell injection, subprocess import and partial path checks
 severity = "medium"

scripts/install.sh

@@ -346,6 +346,9 @@ echo -e "${MUTED}For more information visit ${NC}https://strix.ai"
 echo -e "${MUTED}Supported models ${NC}https://docs.strix.ai/llm-providers/overview"
 echo -e "${MUTED}Join our community ${NC}https://discord.gg/strix-ai"
 echo ""
+echo -e "${MUTED}Run a pentest in Strix Cloud ${NC}https://app.strix.ai"
+echo -e "${MUTED}Enterprise ${NC}https://strix.ai/demo"
+echo ""
 
 echo -e "${YELLOW}→${NC} Run ${MUTED}source ~/.$(basename $SHELL)rc${NC} or open a new terminal"
 echo ""

skills/api-security-testing/SKILL.md

@@ -11,7 +11,7 @@ metadata:
 
 APIs fail differently from web UIs: there is no rendered surface to crawl, the interesting bugs are authorization-shaped rather than injection-shaped, and the same endpoint behaves differently per token. This workflow targets those specifics with Strix's autonomous agents, using the current [OWASP API Security Top 10 (2023)](https://owasp.org/API-Security/editions/2023/en/0x11-t10/) as the coverage checklist. For the web-app equivalent, the current edition is the OWASP Top 10:2025 — see **owasp-top-10-testing**.
 
-Install, LLM setup, full CLI flags, and the managed-cloud path are in the **penetration-testing-with-strix** skill. Read it if `strix --version` fails or the target is not an API.
+Install, LLM setup, full CLI flags, and the managed-cloud path are in the **penetration-testing-with-strix** skill. Read it if `strix --version` fails or the target is not an API. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**).
 
 ## 1. Gather what the agents need
 

skills/application-security-testing/SKILL.md

@@ -11,7 +11,7 @@ metadata:
 
 Entry point for "make my application secure" requests, where the target is not yet a single URL or repo. The job here is to pick the right test per asset, run it, and produce one ranked plan — not to run everything at maximum depth.
 
-Install, LLM setup, all CLI flags, and the managed-cloud path live in the **penetration-testing-with-strix** skill. Read it first if `strix --version` fails.
+Install, LLM setup, all CLI flags, and the managed-cloud path live in the **penetration-testing-with-strix** skill. Read it first if `strix --version` fails. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**).
 
 Only test assets the user owns or is authorized to test. Confirm authorization before the first run, and prefer staging over production, because the agents send real exploit payloads and can change data.
 

skills/ci-security-scanning-with-strix/SKILL.md

@@ -113,11 +113,11 @@ Gate the pipeline on the exit code (see the budget/fail-open caveat above — gi
 
 # Option B — Managed platform (no runner infra)
 
-No workflow file, no Docker, no LLM key. Two ways to use it:
+No workflow file, no Docker, no LLM key. Three ways to use it:
 
 1. **PR-review app (zero code):** the user installs the Strix GitHub/GitLab/Bitbucket app and enables PR reviews for the repo in the app.strix.ai dashboard. Every PR is then reviewed automatically, with findings posted as PR comments. Nothing to add to the repo. This is the lowest-effort path — recommend it first when the user just wants PR gating.
 
-2. **API-triggered from any pipeline:** if you want to trigger from an existing pipeline (or a system without the SCM app), call the API with a token that has `pr_reviews:write` (or `scans:write`). Store the token as a CI secret; ask the user to create it at **Settings → API Access**. Example GitHub Actions step:
+2. **CLI-triggered from any pipeline:** if you want to trigger from an existing pipeline (or a system without the SCM app), use the same `strix` binary with a token that has `pr_reviews:write`. Store the token as a CI secret and ask the user to create it at **Settings → API Access**. Read the repository's `provider` and `installation_id` once with `strix cloud repos list`. Example GitHub Actions step:
 
    ```yaml
    - name: Strix PR review (managed)
@@ -125,12 +125,25 @@ No workflow file, no Docker, no LLM key. Two ways to use it:
      env:
        STRIX_API_TOKEN: ${{ secrets.STRIX_API_TOKEN }}
      run: |
-       curl -sS --fail https://app.strix.ai/api/v1/pr-reviews/start \
-         -H "Authorization: Bearer $STRIX_API_TOKEN" \
-         -H "Content-Type: application/json" \
-         -d "{\"repository_full_name\":\"${{ github.repository }}\",\"pr_number\":${{ github.event.pull_request.number }}}"
+       curl -sSL https://strix.ai/install | bash
+       strix cloud pr-reviews start \
+         --provider github \
+         --installation-id "${{ vars.STRIX_INSTALLATION_ID }}" \
+         --repository-full-name "${{ github.repository }}" \
+         --pr-number "${{ github.event.pull_request.number }}"
    ```
 
-   To gate the build on results, poll the PR review / scan status and fail on unresolved criticals/highs. Full endpoints (PR reviews, scans, SARIF export, schedules for scheduled deep scans) are in the **managed-pentesting-with-strix** skill.
+   Output is JSON when stdout is not a terminal, and there are no prompts without a TTY. To gate the build on results, poll `strix cloud pr-reviews get <id> --json` and fail on unresolved criticals or highs. The raw REST endpoint (`POST /api/v1/pr-reviews/start`) works too when the pipeline cannot install the CLI.
+
+3. **Source upload from a pipeline without an SCM app:** upload the checked-out tree as a cloud code review (`scans:write` and `uploads:write`). The two-step digest handoff keeps a human in control of what leaves the runner:
+
+   ```bash
+   strix cloud scans start --source . --dry-run --show-files --json   # review, capture source.archive_sha256
+   strix cloud scans start --source . --approve-sha256 "$SOURCE_SHA256" --wait
+   ```
+
+   Exit codes: `0` success, `4` auth or plan limit, `5` payment required. Non-Enterprise scans consume credits.
+
+Full CLI coverage (PR reviews, scans, SARIF export, schedules) is in the **managed-pentesting-with-strix** skill.
 
 Recommend Option B for most teams (no maintenance, central dashboard); use Option A when scans must stay entirely within your own infrastructure.

skills/find-security-vulnerabilities-in-code/SKILL.md

@@ -11,7 +11,7 @@ metadata:
 
 White-box security review with Strix: the agents read the source to build a model of routes, sinks, and authorization checks, then attempt real exploitation. Findings come with a proof-of-concept, so the output is a short list of proven issues rather than the hundreds of "potential" hits a pattern-matching scanner produces.
 
-Install, LLM setup, all flags, and the managed-cloud path are in the **penetration-testing-with-strix** skill.
+Install, LLM setup, all flags, and the managed-cloud path are in the **penetration-testing-with-strix** skill. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**).
 
 ## Run it
 

skills/fix-security-vulnerabilities-with-strix/SKILL.md

@@ -18,7 +18,7 @@ Get the findings from wherever the scan ran:
 - **OSS CLI** — artifacts in `strix_runs/<run-name>/`:
   - `vulnerabilities/*.md` — one finding per file: description, severity, PoC steps or script, affected code locations, remediation guidance.
   - `vulnerabilities.json` — the same findings as JSON (ids, severity, CWE/CVE, `code_locations` with `fix_before`/`fix_after` suggestions when available).
-- **Cloud (app.strix.ai)** — fetch the scan's `vulnerabilities[]` via `GET /api/v1/scans/{scanId}` (or `GET /api/v1/vulnerabilities` org-wide). Each carries `severity, cwe, endpoint, method, impact, technical_analysis, poc_description, poc_script_code` and, for code findings, `code_file`/`code_diff`/`code_before`/`code_after`. See the **managed-pentesting-with-strix** skill for auth.
+- **Cloud (app.strix.ai)** — pull findings with the CLI: `strix cloud vulns list --scan-id <scan-id> --json` (or `strix cloud scans get <scan-id> --json | jq '.vulnerabilities'`, or `strix cloud vulns list --severity critical` org-wide). Each finding carries `severity, cwe, endpoint, method, impact, technical_analysis, poc_description, poc_script_code` and, for code findings, `code_file`/`code_diff`/`code_before`/`code_after`. After a fix is verified, mark it with `strix cloud vulns update <id> --status fixed`. See the **managed-pentesting-with-strix** skill for `strix cloud login` and scopes.
 
 Order work by severity: critical → high → medium → low. Every Strix finding was validated with a working proof-of-concept, so do not dismiss findings as false positives without re-testing the PoC yourself.
 

skills/managed-pentesting-with-strix/SKILL.md

@@ -1,23 +1,59 @@
 ---
 name: managed-pentesting-with-strix
-description: Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed. Create an API token, register domain/repository assets, launch and poll scans, triage vulnerabilities, export SARIF, download PDF/DOCX pentest reports for SOC 2 and other compliance evidence (Enterprise plan), start PR reviews, and set up schedules and webhooks. Use when the user wants continuous or scheduled pentesting-as-a-service, an auditor-ready pentest report, scans tracked in a team dashboard, or security testing from a sandboxed agent/CI environment with no infrastructure.
+description: Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the `strix cloud` CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance reports, start PR reviews, buy credits, and set up schedules or webhooks. Use for managed, continuous, scheduled, team-tracked, or sandboxed-agent security testing.
 license: Apache-2.0
 metadata:
   author: usestrix
   homepage: https://docs.app.strix.ai
 ---
 
-# Strix Cloud API (managed, no local infra)
+# Strix Cloud (managed, no local infra)
 
 Use this when you want Strix's autonomous pentesting **without running Docker or an LLM yourself** — the scan runs on Strix's infrastructure and results are tracked in a team dashboard. This is the right choice in sandboxed/hosted agent and CI environments, for teams, and for scheduled/continuous testing (downloadable PDF/DOCX reports are an Enterprise-plan feature). For fully local, free, air-gapped, or BYO-LLM runs, use the open-source CLI in the **penetration-testing-with-strix** skill instead — both share the same engine and SARIF output, so you can mix them.
 
-Full reference: **[docs.app.strix.ai](https://docs.app.strix.ai)** · OpenAPI: `https://docs.app.strix.ai/openapi.json`
+There are two equivalent interfaces. Prefer the CLI:
 
-## Setup
+- **`strix cloud` CLI** — every REST operation has a command in the form `strix cloud <resource> <verb>`. Install with `curl -sSL https://strix.ai/install | bash`. Run `strix cloud` to list all resources and `strix cloud <resource> help` (or `-h`) to list a resource's verbs; a bare resource with a safe read operation runs its documented default.
+- **REST API** — base URL `https://app.strix.ai/api/v1`, `Authorization: Bearer <token>` on every request. Full reference: **[docs.app.strix.ai](https://docs.app.strix.ai)** · agent index: `https://docs.app.strix.ai/llms.txt` · OpenAPI: `https://docs.app.strix.ai/openapi.json`.
 
-- **Base URL:** `https://app.strix.ai/api/v1`
-- **Auth:** every request sends `Authorization: Bearer <token>`. Tokens are **org-scoped**.
-- **Get a token:** the user creates one in the dashboard at **Settings → API Access** (app.strix.ai). Ask them for it; never hardcode, log, or commit it. Store it in an env var or the CI secret store.
+The CLI is equally usable by agents and people. Output is complete JSON when stdout is not a terminal, or when you pass `--json`; terminal tables favor names, branches, lifecycle states, and numbered selectors. Human lists retain the selectors needed by follow-up commands but omit internal organization/user IDs; a selector too long for the compact table is repeated losslessly in a copyable block. Paginated lists print the next `--page` or `--offset`, and detail views preserve useful prose within a safe terminal bound; use `--json` for the complete record. Token lists label credentials as active, expired, or revoked. Binary downloads are the exception: redirect raw bytes intentionally, or use `--output FILE --json` to write the file and receive structured metadata. There are no interactive prompts when stdin is not a terminal. Exit codes: `0` success, `1` request/runtime error, `2` invalid usage, `4` authentication or plan limit, `5` payment required.
+
+Every resource group with a safe read operation has a useful default action, and `-h` or `help` always shows its verbs. Native tab completion includes resources, verbs, flags, workspace commands, and local paths:
+
+```bash
+source <(strix completions zsh)       # current zsh session
+source <(strix completions bash)      # current bash session
+strix completions fish | source       # current fish session
+```
+
+Write commands take request fields as flags. Every write command also accepts one JSON object with `--data`, which is the way to send fields that have no flag:
+
+```bash
+strix cloud scans start --data '{"engagement_type":"code_review"}'   # literal JSON
+strix cloud scans start --data @request.json                         # read a file
+cat request.json | strix cloud scans start --data -                  # read standard input
+```
+
+The platform enforces plan and role limits, and the CLI passes the platform message through. Report downloads need the Enterprise plan. Schedules need the Pro plan. Billing writes need an admin token. A blocked command exits with code `4`.
+
+## Setup: sign in
+
+Run the device sign-in. It creates the user's account and workspace on first use and stores a personal API token in `~/.strix/platform-auth.json`:
+
+```bash
+strix cloud login
+# Non-interactive least-privilege example:
+strix cloud login --scopes scans:read scans:write uploads:write billing:read vulnerabilities:read assets:read assets:write
+# Or use a stable named profile:
+strix cloud login --scope-profile recommended
+```
+
+The user approves the sign-in in the browser. With `--scopes` (and optionally `--workspace <name-or-id>`) there are no terminal prompts, so the command works from a non-interactive agent shell. In an interactive terminal without flags, the CLI offers a workspace picker and scope presets (Recommended, Full access, Minimal, Custom). Recommended covers ordinary scans, source uploads, workspace switching, and user-approved credit top-ups; it excludes `tokens:write`, which must be requested explicitly when credential management is required. Use explicit scopes for a narrower automation token.
+
+- `strix cloud whoami` is the fast local status. `strix cloud session --json` verifies the remote device session; `strix cloud session scopes` shows both effective access and the immutable login ceiling.
+- `strix cloud logout` revokes the remote session before removing the local token. On a network or server failure it keeps the token so the user can retry; `--local-only` deliberately skips revocation.
+- Every other `strix cloud` command uses the stored token automatically. `--token <token>` or `STRIX_API_TOKEN` is a stateless per-command override and never overwrites the stored account. For an override that is itself a CLI session, also pass `--workspace-id` or set `STRIX_WORKSPACE_ID`.
+- Never hardcode, log, or commit the token. Store it in an env var or the CI secret store.
 - **Scopes (least-privilege):** assign only what the integration needs and rotate regularly:
 
   | Scope | Grants |
@@ -28,15 +64,105 @@ Full reference: **[docs.app.strix.ai](https://docs.app.strix.ai)** · OpenAPI: `
   | `schedules:read` / `:write` | read schedules · create/trigger recurring scans |
   | `pr_reviews:write` | trigger PR security reviews |
   | `webhooks:read` / `:write` | manage webhook subscriptions |
-  | `tokens:write` | create/revoke API tokens |
+  | `uploads:write` | upload local source or documents for a scan |
+  | `organizations:read` | read organization details (listing/switching the signed-in user's workspaces needs no API scope) |
+  | `organizations:write` | create/update workspaces (admin) |
+  | `tokens:write` | create/revoke ordinary API tokens (not needed to manage the current CLI session) |
+  | `knowledge:read` / `:write` | read/update organization knowledge |
+  | `audit:read` | read/export the Enterprise audit log |
+  | `billing:read` / `billing:write` | read credit balance & auto top-up settings · buy credits (admin) |
+
+HTTP errors map to messages and exit codes: `401` bad/expired token (exit `4`), `402` out of credits (exit `5`), `403` scope/plan-tier limit (exit `4`), `422` validation error (exit `1`).
+
+Create a time-limited automation token with `strix cloud tokens create`. Use
+`--rbac-scopes` to restrict it to target IDs, tags, or business units; the value is a
+JSON array of `{ "type": "target|tag|business_unit", "value": "..." }` objects:
 
 ```bash
-export STRIX_API_TOKEN="<token>"
-BASE=https://app.strix.ai/api/v1
-auth=(-H "Authorization: Bearer $STRIX_API_TOKEN")
+strix cloud tokens create --type service --name staging-ci \
+  --expires-at 2026-12-31T23:59:59Z \
+  --scopes scans:read scans:write \
+  --rbac-scopes '[{"type":"tag","value":"staging"}]'
 ```
 
-All examples use `jq` to parse JSON. Handle HTTP errors: `401` bad/expired token, `402` out of credits, `403` scope/plan-tier limit, `422` validation error.
+The token secret is returned once. Store it directly in a secret manager and do not
+print or commit it. `--expires-at` and `--expires-in-days` are mutually exclusive.
+
+## 0. Credits & top-ups
+
+Non-Enterprise scans consume org credits. Enterprise engagements are plan-included and do not debit the wallet. Check the balance before a scan (`billing:read`):
+
+```bash
+strix cloud credits
+```
+
+When the balance is too low, buy credits with `strix cloud billing topup` (`billing:write`, admin token). The server answers the first request with **HTTP 402 and a machine-payment challenge** (Stripe Machine Payments Protocol). The CLI pays the challenge with the Stripe Link wallet client when Node.js is available — the user approves the spend in the [Link app](https://link.com/agents). The response returns the receipt (`credits_granted`, `duplicate`, `reference`) and the new balance.
+
+A default-tier source-only code review currently starts at 60 credits. Source uploads are not free: they launch an ordinary `code_review` and use the same deterministic scope estimator. The service checks the full balance before launch, reserves credits atomically only after validation succeeds, and does not create or charge a rejected scan. Retests and Enterprise scans are exempt.
+
+```bash
+strix cloud billing topup --credits 20 --yes   # explicit approval; skips the TTY prompt
+strix cloud billing topup --credits 20 --no-pay   # print the 402 challenge without paying
+```
+
+The default payment path is the Stripe Link wallet. When no wallet is connected, an interactive `strix cloud billing topup` starts the Link sign-in for the user and prints the verification link. The user approves the connection one time in the Link app, and then approves each payment there. No keys or variables are necessary. In a non-interactive process, the command stops and tells the user to connect the wallet at [link.com/agents](https://link.com/agents) or to use the hosted checkout link.
+
+In a non-interactive agent or CI process, payment never proceeds unless the command includes `--yes`. Show the challenge or estimated spend to the user and obtain approval before adding it. `--no-pay` always stops after printing the challenge.
+
+If the user does not want a wallet, create a hosted checkout link with `strix cloud billing subscribe --plan strix_top_up` and give the link to the user. The user pays in the browser.
+
+Automatic top-ups (admin): `strix cloud billing auto-topup` shows the setting. Enable it with:
+
+```bash
+strix cloud billing auto-topup update --enabled --topup-credits 20 --monthly-cap-credits 200
+```
+
+An omitted `--monthly-cap-credits` keeps the stored cap. Pass `--no-monthly-cap` to remove the cap.
+
+### Workspaces and account setup
+
+Manage workspaces with a personal token from `strix cloud login`:
+
+```bash
+strix cloud workspaces list                    # numbered name/role/current list
+strix cloud workspaces create --name "My Team"  # admin + organizations:write
+strix cloud workspaces use 2                   # displayed number, exact name, or ID
+strix cloud workspace use "My Team"            # singular `workspace` alias also works
+strix cloud session scopes                     # effective scopes + consent ceiling
+strix cloud session scopes set minimal         # narrow the session
+strix cloud org members invite --email dev@example.com --role analyst
+```
+
+`workspaces use` retargets the current personal token to a workspace the user already belongs to and stores the updated workspace metadata; the bearer secret and expiry stay unchanged. It does not reprompt during ordinary switches: the server preserves the chosen profile, enforces the immutable login ceiling, and caps effective scopes by the target role. Use `--scope-profile` or `--scopes` to narrow within that ceiling; broader consent requires `strix cloud login` again. The CLI pins each process to the workspace it started in, so concurrent shells fail with a recoverable conflict instead of silently crossing organizations.
+
+### Handoffs a person must finish
+
+Four steps end at the user. The command creates the link or the record and prints it. Strix opens the browser only in an interactive terminal. Pass `--no-browser` to print the URL only.
+
+```bash
+strix cloud billing subscribe --plan strix_cloud # hosted checkout page for the Cloud plan
+strix cloud billing portal                       # billing portal for the card and the plan
+strix cloud integrations install github          # GitHub App or Slack installation page
+strix cloud domains verify <domain-id>           # DNS record to add, then run it again
+```
+
+Give the printed URL or DNS record to the user and wait. Do not claim that the payment, the installation, or the DNS change is complete. Confirm the result afterwards with `strix cloud credits`, `strix cloud integrations list`, or `strix cloud domains list`. All four commands need an admin token, except `domains verify`, which needs `assets:write`.
+
+### Organization knowledge
+
+Agents can manage the organization knowledge base without the dashboard (`knowledge:read` / `knowledge:write`):
+
+```bash
+strix cloud knowledge list --search authentication
+strix cloud knowledge add --title "Authentication" --content "Staging uses SSO."
+strix cloud knowledge update <document-id> --content "Staging uses SSO and TOTP."
+strix cloud knowledge delete <document-id>
+strix cloud knowledge policies add --key staging-only --content "Never test production."
+strix cloud knowledge policies delete staging-only
+strix cloud knowledge repos entries usestrix/strix
+```
+
+Knowledge policy writes require an admin token. Repository names are passed as normal `owner/name` values; the CLI handles URL encoding. The `costs` and `llm-settings` commands target on-prem installations and return `404` on app.strix.ai.
 
 ## 1. Register the target as an asset
 
@@ -44,109 +170,152 @@ Scans run against **registered assets**, not raw URLs. Register once, then reuse
 
 ```bash
 # Domain (black-box / live target). Requires domain verification before external scanning.
-# asset_type must be one of: web_app | api | attack_surface.
-curl -sS "$BASE/domains" "${auth[@]}" -H "Content-Type: application/json" \
-  -d '{"domain":"staging.example.com","asset_type":"web_app"}' | jq '{id:.domain.id, status, reachable, verification}'
+# --asset-type must be one of: web_app | api | attack_surface.
+strix cloud domains add --domain staging.example.com --asset-type web_app
 
 # Repository (white-box / code review). `full_name` is "owner/name".
-# Send one repository object, or a bare JSON array for several — not an object
-# wrapping a "repositories" key (that is rejected with 400).
-curl -sS "$BASE/repositories" "${auth[@]}" -H "Content-Type: application/json" \
-  -d '[{"full_name":"org/app","provider":"github"}]' | jq '.repositories[] | {id, full_name}'
+strix cloud repos add --data '{"full_name":"org/app","provider":"github"}'
 ```
 
-Look up existing assets instead of re-adding: `GET /domains`, `GET /repositories` (both `assets:read`, paginated with `?page=&limit=`).
+Look up existing assets instead of re-adding: `strix cloud domains list`, `strix cloud repos list` (both `assets:read`).
 
 ## 2. Launch a scan
 
-`POST /scans` (`scans:write`). Provide at least one target via `domain_ids`, `repository_ids`, or `internal_targets` (internal infra needs a network connector — see docs).
+`strix cloud scans start` (`scans:write`). Provide at least one target with `--domain-ids`, `--repository-ids`, or `--internal-targets` (internal infra needs a network connector — see docs).
 
 ```bash
-scan_id=$(curl -sS "$BASE/scans" "${auth[@]}" -H "Content-Type: application/json" -d '{
-  "engagement_type": "live_test",
-  "domain_ids": ["<domain-uuid>"],
-  "focus": "IDOR, auth bypass, SSRF",
-  "context": "Staging. Test account creds are configured as a test user.",
-  "notify_on_completion": true
-}' | jq -r .scan_id)
-echo "$scan_id"
+strix cloud scans start \
+  --engagement-type live_test \
+  --domain-ids <domain-uuid> \
+  --focus "IDOR, auth bypass, SSRF" \
+  --context "Staging. Test account creds are configured as a test user." \
+  --notify-on-completion
 ```
 
-Useful `CreateScanRequest` fields:
+Useful flags (each maps to a `CreateScanRequest` field):
 
-| Field | Purpose |
+| Flag | Purpose |
 |---|---|
-| `engagement_type` | `live_test` (default), `code_review`, `internal_infra`, `compliance_pentest` |
-| `domain_ids` / `repository_ids` / `internal_targets` | targets (at least one) |
-| `domain_paths` / `repository_branches` | narrow to specific paths / branches |
-| `credentials` | authenticated scanning, incl. `mfa_method` (`totp`/`email_otp`/…) + `totp_secret` |
-| `headers` | extra HTTP headers (API keys, for example) for the target |
-| `focus` / `concerns` / `context` | steer the agents |
-| `upload_ids` | attach uploaded source/docs archives for white-box context |
-| `notify_on_completion` / `notification_emails` | email when done |
+| `--engagement-type` | `live_test` (default), `code_review`, `internal_infra`, `compliance_pentest` |
+| `--domain-ids` / `--repository-ids` / `--internal-targets` | targets (at least one) |
+| `--domain-paths` / `--repository-branches` | narrow to specific paths / branches (JSON maps) |
+| `--credentials` | authenticated scanning, incl. `mfa_method` (`totp`/`email_otp`/…) + `totp_secret` (JSON list) |
+| `--headers` | extra target HTTP headers as a JSON array of header objects |
+| `--focus` / `--concerns` / `--context` | free-form strings that steer the agents |
+| `--upload-ids` | attach uploaded source/docs archives for white-box context |
+| `--notify-on-completion` / `--notification-emails` | email when done |
 
-Response is `{ scan_id, title, status }` with `status` = `pending`.
+Without `--source`, the response is `{ scan_id, title, status }` with `status` = `pending`.
+Local-source success wraps that platform response as
+`{ source, upload_id, scan: { scan_id, title, status } }`, so automation can retain the exact
+approved manifest and staged-upload identifier alongside the created scan.
 
-## 3. Poll to completion
+### Scan a local workspace in the cloud
 
-`GET /scans/{scanId}` (`scans:read`). Status flow: `pending → running → completed` (or `failed` / `cancelled`). Poll on an interval — scans take minutes to hours. Do not block.
+For an agent or CI workflow, bind approval to the exact source snapshot that was reviewed. Run
+the dry run with the intended source-selection flags, review the manifest and selected paths,
+and capture `source.archive_sha256`. Then repeat the same `--source`, every `--exclude`, and
+any `--include-hidden`, `--include-sensitive`, or `--include-archives` flags with
+`--approve-sha256`:
 
 ```bash
-while :; do
-  s=$(curl -sS "$BASE/scans/$scan_id" "${auth[@]}" | jq -r .status)
-  echo "status=$s"; [[ "$s" =~ ^(completed|failed|cancelled)$ ]] && break
-  sleep 60
-done
+strix cloud scans start --source . --exclude 'private/' --dry-run --show-files --json
+# After reviewing the output, capture its source.archive_sha256 value:
+SOURCE_SHA256="<reviewed source.archive_sha256>"
+# Repeat every source-selection flag unchanged; a source-only scan infers code_review.
+strix cloud scans start --source . --exclude 'private/' \
+  --approve-sha256 "$SOURCE_SHA256" --wait
 ```
 
+The CLI rebuilds the archive and refuses the upload if its SHA-256 no longer matches. `--yes`
+has deliberately narrower semantics: it approves only the snapshot built during that one
+invocation. Use it for a deliberate human or one-shot approval, not as the second half of a
+digest-bound agent/CI review. Without a TTY, a source upload requires either matching
+`--approve-sha256` approval or `--yes`; an interactive terminal can instead show the summary,
+the selected filenames when `--show-files` is set, and a `[y/N]` confirmation for its current
+snapshot.
+
+The default selection is privacy-conscious: in a Git worktree it includes tracked files plus untracked files that are not ignored; it honors `.gitignore`, excludes every hidden path component, always excludes `.git`, symlinks, dependencies/build output, secret-like filenames, and nested archives. Add project exclusions to `.strixignore` (one exclude glob per line) or repeat `--exclude GLOB`; a trailing slash such as `private/` excludes that directory subtree.
+
+The client refuses more than 20,000 files, a file over 25 MiB, more than 250 MiB expanded, or a ZIP over 50 MiB. The service then stream-inflates the ZIP and independently rejects malformed or unsupported entries, unsafe paths, too many entries, oversized entries, excessive expanded data, and oversized compressed input, so an untrusted client cannot bypass the ZIP-bomb controls by forging metadata.
+
+Only use `--include-hidden`, `--include-sensitive`, or `--include-archives` after the dry-run manifest shows that the scan needs them. Hidden and sensitive files are separate opt-ins: for example, including `.env` requires both `--include-hidden` and `--include-sensitive`.
+
+The CLI removes its private temporary local archive after every invocation. Once a remote
+upload is staged, a definitive scan rejection causes the CLI to delete it. A network failure,
+`5xx` response, malformed success response, or interruption after scan launch begins is
+ambiguous—the platform may have accepted the scan—so the CLI retains the upload and returns
+its `upload_id` with `launch_outcome_unknown: true`. If an automatic deletion attempt cannot
+be confirmed, it instead returns the retained `upload_id` with `cleanup_unknown: true`.
+Before retrying, run `strix cloud scans list` to avoid a duplicate scan or charge. If no scan
+is linked to the retained upload, remove it with `strix cloud uploads delete UPLOAD_ID`;
+linked uploads cannot be deleted.
+
+With no explicit type, source alone infers `code_review`. Any domain target wins and infers `live_test`, so source plus a deployed domain is the normal white-box live-test workflow. Pass `--engagement-type` when you need to override the inference.
+
+## 3. Wait for completion
+
+Pass `--wait` to `scans start` to poll until the scan reaches a final state, or poll yourself with `strix cloud scans get <scan-id>` (`scans:read`). Bound automation with `--wait-timeout SECONDS`; timeout exits cleanly without cancelling the remote scan. Status flow: `pending → running → completed` (or `failed` / `cancelled`). Scans take minutes to hours — poll on an interval, do not block indefinitely.
+
 ## 4. Read findings
 
 The scan-detail response includes `executive_summary`, `methodology`, `recommendations`, a `findings` severity roll-up, and a `vulnerabilities[]` array. Each vulnerability carries `title, severity, status, cvss, cwe, endpoint, method, impact, technical_analysis, poc_description, poc_script_code`, and (for code findings) `code_file`/`code_diff`/`code_before`/`code_after`.
 
 ```bash
-curl -sS "$BASE/scans/$scan_id" "${auth[@]}" \
+strix cloud scans get <scan-id> --json \
   | jq '["critical","high","medium","low","info"] as $order
        | .vulnerabilities
        | sort_by(.severity as $s | $order | index($s))
        | .[] | {title, severity, endpoint, cwe}'
 ```
 
-Cloud severities are `critical | high | medium | low` and statuses are `open | in_progress | fixed | ignored`. Sort by an explicit severity order rather than `sort_by(.severity)`, which sorts alphabetically (critical, high, low, medium).
+Cloud severities are `critical | high | medium | low` and statuses are `open | in_progress | snoozed | fixed | ignored | not_affected`. Sort by an explicit severity order rather than `sort_by(.severity)`, which sorts alphabetically (critical, high, low, medium).
 
-Org-wide triage across scans: `GET /vulnerabilities` (`vulnerabilities:read`; filter by severity/status). Update triage state with the vulnerabilities `:write` endpoints. To remediate, hand off to the **fix-security-vulnerabilities-with-strix** skill.
+Org-wide triage across scans: `strix cloud vulns list --severity critical` (`vulnerabilities:read`, and it also filters by `--status`, `--scan-id`, and more). Update triage state with `strix cloud vulns update <id> --status fixed`. To remediate, hand off to the **fix-security-vulnerabilities-with-strix** skill.
 
 ## 5. Export & report
 
 ```bash
 # SARIF 2.1.0 for GitHub code scanning / ASPM ingestion
-curl -sS "$BASE/scans/$scan_id/sarif" "${auth[@]}" -o findings.sarif
+strix cloud scans sarif <scan-id> --output findings.sarif
 
-# Report. The format and file type are query params (`Accept` is ignored):
-#   format=technical (default) | retest | attestation | executive_summary
-#   type=pdf (default) | docx
-# Any report download requires the Enterprise plan; formats beyond `technical`,
+# Report. Formats: technical (default) | retest | attestation | executive_summary
+# Types: pdf (default) | docx
+# Any report download requires the Enterprise plan. Formats beyond `technical`,
 # DOCX, and white-label branding are Enterprise-only too. Scan must be completed.
-curl -sS "$BASE/scans/$scan_id/report?format=technical&type=pdf" "${auth[@]}" -o strix-report.pdf
+strix cloud scans report <scan-id> --format technical --type pdf --output strix-report.pdf
+```
+
+Downloads refuse to replace a file unless `--force` is explicit. Enterprise audit logs can be streamed as JSON or exported without trying to JSON-decode the body:
+
+```bash
+strix cloud audit list --format csv --all --output audit.csv
+strix cloud audit list --format ndjson --all --output audit.ndjson
 ```
 
 ## 6. PR reviews
 
-Trigger an automated security review of a pull request (`pr_reviews:write`); results appear as PR comments and in the dashboard:
+Trigger an automated security review of a pull request (`pr_reviews:write`). Read the repository's `provider` and `installation_id` with `strix cloud repos list`; both identify the installed source-control integration. The results appear as PR comments and in the dashboard:
 
 ```bash
-curl -sS "$BASE/pr-reviews/start" "${auth[@]}" -H "Content-Type: application/json" \
-  -d '{"repository_full_name":"org/app","pr_number":123}'
+strix cloud pr-reviews start \
+  --provider github \
+  --installation-id <installation-id> \
+  --repository-full-name org/app \
+  --pr-number 123
 ```
 
-List/inspect via `GET /pr-reviews` and `GET /pr-reviews/{id}`. Repo-level PR-review behavior is configured with the repository-settings endpoint.
+List/inspect with `strix cloud pr-reviews list` and `strix cloud pr-reviews get <id>`. Repo-level PR-review behavior is configured with `strix cloud pr-reviews settings`.
 
 ## 7. Continuous testing (schedules & webhooks)
 
-- **Schedules** (`schedules:write`, Pro plan): create recurring scans and trigger them on demand — the managed equivalent of a cron-driven CLI loop.
-- **Webhooks** (`webhooks:write`): subscribe to pentest/vulnerability lifecycle events such as `scan.completed` and `vulnerability.created` to push results into Slack, ticketing, or your own pipeline instead of polling.
+- **Schedules** (`schedules:write`, Pro plan): `strix cloud schedules create` makes recurring scans, and `strix cloud schedules trigger <id>` runs one on demand — the managed equivalent of a cron-driven CLI loop.
+- **Webhooks** (`webhooks:write`): `strix cloud webhooks create` subscribes to pentest/vulnerability lifecycle events such as `scan.completed` and `vulnerability.created` to push results into Slack, ticketing, or your own pipeline instead of polling.
 
 See the schedules and webhooks sections at [docs.app.strix.ai](https://docs.app.strix.ai) for payloads.
 
+Network connectors are Enterprise-only. `strix cloud connectors create` may return a one-time enrollment command containing credentials; do not paste it into logs, and request it with `--include-command` only when the user is ready to install it. Browser checkout, source-control installation, DNS verification, connector installation, chat sharing, and publishing SARIF to an external provider are user handoffs or explicit external mutations—prepare the command/link, then obtain the appropriate approval before completing them.
+
 ## Safety
 
 Only scan assets the user's organization owns or is authorized to test. External domain scans require verification (DNS/file/meta-tag) enforced by the platform — do not try to bypass it.

skills/owasp-top-10-testing/SKILL.md

@@ -13,7 +13,7 @@ The OWASP Top 10 is a taxonomy of risk categories, not a test suite — "OWASP T
 
 **Use the current edition: [OWASP Top 10:2025](https://owasp.org/Top10/)** (8th installment, superseding 2021). Ask the user before targeting an older edition — some compliance checklists still reference 2021, and a report labelled with the wrong edition is misleading. Key differences from 2021: **SSRF is folded into A01**, **A03 Software Supply Chain Failures** expands the old "Vulnerable and Outdated Components", and **A10 Mishandling of Exceptional Conditions** is new; A02 Security Misconfiguration moved 5→2.
 
-Install, LLM setup, and the managed-cloud alternative: **penetration-testing-with-strix**.
+Install, LLM setup, and the managed-cloud alternative: **penetration-testing-with-strix**. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**).
 
 ## What is and is not testable by an agent
 

skills/penetration-testing-with-strix/SKILL.md

@@ -12,7 +12,7 @@ metadata:
 Strix runs autonomous AI pentesting agents that dynamically exploit a target and only report findings validated with a working proof-of-concept. There are **two ways to run it, built on the same engine and producing the same findings** — pick per situation, and mix them freely:
 
 - **Open-source CLI** (self-hosted) — runs on your machine in a Docker sandbox with your own LLM key. Free, fully local, BYO-LLM, air-gap capable. Docs: [docs.strix.ai](https://docs.strix.ai).
-- **Cloud API** (managed) — runs on Strix's infrastructure via `https://app.strix.ai/api/v1`. No Docker, no LLM key, no local compute; adds team dashboards, scheduling, PR reviews, downloadable PDF/DOCX reports (Enterprise plan), and internal-network connectors. Docs: [docs.app.strix.ai](https://docs.app.strix.ai). Full workflow in the **managed-pentesting-with-strix** skill.
+- **Managed cloud** — runs on Strix's infrastructure, driven from the same CLI (`strix cloud ...`) or the REST API at `https://app.strix.ai/api/v1`. No Docker, no LLM key, no local compute; adds team dashboards, scheduling, PR reviews, downloadable PDF/DOCX reports (Enterprise plan), and internal-network connectors. Docs: [docs.app.strix.ai](https://docs.app.strix.ai). Full workflow in the **managed-pentesting-with-strix** skill.
 
 ## Which one? (decide, do not default)
 
@@ -122,27 +122,33 @@ Artifacts land in `strix_runs/<run-name>/`:
 
 ---
 
-# Option B — Cloud API (managed, no local infra)
+# Option B — Managed cloud (no local infra)
 
-Full details, asset registration, polling, reports, PR reviews, schedules, and webhooks are in the **managed-pentesting-with-strix** skill. Minimal launch-and-poll:
+The same `strix` binary drives the managed platform. Every command starts with `strix cloud`. Full details — asset registration, source uploads, reports, PR reviews, schedules, webhooks, and billing — are in the **managed-pentesting-with-strix** skill. Minimal flow:
 
 ```bash
-export STRIX_API_TOKEN="<token>"   # org-scoped bearer, from Settings → API Access at app.strix.ai
-BASE=https://app.strix.ai/api/v1
+# 1. Sign in (device flow — the user confirms a code in the browser; this also
+#    creates the account and workspace when needed)
+strix cloud login
 
-# 1. Launch a scan against an already-registered domain/repo asset
-scan_id=$(curl -sS "$BASE/scans" \
-  -H "Authorization: Bearer $STRIX_API_TOKEN" -H "Content-Type: application/json" \
-  -d '{"engagement_type":"live_test","domain_ids":["<domain-uuid>"]}' | jq -r .scan_id)
+# If you need specific scopes, request them with --scopes:
+#   strix cloud login --scopes scans:read scans:write assets:read assets:write \
+#     vulnerabilities:read billing:read billing:write
 
-# 2. Poll until terminal (pending → running → completed/failed/cancelled)
-curl -sS "$BASE/scans/$scan_id" -H "Authorization: Bearer $STRIX_API_TOKEN" | jq '.status'
+# 2. Register and verify the target domain (verification prints a DNS record for the user)
+strix cloud domains add --domain staging.example.com --asset-type web_app
+strix cloud domains verify <domain-id>
 
-# 3. Read validated findings from the scan detail's `vulnerabilities[]`, or export SARIF
-curl -sS "$BASE/scans/$scan_id/sarif" -H "Authorization: Bearer $STRIX_API_TOKEN" -o findings.sarif
+# 3. Launch and wait
+strix cloud scans start --engagement-type live_test --domain-ids <domain-id> --wait
+
+# 4. Read validated findings
+strix cloud vulns list --severity critical
 ```
 
-Ask the user to create the token (and register the target as a domain/repository asset) if they have not. If Docker/local prerequisites are not already satisfied, use this path instead of trying to install infra.
+For a local repository, `strix cloud scans start --source .` uploads the working tree (needs `uploads:write`) and infers a code review. When credits run out, `strix cloud billing topup` starts an agent-payable Stripe challenge — the managed skill covers the payment flow. Output is JSON when stdout is not a terminal, so the commands compose in scripts.
+
+The raw REST API works too (`https://app.strix.ai/api/v1`, org-scoped bearer token — see [docs.app.strix.ai](https://docs.app.strix.ai)). If Docker or local prerequisites are not already satisfied, use this path instead of trying to install infra.
 
 ---
 

skills/web-app-penetration-testing/SKILL.md

@@ -11,7 +11,7 @@ metadata:
 
 Black-box (and optionally source-assisted) penetration testing of a running web app with Strix's autonomous agents. Every reported finding is validated with a working exploit, so there are no signature-based false positives to triage.
 
-Install, LLM setup, all CLI flags, and the managed-cloud alternative are covered in the **penetration-testing-with-strix** skill — read it if the target is not a running web app, or if `strix --version` fails. This skill is the web-app-specific workflow.
+Install, LLM setup, all CLI flags, and the managed-cloud alternative are covered in the **penetration-testing-with-strix** skill — read it if the target is not a running web app, or if `strix --version` fails. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**). This skill is the web-app-specific workflow.
 
 ## 1. Confirm authorization and scope
 

strix/agents/factory.py

@@ -52,6 +52,7 @@ from strix.tools.reporting.tool import (
     create_vulnerability_report,
     get_report,
     list_reports,
+    update_vulnerability_report,
 )
 from strix.tools.respond.tool import respond_to_user
 from strix.tools.thinking.tool import think
@@ -68,7 +69,7 @@ from strix.tools.todo.tools import (
     mark_todo_pending,
     update_todo,
 )
-from strix.tools.web_search.tool import web_search
+from strix.tools.web_search.tool import web_get_contents, web_search
 
 
 if TYPE_CHECKING:
@@ -578,8 +579,10 @@ _BASE_TOOLS: tuple[Tool, ...] = (
     save_threat_model,
     amend_threat_model,
     web_search,
+    web_get_contents,
     create_vulnerability_report,
     create_dependency_report,
+    update_vulnerability_report,
     list_reports,
     get_report,
     list_requests,

strix/agents/prompts/system_prompt.jinja

@@ -239,7 +239,9 @@ VALIDATION REQUIREMENTS:
 - Before filing any report, run the counterevidence pass: argue the strongest case AGAINST the finding, record what you found in the `counterevidence` field, set `confidence` honestly (a static-only trace you couldn't execute is at best `medium`), and state what evidence would change the severity. See the counterevidence and severity-calibration knowledge above.
 - A vulnerability is ONLY considered reported when a reporting agent uses create_vulnerability_report (or create_dependency_report for known-CVE dependency/supply-chain findings) with full details. Mentions in agent_finish, finish_scan, or generic messages are NOT sufficient
 - Reporting and fixing are ONE step, not two: when source is available, the reporting agent derives the concrete fix and files it INLINE via create_vulnerability_report (`code_locations` with `fix_before`/`fix_after` + `fix_pr_body`) — the report is not complete without it. Do NOT report first and then spawn a separate downstream agent to re-derive and re-apply the same patch; that just re-does the analysis and wastes tokens. (Do not silently patch a finding WITHOUT filing a report — the report, with its embedded fix, is the deliverable.)
-- DEDUPLICATION: The create_vulnerability_report tool uses LLM-based deduplication. If it rejects your report as a duplicate, DO NOT attempt to re-submit the same vulnerability. Accept the rejection and move on to testing other areas. The vulnerability has already been reported by another agent
+- DEDUPLICATION: The create_vulnerability_report tool uses LLM-based deduplication. If it rejects your report as a duplicate, DO NOT attempt to re-submit the same vulnerability. Accept the rejection and move on to testing other areas. The vulnerability has already been reported by another agent. If your evidence proves more than the finding it matched (a working exploit where that one had only a static trace, a chain that raises the impact), revise that finding with update_vulnerability_report using the duplicate_of id — never re-file it.
+- HTTP EVIDENCE: a finding you validated through the proxy is not fully filed until `http_exchange_ids` carries the proxy request ids of the exchanges that prove it — the request that triggers the vulnerability plus the baseline/control request it differs from (an unauthenticated success next to the authenticated one, the payload response next to the benign one). Copy the ids exactly as `list_requests`/`view_request` show them, never invent or guess one, and never omit the field to bypass validation. Leave it out only when there is no captured HTTP exchange at all (static-only code findings, dependency CVEs). If you filed before the proving exchanges existed, attach them afterwards with update_vulnerability_report. Without the ids, the finding ships as prose nobody can replay.
+- REVISING A FINDING: use update_vulnerability_report (report id + the fields you want to replace + update_reason) when you learn something a finding already on file does not carry — you built the PoC after filing it, a chain raised its impact, further testing weakened it, or its counterevidence/remediation/code locations were wrong. Editing a finding needs no duplicate verdict, and it is always better than filing a second report for the same issue. Read the finding first with get_report, and pass only the fields that change.
 - REVIEWING FILED FINDINGS (orchestrator/root agent): use list_reports to see every vulnerability filed so far in this scan (by any agent, root or child) — metadata-first with per-severity counts — and get_report to read one finding in full by its id. These are read-only orchestration tools: the root agent uses them to track coverage, avoid dispatching work on already-covered ground, assemble the finish_scan executive summary, and reason about attack-chaining across confirmed findings. Leaf/specialist agents should NOT call them — just do your assigned testing and file findings. Each entry shows which agent filed it (agent_name), and your own entries are flagged by_you. list_notes/get_note do the same for notes.
 
 STATE & COORDINATION TOOLS (when and how):
@@ -492,6 +494,8 @@ SPECIALIZED TOOLS:
 PROXY & INTERCEPTION:
 - Caido CLI - Modern web proxy (already running). Use the proxy tools
   directly, or import `caido_api` from sandbox Python scripts.
+- Every proxied exchange has a request id (`list_requests`/`view_request`). Note the ids of the
+  requests that prove a finding as you test — they go into `http_exchange_ids` when you report it.
 - HTTPQL filters (for `list_requests`): quote string values, leave integers unquoted (`resp.code.eq:200`, not `"200"`); combine terms with `AND`/`OR` (there is no `NOT` — use the negated operator `ne`/`ncont`/`nregex`). Numeric fields (`resp.code`, `req.port`) use `eq`/`ne`/`gt`/`gte`/`lt`/`lte`; text fields (`req.host`, `req.path`, `req.method`, `req.raw`) use `cont`/`ncont`/`eq`/`regex`. Example: `resp.code.gte:200 AND resp.code.lt:300 AND req.host.cont:"api"`.
 
 CAIDO PROXY ERROR PAGES — NOT RESPONSES FROM THE TARGET:

strix/config/codex.py

@@ -72,32 +72,8 @@ def _write_store(data: dict[str, Any]) -> None:
     write_secret_text(AUTH_PATH, json.dumps(data, indent=2))
 
 
-def read_provider_record(provider: str) -> dict[str, Any] | None:
-    """Raw record for *provider* from the shared subscription-auth store."""
-    record = _read_store().get(provider)
-    return record if isinstance(record, dict) else None
-
-
-def save_provider_record(provider: str, record: dict[str, Any]) -> None:
-    data = _read_store()
-    data[provider] = record
-    _write_store(data)
-
-
-def remove_provider_record(provider: str) -> None:
-    data = _read_store()
-    if provider not in data:
-        return
-    del data[provider]
-    if data:
-        _write_store(data)
-        return
-    with contextlib.suppress(OSError):
-        AUTH_PATH.unlink()
-
-
 def read_record() -> dict[str, Any] | None:
-    record = read_provider_record(PROVIDER)
+    record = _read_store().get(PROVIDER)
     if not isinstance(record, dict) or record.get("type") != "oauth":
         return None
     if not (record.get("access") and record.get("refresh") and record.get("account_id")):
@@ -110,11 +86,21 @@ def is_authenticated() -> bool:
 
 
 def save_record(record: dict[str, Any]) -> None:
-    save_provider_record(PROVIDER, record)
+    data = _read_store()
+    data[PROVIDER] = record
+    _write_store(data)
 
 
 def logout() -> None:
-    remove_provider_record(PROVIDER)
+    data = _read_store()
+    if PROVIDER not in data:
+        return
+    del data[PROVIDER]
+    if data:
+        _write_store(data)
+        return
+    with contextlib.suppress(OSError):
+        AUTH_PATH.unlink()
 
 
 @contextlib.contextmanager
@@ -197,7 +183,7 @@ def build_authorize_url(challenge: str, state: str) -> str:
         "code_challenge": challenge,
         "code_challenge_method": "S256",
         "state": state,
-        "id_token_add_organizations": "true",
+        "id_token_add_organizations": "true",  # nosec B105 - boolean flag, not a secret
         "codex_cli_simplified_flow": "true",
         "originator": ORIGINATOR,
     }

strix/config/loader.py

@@ -10,11 +10,13 @@ from typing import TYPE_CHECKING, Any
 
 from pydantic import AliasChoices, BaseModel
 
-from strix.config.settings import Settings
+from strix.config.settings import LlmSettings, Settings
 from strix.utils.secret_files import write_secret_text
 
 
 if TYPE_CHECKING:
+    from collections.abc import Mapping
+
     from pydantic.fields import FieldInfo
 
 
@@ -25,6 +27,11 @@ _DEFAULT_PATH: Path = Path.home() / ".strix" / "cli-config.json"
 _override: Path | None = None
 _cached: Settings | None = None
 
+# Model, API key, and API base describe one provider connection. When the shell
+# changes any of them, the stored values of the others no longer belong together
+# and are dropped rather than mixed with the new value.
+_LINKED_LLM_FIELDS = ("model", "api_key", "api_base")
+
 
 def load_settings() -> Settings:
     """Resolve settings from env + JSON file + defaults. Memoized.
@@ -54,22 +61,31 @@ def apply_config_override(path: Path) -> None:
 
 
 def persist_current() -> None:
-    """Write currently-set env vars to the active config file (0o600)."""
+    """Merge currently-set env vars into the active config file (0o600).
+
+    Values already in the file survive when their env var is unset, so a
+    run that gets its settings from the file does not erase them. An env
+    var set to the empty string clears the field from the file. A change to
+    any linked LLM connection var drops the whole stored connection first.
+    """
     s = load_settings()
     target = _override or _DEFAULT_PATH
     target.parent.mkdir(parents=True, exist_ok=True)
 
-    env_block: dict[str, str] = {}
-    for sub_name in s.model_fields:
+    env_block = _drop_stale_llm_connection(_read_env_block(target))
+    for sub_name in type(s).model_fields:
         sub_model = getattr(s, sub_name)
         if not isinstance(sub_model, BaseModel):
             continue
         for finfo in type(sub_model).model_fields.values():
-            for alias in _aliases_for(finfo):
-                value = os.environ.get(alias.upper())
-                if value:
-                    env_block[alias.upper()] = value
-                    break
+            aliases = [alias.upper() for alias in _aliases_for(finfo)]
+            active = next((alias for alias in aliases if alias in os.environ), None)
+            if active is None:
+                continue
+            for alias in aliases:
+                env_block.pop(alias, None)
+            if os.environ[active]:
+                env_block[active] = os.environ[active]
 
     write_secret_text(target, json.dumps({"env": env_block}, indent=2))
 
@@ -93,17 +109,9 @@ def _read_json_overrides(path: Path) -> dict[str, dict[str, Any]]:
     Only includes keys whose env var is NOT already set, so env always
     wins over the persisted file.
     """
-    if not path.exists():
+    env_block_upper = _drop_stale_llm_connection(_read_env_block(path))
+    if not env_block_upper:
         return {}
-    try:
-        data = json.loads(path.read_text(encoding="utf-8"))
-    except (json.JSONDecodeError, OSError):
-        return {}
-    env_block = data.get("env", {}) if isinstance(data, dict) else {}
-    if not isinstance(env_block, dict):
-        return {}
-
-    env_block_upper = {str(k).upper(): v for k, v in env_block.items()}
     env_present = {k.upper() for k in os.environ}
 
     nested: dict[str, dict[str, Any]] = {}
@@ -123,3 +131,38 @@ def _read_json_overrides(path: Path) -> dict[str, dict[str, Any]]:
         if sub_data:
             nested[sub_name] = sub_data
     return nested
+
+
+def _first_alias_value(aliases: list[str], source: Mapping[str, Any]) -> Any | None:
+    return next((source[alias] for alias in aliases if alias in source), None)
+
+
+def _drop_stale_llm_connection(env_block: dict[str, Any]) -> dict[str, Any]:
+    """Remove every linked LLM var from ``env_block`` if the shell changed any of them."""
+    linked_aliases = [
+        [alias.upper() for alias in _aliases_for(LlmSettings.model_fields[name])]
+        for name in _LINKED_LLM_FIELDS
+    ]
+    changed = any(
+        (env_value := _first_alias_value(aliases, os.environ)) is not None
+        and env_value != _first_alias_value(aliases, env_block)
+        for aliases in linked_aliases
+    )
+    if not changed:
+        return env_block
+    stale = {alias for aliases in linked_aliases for alias in aliases}
+    return {k: v for k, v in env_block.items() if k not in stale}
+
+
+def _read_env_block(path: Path) -> dict[str, Any]:
+    """Return the ``env`` block stored in ``path`` with upper-cased keys, or ``{}``."""
+    if not path.exists():
+        return {}
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+    except (json.JSONDecodeError, OSError):
+        return {}
+    env_block = data.get("env", {}) if isinstance(data, dict) else {}
+    if not isinstance(env_block, dict):
+        return {}
+    return {str(k).upper(): v for k, v in env_block.items()}

strix/config/models.py

@@ -20,7 +20,6 @@ from agents.model_settings import ModelSettings
 from agents.models.fake_id import FAKE_RESPONSES_ID
 from agents.models.interface import Model, ModelProvider
 from agents.models.multi_provider import MultiProvider
-from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
 from agents.models.openai_responses import OpenAIResponsesModel
 from agents.retry import (
     ModelRetryBackoffSettings,
@@ -37,7 +36,7 @@ from openai.types.responses import (
 from openai.types.responses.response_usage import ResponseUsage
 from openai.types.shared import Reasoning
 
-from strix.config import codex, opencode
+from strix.config import codex
 from strix.config.loader import load_settings
 from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_input
 from strix.config.tool_call_limits import TurnToolCallLimiter
@@ -80,12 +79,7 @@ def _retry_statusless_provider_errors(context: RetryPolicyContext) -> bool:
 
 
 class _CodexResponsesModel(OpenAIResponsesModel):
-    """Responses model for stateless subscription gateways (always streamed).
-
-    Used for the ChatGPT subscription backend and for Responses-served models on
-    the OpenCode gateway: neither stores responses server-side, so reasoning is
-    carried inline via ``reasoning.encrypted_content``.
-    """
+    """Responses model for the ChatGPT subscription backend (always streamed, stateless)."""
 
     def __init__(
         self,
@@ -526,7 +520,6 @@ class StrixProvider(MultiProvider):
     def get_model(self, model_name: str | None) -> Model:
         llm = load_settings().llm
         slug = codex.subscription_model(model_name)
-        oc = opencode.subscription_model(model_name)
         idle_timeout = float(llm.stream_idle_timeout)
         if slug:
             # The ChatGPT subscription backend is always streamed; it has no
@@ -537,35 +530,6 @@ class StrixProvider(MultiProvider):
                 codex.get_subscription_client(),
                 reasoning_effort=llm.reasoning_effort,
             )
-        elif oc and oc.protocol == opencode.PROTOCOL_RESPONSES:
-            model = _CodexResponsesModel(
-                oc.slug,
-                opencode.get_subscription_client(oc.base_url),
-                reasoning_effort=llm.reasoning_effort,
-            )
-        elif oc and oc.protocol == opencode.PROTOCOL_MESSAGES:
-            # Claude models are served on Anthropic's ``/messages``, which the
-            # OpenAI SDK cannot speak: it has no Messages method and sends the
-            # key as a bearer token rather than ``x-api-key``. LiteLLM's
-            # Anthropic route handles both, so the gateway becomes an Anthropic
-            # base URL with the subscription key.
-            from agents.extensions.models.litellm_model import LitellmModel
-
-            model = LitellmModel(
-                model=f"anthropic/{oc.slug}",
-                base_url=oc.messages_url,
-                api_key=opencode.get_api_key(),
-            )
-            if llm.disable_streaming:
-                model = _NonStreamingModel(model)
-                idle_timeout = 0.0
-        elif oc:
-            model = OpenAIChatCompletionsModel(
-                oc.slug, opencode.get_subscription_client(oc.base_url)
-            )
-            if llm.disable_streaming:
-                model = _NonStreamingModel(model)
-                idle_timeout = 0.0
         else:
             model = super().get_model(model_name)
             if llm.disable_streaming:
@@ -598,6 +562,8 @@ DEFAULT_MODEL_RETRY = ModelRetrySettings(
 )
 
 RECOMMENDED_MODEL_NAMES = (
+    "zai/glm-5.3",
+    "zai/glm-5.3-flash",
     "openai/gpt-5.6-sol",
     "openai/gpt-5.6-terra",
     "openai/gpt-5.6-luna",
@@ -606,6 +572,7 @@ RECOMMENDED_MODEL_NAMES = (
     "openai/gpt-5.5",
     "openai/gpt-5.4",
     "openai/gpt-5.3-codex",
+    "anthropic/claude-fable-5-1",
     "anthropic/claude-fable-5",
     "anthropic/claude-opus-5",
     "anthropic/claude-opus-4-8",
@@ -613,6 +580,8 @@ RECOMMENDED_MODEL_NAMES = (
     "anthropic/claude-sonnet-4-6",
     "vertex_ai/gemini-3.1-pro-preview",
     "gemini/gemini-3.1-pro-preview",
+    "vertex_ai/gemini-3.7-flash",
+    "gemini/gemini-3.7-flash",
     "gemini/gemini-3.6-flash",
     "deepseek/deepseek-v4-pro",
     "deepseek/deepseek-v4-flash",
@@ -624,25 +593,27 @@ RECOMMENDED_MODEL_NAMES = (
 
 _RECOMMENDED_MODEL_NAME_SET = frozenset(name.lower() for name in RECOMMENDED_MODEL_NAMES)
 
-FRONTIER_MODEL_FAMILIES = (
-    (("azure", "azure_ai", "bedrock_mantle", "chatgpt", "openai", "opencode"), ("gpt-5",)),
-    (
-        (
-            "anthropic",
-            "azure_ai",
-            "bedrock",
-            "claude",
-            "databricks",
-            "opencode",
-            "snowflake",
-            "vertex_ai",
-        ),
-        ("claude-fable-5", "claude-opus-5", "claude-opus-4", "claude-sonnet-5", "claude-sonnet-4"),
-    ),
-    (("google", "gemini", "opencode", "vertex_ai"), ("gemini-3",)),
-    (("deepseek", "opencode"), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
-    (("alibaba", "dashscope", "opencode", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
-    (("kimi", "moonshot", "moonshotai", "opencode"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
+# Matched against the bare model name only: the route (``openai/``, ``openrouter/``,
+# a local gateway, ...) says nothing about the model's quality.
+FRONTIER_MODEL_PREFIXES = (
+    "gpt-5",
+    "claude-fable-5",
+    "claude-opus-5",
+    "claude-opus-4",
+    "claude-sonnet-5",
+    "claude-sonnet-4",
+    "gemini-3",
+    "deepseek-v4",
+    "deepseek-r1",
+    "deepseek-reasoner",
+    "qwen3.8",
+    "qwen3.7",
+    "qwen3-max",
+    "kimi-k3",
+    "kimi-k2.7",
+    "kimi-k2.6",
+    "glm-5.3",
+    "glm-5.2",
 )
 
 
@@ -650,14 +621,7 @@ def configure_sdk_model_defaults(settings: Settings) -> None:
     """Apply Strix config to SDK-native defaults."""
     llm = settings.llm
     set_tracing_disabled(True)
-    oc = opencode.subscription_model(llm.model)
-    if codex.subscription_model(llm.model) or oc:
-        # A subscription run carries its own client and credentials, so none of
-        # the api_key/api_base defaults below apply. The Anthropic route is the
-        # exception: it goes through LiteLLM, which still needs the
-        # compatibility flags and the cost callback.
-        if oc is not None and oc.protocol == opencode.PROTOCOL_MESSAGES:
-            _configure_litellm_compatibility()
+    if codex.subscription_model(llm.model):
         return
     _configure_litellm_compatibility()
     _configure_openrouter_attribution(llm.model)
@@ -842,11 +806,6 @@ def uses_chat_completions_tool_schema(model_name: str, settings: Settings) -> bo
     """Return whether the resolved SDK route can only receive JSON function tools."""
     if codex.subscription_model(model_name):
         return False
-    oc = opencode.subscription_model(model_name)
-    if oc:
-        # Chat Completions takes JSON function tools; so does the LiteLLM
-        # Anthropic route, which translates them to Anthropic tool blocks.
-        return oc.protocol != opencode.PROTOCOL_RESPONSES
     model = model_name.strip().lower()
     if "/" in model and not model.startswith("openai/"):
         return True
@@ -888,11 +847,8 @@ def is_recommended_or_frontier_model(model_name: str) -> bool:
         return False
     if name in _RECOMMENDED_MODEL_NAME_SET:
         return True
-    provider_name, bare_model_name = _split_model_provider(name)
-    return any(
-        _matches_frontier_family(provider_name, bare_model_name, provider_markers, prefixes)
-        for provider_markers, prefixes in FRONTIER_MODEL_FAMILIES
-    )
+    bare_model_name = name.rsplit("/", 1)[-1]
+    return _matches_model_prefix(bare_model_name, FRONTIER_MODEL_PREFIXES)
 
 
 def _normalized_model_name(model_name: str) -> str:
@@ -904,28 +860,6 @@ def _normalized_model_name(model_name: str) -> str:
     return name
 
 
-def _split_model_provider(model_name: str) -> tuple[str | None, str]:
-    if "/" not in model_name:
-        return None, model_name
-    provider_name, bare_model_name = model_name.rsplit("/", 1)
-    return provider_name, bare_model_name
-
-
-def _matches_frontier_family(
-    provider_name: str | None,
-    model_name: str,
-    provider_markers: tuple[str, ...],
-    model_prefixes: tuple[str, ...],
-) -> bool:
-    if not _matches_model_prefix(model_name, model_prefixes):
-        return False
-    if provider_name is None:
-        return True
-    return _contains_provider_marker(
-        provider_name, provider_markers, split_compound_names=True
-    ) or _contains_provider_marker(model_name, provider_markers)
-
-
 def _matches_model_prefix(model_name: str, model_prefixes: tuple[str, ...]) -> bool:
     return any(
         candidate.startswith(prefix)
@@ -943,16 +877,6 @@ def _model_name_candidates(model_name: str) -> tuple[str, ...]:
     return (model_name, *suffixes)
 
 
-def _contains_provider_marker(
-    value: str, provider_markers: tuple[str, ...], *, split_compound_names: bool = False
-) -> bool:
-    parts = set(value.replace(".", "/").split("/"))
-    if split_compound_names:
-        for separator in ("_", "-"):
-            parts.update(piece for part in tuple(parts) for piece in part.split(separator))
-    return any(marker in parts for marker in provider_markers)
-
-
 def is_known_openai_bare_model(model_name: str) -> bool:
     import litellm
 

strix/config/opencode.py

@@ -1,230 +0,0 @@
-"""OpenCode subscription auth: API-key sign-in and the clients that route
-inference through the OpenCode gateway.
-
-Covers both OpenCode offerings, Zen (pay-as-you-go credits) and Go (the
-monthly subscription), which share one account and API key but live behind
-different gateway base URLs. Unlike the ChatGPT subscription there is no
-OAuth: the user copies a plain API key from https://opencode.ai/auth, and
-using the gateway from other agents is officially supported.
-
-The gateway speaks three protocols and serves each model family on exactly
-one of them (see https://opencode.ai/docs/zen/), answering a request sent to
-the wrong one with an unhandled 500 rather than a 404. ``_protocol()`` holds
-the mapping; ``SubscriptionModel.protocol`` carries the result. Claude runs on
-Anthropic's ``/messages``, which the OpenAI SDK cannot speak, so that route
-goes through LiteLLM instead of the clients built here.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any
-
-import requests
-
-from strix.config import codex
-
-
-if TYPE_CHECKING:
-    from openai import AsyncOpenAI
-
-
-PROVIDER = "opencode"
-
-ZEN_BASE_URL = "https://opencode.ai/zen/v1"
-GO_BASE_URL = "https://opencode.ai/zen/go/v1"
-
-# ``opencode/<model>`` runs on Zen credits; ``opencode-go/<model>`` on the Go
-# subscription (matching OpenCode's own ``opencode-go/`` model ids).
-ZEN_PREFIX = "opencode/"
-GO_PREFIX = "opencode-go/"
-
-AUTH_CONSOLE_URL = "https://opencode.ai/auth"
-
-_KEY_CHECK_TIMEOUT = 30
-
-
-class OpencodeAuthError(Exception):
-    def __init__(self, code: str, message: str | None = None) -> None:
-        self.code = code
-        super().__init__(message or code)
-
-
-PROTOCOL_CHAT = "chat"
-PROTOCOL_RESPONSES = "responses"
-PROTOCOL_MESSAGES = "messages"
-
-PLAN_ZEN = "zen"
-PLAN_GO = "go"
-
-_PLAN_LABELS = {PLAN_ZEN: "OpenCode Zen", PLAN_GO: "OpenCode Go"}
-
-
-@dataclass(frozen=True)
-class SubscriptionModel:
-    slug: str
-    base_url: str
-    protocol: str
-    plan: str
-
-    @property
-    def uses_responses(self) -> bool:
-        return self.protocol == PROTOCOL_RESPONSES
-
-    @property
-    def messages_url(self) -> str:
-        """Anthropic-protocol endpoint for this gateway, e.g. ``.../zen/v1/messages``."""
-        return f"{self.base_url}/messages"
-
-    @property
-    def label(self) -> str:
-        return _PLAN_LABELS[self.plan]
-
-    @property
-    def metered(self) -> bool:
-        """Whether a run spends money per request.
-
-        Zen bills prepaid credits per request, so its runs cost real money and
-        must not be reported as free. Go is a flat monthly fee, where a run's
-        marginal cost genuinely is zero.
-        """
-        return self.plan == PLAN_ZEN
-
-
-def _protocol(slug: str, base_url: str) -> str:
-    """Which wire protocol the gateway serves *slug* on.
-
-    The gateway routes by model family and answers a request sent to the wrong
-    protocol with an unhandled 500 rather than a 404, so the mapping has to be
-    right. Probed against both gateways per family:
-
-    * Claude on Anthropic's ``/messages``
-    * GPT, Grok (Zen) and Muse on OpenAI's ``/responses``
-    * DeepSeek, MiniMax, Kimi, GLM and Qwen on Chat Completions
-
-    Grok is absent from the Go catalog, so its Zen-only Responses route costs
-    nothing there. Kimi and Qwen also answer on ``/messages``, but Chat
-    Completions works for them on both plans and stays the single mapping.
-    """
-    lowered = slug.lower()
-    if lowered.startswith("claude-"):
-        return PROTOCOL_MESSAGES
-    if lowered.startswith(("gpt-", "muse-")):
-        return PROTOCOL_RESPONSES
-    if lowered.startswith("grok") and base_url == ZEN_BASE_URL:
-        return PROTOCOL_RESPONSES
-    return PROTOCOL_CHAT
-
-
-def subscription_model(model_name: str | None) -> SubscriptionModel | None:
-    """The gateway model behind an ``opencode/`` or ``opencode-go/`` STRIX_LLM."""
-    name = (model_name or "").strip()
-    lowered = name.lower()
-    for prefix, base_url, plan in (
-        (GO_PREFIX, GO_BASE_URL, PLAN_GO),
-        (ZEN_PREFIX, ZEN_BASE_URL, PLAN_ZEN),
-    ):
-        if lowered.startswith(prefix):
-            slug = name[len(prefix) :]
-            if not slug:
-                return None
-            return SubscriptionModel(slug, base_url, _protocol(slug, base_url), plan)
-    return None
-
-
-def read_record() -> dict[str, Any] | None:
-    record = codex.read_provider_record(PROVIDER)
-    if not isinstance(record, dict) or record.get("type") != "api_key":
-        return None
-    key = record.get("key")
-    if not isinstance(key, str) or not key:
-        return None
-    return record
-
-
-def is_authenticated() -> bool:
-    return read_record() is not None
-
-
-def save_api_key(key: str) -> None:
-    codex.save_provider_record(PROVIDER, {"type": "api_key", "provider": PROVIDER, "key": key})
-
-
-def logout() -> None:
-    codex.remove_provider_record(PROVIDER)
-
-
-def get_api_key() -> str:
-    record = read_record()
-    if record is None:
-        raise OpencodeAuthError(
-            "not_authenticated", "not signed in; run: strix auth login opencode"
-        )
-    return str(record["key"])
-
-
-def validate_api_key(key: str) -> None:
-    """Check the key against the gateway's models endpoint; raise if rejected."""
-    try:
-        response = requests.get(
-            f"{ZEN_BASE_URL}/models",
-            headers={"Authorization": f"Bearer {key}"},
-            timeout=_KEY_CHECK_TIMEOUT,
-        )
-    except requests.RequestException as exc:
-        raise OpencodeAuthError("unavailable", str(exc)) from exc
-    if response.status_code in (401, 403):
-        raise OpencodeAuthError(
-            "invalid_key", f"OpenCode rejected the API key (HTTP {response.status_code})"
-        )
-    if response.status_code >= 400:
-        raise OpencodeAuthError("http_error", f"HTTP {response.status_code}: {response.text[:300]}")
-
-
-def build_openai_client(base_url: str) -> AsyncOpenAI:
-    import httpx
-    from openai import AsyncOpenAI
-
-    return AsyncOpenAI(
-        api_key=get_api_key(),
-        base_url=base_url,
-        http_client=httpx.AsyncClient(timeout=httpx.Timeout(600.0, connect=30.0)),
-    )
-
-
-_subscription_clients: dict[str, AsyncOpenAI] = {}
-
-
-def get_subscription_client(base_url: str) -> AsyncOpenAI:
-    client = _subscription_clients.get(base_url)
-    if client is None:
-        client = build_openai_client(base_url)
-        _subscription_clients[base_url] = client
-    return client
-
-
-def auth_mode(model_name: str | None) -> str:
-    """Return "subscription" when STRIX_LLM runs on any subscription
-    (OpenCode or ChatGPT), else "api_key"."""
-    if subscription_model(model_name) or codex.subscription_model(model_name):
-        return "subscription"
-    return "api_key"
-
-
-def subscription_plan(model_name: str | None) -> str | None:
-    """Which OpenCode plan STRIX_LLM runs on: "zen", "go", or None.
-
-    Recorded alongside ``subscription_provider`` rather than folded into it, so
-    consumers that compare the provider against "opencode" keep working.
-    """
-    oc = subscription_model(model_name)
-    return oc.plan if oc else None
-
-
-def subscription_provider(model_name: str | None) -> str | None:
-    """The subscription behind STRIX_LLM: "opencode", "chatgpt", or None."""
-    if subscription_model(model_name):
-        return PROVIDER
-    if codex.subscription_model(model_name):
-        return "chatgpt"
-    return None

strix/config/settings.py

@@ -120,6 +120,10 @@ class TelemetrySettings(BaseSettings):
     enabled: bool = Field(default=True, alias="STRIX_TELEMETRY")
 
 
+WebSearchProvider = Literal["auto", "perplexity", "exa"]
+ExaSearchType = Literal["auto", "fast", "instant", "deep-lite", "deep", "deep-reasoning"]
+
+
 class IntegrationSettings(BaseSettings):
     model_config = _BASE_CONFIG
 
@@ -128,6 +132,25 @@ class IntegrationSettings(BaseSettings):
         alias="PERPLEXITY_API_KEY",
         repr=False,
     )
+    exa_api_key: str | None = Field(
+        default=None,
+        alias="EXA_API_KEY",
+        repr=False,
+    )
+    web_search_provider: WebSearchProvider = Field(
+        default="auto",
+        alias="STRIX_WEB_SEARCH_PROVIDER",
+    )
+    exa_search_type: ExaSearchType = Field(
+        default="auto",
+        alias="STRIX_EXA_SEARCH_TYPE",
+    )
+    exa_num_results: int = Field(
+        default=5,
+        ge=1,
+        le=100,
+        alias="STRIX_EXA_NUM_RESULTS",
+    )
     postman_api_key: str | None = Field(
         default=None,
         alias="POSTMAN_API_KEY",

strix/core/agents.py

@@ -24,6 +24,8 @@ logger = logging.getLogger(__name__)
 
 Status = Literal["running", "waiting", "completed", "stopped", "crashed", "failed", "budget_paused"]
 
+TERMINAL_STATUSES: frozenset[str] = frozenset({"completed", "stopped", "crashed", "failed"})
+
 # Why an agent parked. The user can message any agent, so this - not the agent's
 # position in the tree - decides whether waiting is bounded: only an agent waiting
 # on other agents is re-checked on a timer.
@@ -36,6 +38,10 @@ class AgentRuntime:
     task: asyncio.Task[Any] | None = None
     stream: Any | None = None
     interrupt_on_message: bool = False
+    # Whether the agent's loop parks after a terminal state and can be woken by a
+    # later message. A non-interactive loop returns instead, so once such an
+    # agent is terminal nothing will ever read its mailbox again.
+    resumable: bool = True
     wake: asyncio.Event = field(default_factory=asyncio.Event)
     mailbox: list[dict[str, Any]] = field(default_factory=list)
     user_wake_required: bool = False
@@ -175,6 +181,7 @@ class AgentCoordinator:
         session: Session | None = None,
         task: asyncio.Task[Any] | None = None,
         interrupt_on_message: bool | None = None,
+        resumable: bool | None = None,
     ) -> None:
         async with self._lock:
             runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
@@ -184,6 +191,8 @@ class AgentCoordinator:
                 runtime.task = task
             if interrupt_on_message is not None:
                 runtime.interrupt_on_message = interrupt_on_message
+            if resumable is not None:
+                runtime.resumable = resumable
 
     async def mark_running(self, agent_id: str) -> None:
         async with self._lock:
@@ -275,10 +284,29 @@ class AgentCoordinator:
             self._parent_notified.add(agent_id)
             return True
 
+    def _unreachable_locked(self, agent_id: str) -> bool:
+        """True when the agent is terminal and no loop will ever read its mailbox."""
+        if self.statuses.get(agent_id) not in TERMINAL_STATUSES:
+            return False
+        runtime = self.runtimes.get(agent_id)
+        return runtime is not None and not runtime.resumable
+
+    async def reachability(self, agent_id: str) -> tuple[bool, Status | None]:
+        """Whether a message to ``agent_id`` can still be acted on, plus its status."""
+        async with self._lock:
+            status = self.statuses.get(agent_id)
+            if status is None:
+                return False, None
+            return not self._unreachable_locked(agent_id), status
+
     async def send(
         self, target_agent_id: str, message: dict[str, Any], *, interrupt: bool = True
     ) -> bool:
-        """Queue a user/peer message in the target's mailbox and wake it."""
+        """Queue a user/peer message in the target's mailbox and wake it.
+
+        Returns False when nothing will ever read the message: the target is
+        unknown, or it is terminal and its loop does not park for wake-ups.
+        """
         from_user = message.get("from") == "user"
         if from_user and self._budget_paused:
             await self.resume_from_budget_pause(exclude=target_agent_id)
@@ -286,6 +314,13 @@ class AgentCoordinator:
             if target_agent_id not in self.statuses:
                 logger.debug("agent.send dropped unknown target=%s", target_agent_id)
                 return False
+            if self._unreachable_locked(target_agent_id):
+                logger.info(
+                    "agent.send dropped: target=%s is %s and cannot be woken",
+                    target_agent_id,
+                    self.statuses[target_agent_id],
+                )
+                return False
             runtime = self.runtimes.setdefault(target_agent_id, AgentRuntime())
             runtime.mailbox.append(dict(message))
             self.pending_counts[target_agent_id] = self.pending_counts.get(target_agent_id, 0) + 1

strix/core/execution.py

@@ -202,6 +202,7 @@ async def run_agent_loop(
         agent_id,
         session=session,
         interrupt_on_message=interactive,
+        resumable=interactive,
     )
     result: RunResultBase | None = None
 
@@ -1006,7 +1007,7 @@ async def _start_child_runner(
 ) -> None:
     session = open_agent_session(child_id, agents_db_path)
     sessions_to_close.append(session)
-    await coordinator.attach_runtime(child_id, session=session)
+    await coordinator.attach_runtime(child_id, session=session, resumable=interactive)
 
     child_ctx: dict[str, Any] = dict(parent_ctx)
     child_ctx["agent_id"] = child_id

strix/core/inputs.py

@@ -8,7 +8,6 @@ from typing import TYPE_CHECKING, Any
 from agents.model_settings import ModelSettings
 from openai.types.shared import Reasoning
 
-from strix.config import opencode
 from strix.config.models import (
     DEFAULT_MODEL_RETRY,
     OPENROUTER_ATTRIBUTION_HEADERS,
@@ -326,13 +325,6 @@ def _prompt_cache_extra_args(model_name: str) -> dict[str, Any] | None:
     """
     if not is_claude_model(model_name) or not routes_through_litellm(model_name):
         return None
-    # OpenCode's Chat Completions and Responses routes use the raw OpenAI SDK,
-    # which rejects this LiteLLM-only argument. Its Anthropic route does go
-    # through LiteLLM, so the injection points apply there as they would for a
-    # direct Anthropic key.
-    oc = opencode.subscription_model(model_name)
-    if oc is not None and oc.protocol != opencode.PROTOCOL_MESSAGES:
-        return None
     if is_bedrock_route(model_name) and not bedrock_route_supports_prompt_caching(model_name):
         return None
 

strix/core/runner.py

@@ -45,6 +45,7 @@ from strix.core.paths import run_dir_for, runtime_state_dir
 from strix.core.sessions import open_agent_session
 from strix.report.state import get_global_report_state
 from strix.runtime import session_manager
+from strix.telemetry import set_scan_phase
 from strix.telemetry.logging import set_scan_id, setup_scan_logging
 from strix.tools.output_store import (
     WORKSPACE_SPILL_DIR,
@@ -116,6 +117,13 @@ def _record_mcp_connections(connections: list[ConnectedMcpServer]) -> None:
     report_state.record_mcp_connections([connection.name for connection in connections])
 
 
+def _note_exit_reason(reason: str) -> None:
+    """Record why the scan stopped so the end-of-scan beacon reports it."""
+    report_state = get_global_report_state()
+    if report_state is not None and report_state.scan_ended_exit_reason is None:
+        report_state.scan_ended_exit_reason = reason
+
+
 def _persist_mcp_status(roster: list[dict[str, Any]]) -> None:
     """Write the run's non-secret MCP connection status roster to run.json.
 
@@ -313,6 +321,7 @@ async def run_strix_scan(
         root_id = uuid.uuid4().hex[:8]
 
     logger.info("Bringing up sandbox session for scan %s", scan_id)
+    set_scan_phase("sandbox_init")
     bundle = await session_manager.create_or_reuse(
         scan_id,
         image=image,
@@ -322,6 +331,7 @@ async def run_strix_scan(
     )
     report("Waiting for the first model response")
     logger.info("Sandbox ready for scan %s", scan_id)
+    set_scan_phase("agent_setup")
 
     sandbox_session = bundle["session"]
 
@@ -428,6 +438,7 @@ async def run_strix_scan(
                         }
                         for summary in mcp_registry.summaries()
                     ]
+
                     # Feed a non-secret connection roster (name / provider /
                     # tool_count / dead) to two consumers: once now (all
                     # currently healthy) and again whenever a connection later
@@ -572,6 +583,7 @@ async def run_strix_scan(
         async with coordinator._lock:
             root_status = coordinator.statuses.get(root_id)
 
+        set_scan_phase("agent_loop")
         result = await run_agent_loop(
             agent=root_agent,
             initial_input=initial_input,
@@ -609,6 +621,7 @@ async def run_strix_scan(
         return result  # noqa: TRY300
     except BudgetExceededError as exc:
         logger.info("Scan %s stopped: %s", scan_id, exc)
+        _note_exit_reason("budget_exceeded")
         if root_id is not None:
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
@@ -621,6 +634,7 @@ async def run_strix_scan(
             exc,
             scan_id,
         )
+        _note_exit_reason("rate_limited")
         if root_id is not None:
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")

strix/interface/auth_cli.py

@@ -1,9 +1,8 @@
-"""`strix auth` — subscription sign-in (login / status / logout).
+"""`strix auth` — ChatGPT subscription sign-in (login / status / logout).
 
-Signing in only stores credentials (``~/.strix/subscription-auth.json``); model
+Signing in only stores OAuth tokens (``~/.strix/subscription-auth.json``); model
 selection stays with ``STRIX_LLM``. A ``chatgpt/<model>`` STRIX_LLM runs on the
-ChatGPT subscription; ``opencode/<model>`` (Zen credits) or
-``opencode-go/<model>`` (Go subscription) run on OpenCode.
+subscription.
 """
 
 from __future__ import annotations
@@ -22,7 +21,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode
+from strix.config import codex, load_settings
 
 
 if TYPE_CHECKING:
@@ -33,20 +32,13 @@ logger = logging.getLogger(__name__)
 
 _CALLBACK_TIMEOUT_S = 300
 
-# CLI-facing name for the default login provider. Internally this is the Codex
-# OAuth flow (``codex.PROVIDER``), but users know it as ChatGPT, so that's what
-# the command and messaging say. ``codex`` is accepted as an alias.
+# CLI-facing name for the login provider. Internally this is the Codex OAuth
+# flow (``codex.PROVIDER``), but users know it as ChatGPT, so that's what the
+# command and messaging say. ``codex`` is accepted as an alias.
 LOGIN_PROVIDER = "chatgpt"
 _ACCEPTED_PROVIDERS = frozenset({LOGIN_PROVIDER, codex.PROVIDER})
-_OPENCODE_PROVIDERS = frozenset({opencode.PROVIDER, "opencode-go", "zen"})
 
-_USAGE = (
-    "Usage:\n"
-    "  strix auth login chatgpt [--manual]\n"
-    "  strix auth login opencode\n"
-    "  strix auth status\n"
-    "  strix auth logout [chatgpt|opencode]"
-)
+_USAGE = "Usage:\n  strix auth login chatgpt [--manual]\n  strix auth status\n  strix auth logout"
 
 
 def run_auth(argv: list[str]) -> int:
@@ -63,7 +55,7 @@ def run_auth(argv: list[str]) -> int:
     handlers: dict[str, Callable[[], int]] = {
         "login": lambda: _login(console, rest),
         "status": lambda: _status(console),
-        "logout": lambda: _logout(console, rest),
+        "logout": lambda: _logout(console),
     }
     handler = handlers.get(subcommand)
     if handler is not None:
@@ -92,14 +84,10 @@ def _login(console: Console, argv: list[str]) -> int:
     except SystemExit as exc:  # argparse already printed the message
         return int(exc.code or 2)
 
-    if args.provider.lower() in _OPENCODE_PROVIDERS:
-        return _login_opencode(console)
-
     if args.provider.lower() not in _ACCEPTED_PROVIDERS:
         console.print(
             f"[red]Unsupported provider:[/] {args.provider}. "
-            f"Supported: '{LOGIN_PROVIDER}' (ChatGPT subscription) and "
-            f"'{opencode.PROVIDER}' (OpenCode Zen/Go)."
+            f"Only '{LOGIN_PROVIDER}' (ChatGPT subscription) is supported."
         )
         return 2
 
@@ -127,63 +115,6 @@ def _login(console: Console, argv: list[str]) -> int:
     return 0
 
 
-def _login_opencode(console: Console) -> int:
-    console.print()
-    console.print("[bold]Signing in with OpenCode[/] [dim](provider: opencode)[/]")
-    console.print(
-        "[dim]This uses your OpenCode Zen credits or Go subscription for inference.\n"
-        f"Get your API key at {opencode.AUTH_CONSOLE_URL}[/]"
-    )
-    console.print()
-    try:
-        key = console.input("Paste your OpenCode API key: ", password=True).strip()
-    except (EOFError, KeyboardInterrupt):
-        console.print("\n[yellow]Sign-in cancelled.[/]")
-        return 130
-    if not key:
-        console.print("[red]No API key provided.[/]")
-        return 2
-    try:
-        opencode.validate_api_key(key)
-    except opencode.OpencodeAuthError as exc:
-        console.print(f"[red]SIGN-IN FAILED:[/] {exc}")
-        return 1
-    opencode.save_api_key(key)
-    _print_opencode_success(console)
-    return 0
-
-
-def _print_opencode_success(console: Console) -> None:
-    text = Text()
-    text.append("Signed in with your OpenCode account", style="bold #22c55e")
-    text.append("\n\n", style="white")
-    text.append("Set ", style="white")
-    text.append("STRIX_LLM", style="bold white")
-    text.append(" to an ", style="white")
-    text.append("opencode/", style="bold cyan")
-    text.append(" model (e.g. ", style="white")
-    text.append("opencode/claude-sonnet-5", style="bold cyan")
-    text.append(") to run on Zen credits, or ", style="white")
-    text.append("opencode-go/", style="bold cyan")
-    text.append(" (e.g. ", style="white")
-    text.append("opencode-go/kimi-k3", style="bold cyan")
-    text.append(") to run on the Go subscription.", style="white")
-    text.append("\n\n", style="white")
-    text.append("Run a scan as usual, e.g. ", style="white")
-    text.append("strix --target https://example.com", style="bold cyan")
-    console.print()
-    console.print(
-        Panel(
-            text,
-            title="[bold white]STRIX",
-            title_align="left",
-            border_style="#22c55e",
-            padding=(1, 2),
-        )
-    )
-    console.print()
-
-
 def _run_oauth_flow(
     console: Console,
     authorize_url: str,
@@ -313,41 +244,24 @@ def _first(query: dict[str, list[str]], key: str) -> str | None:
 
 def _status(console: Console) -> int:
     record = codex.read_record()
-    opencode_signed_in = opencode.is_authenticated()
-    if record is None and not opencode_signed_in:
-        console.print(
-            "[yellow]Not signed in.[/] Run [cyan]strix auth login chatgpt[/] or "
-            "[cyan]strix auth login opencode[/] to sign in."
-        )
+    if record is None:
+        console.print("[yellow]Not signed in.[/] Run [cyan]strix auth login chatgpt[/] to sign in.")
         return 1
     settings = load_settings()
-    if record is not None:
-        console.print("[green]Signed in[/] with a ChatGPT subscription.")
-        console.print(f"  Account: [bold]{record.get('account_id')}[/]")
-    if opencode_signed_in:
-        console.print("[green]Signed in[/] with an OpenCode account.")
-    if codex.subscription_model(settings.llm.model) or opencode.subscription_model(
-        settings.llm.model
-    ):
+    console.print("[green]Signed in[/] with a ChatGPT subscription.")
+    console.print(f"  Account: [bold]{record.get('account_id')}[/]")
+    if codex.subscription_model(settings.llm.model):
         console.print(f"  Runs use the subscription (STRIX_LLM=[bold]{settings.llm.model}[/]).")
     else:
         console.print(
-            "  [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.4[/] or "
-            "[cyan]opencode/claude-sonnet-5[/] to run on a subscription."
+            "  [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.4[/] "
+            "to run on the subscription."
         )
     return 0
 
 
-def _logout(console: Console, argv: list[str] | None = None) -> int:
-    target = (argv[0].lower() if argv else "") or "all"
-    if target in _ACCEPTED_PROVIDERS or target == "all":
-        codex.logout()
-    if target in _OPENCODE_PROVIDERS or target == "all":
-        opencode.logout()
-    if target != "all" and target not in _ACCEPTED_PROVIDERS | _OPENCODE_PROVIDERS:
-        console.print(f"[red]Unknown provider:[/] {target}\n")
-        console.print(_USAGE)
-        return 2
+def _logout(console: Console) -> int:
+    codex.logout()
     console.print("[green]Signed out.[/] Stored subscription credentials removed.")
     return 0
 

strix/interface/cli.py

@@ -105,14 +105,15 @@ async def run_cli(args: Any) -> None:  # noqa: PLR0915
     report_state.set_scan_config(scan_config)
     report_state.save_run_data()
 
-    def display_vulnerability(report: dict[str, Any]) -> None:
+    def display_vulnerability(report: dict[str, Any], *, updated: bool = False) -> None:
         report_id = report.get("id", "unknown")
 
         vuln_text = format_vulnerability_report(report)
 
+        suffix = " (updated)" if updated else ""
         vuln_panel = Panel(
             vuln_text,
-            title=f"[bold red]{report_id.upper()}",
+            title=f"[bold red]{report_id.upper()}{suffix}",
             title_align="left",
             border_style="red",
             padding=(1, 2),
@@ -122,6 +123,9 @@ async def run_cli(args: Any) -> None:  # noqa: PLR0915
         console.print()
 
     report_state.vulnerability_found_callback = display_vulnerability
+    report_state.vulnerability_updated_callback = lambda report: display_vulnerability(
+        report, updated=True
+    )
 
     def cleanup_on_exit() -> None:
         report_state.cleanup()

strix/interface/cli_args.py

@@ -98,6 +98,14 @@ Examples:
   # Extra files placed in the sandbox workspace
   strix --target ./my-project --workspace-file ./wordlist.txt
   strix --target https://app.com --workspace-file ./openapi.yaml:specs/openapi.yaml
+
+Strix Cloud:
+  strix cloud login
+  strix cloud scans start --source . --yes --wait
+  strix cloud                      # list every cloud resource
+
+  Run a pentest in Strix Cloud     https://app.strix.ai
+  Try Strix Enterprise             https://strix.ai/demo
         """,
     )
 

strix/interface/cloud/__init__.py

@@ -0,0 +1,169 @@
+"""`strix cloud` — the managed Strix platform (app.strix.ai) from the terminal.
+
+Every command maps to one operation of the public REST API. Output is JSON
+when stdout is not a terminal, so agents can parse every result. Exit codes:
+0 success, 1 error, 2 invalid usage, 4 authentication required, 5 payment
+required.
+"""
+
+from __future__ import annotations
+
+import json
+import sys
+
+from rich.console import Console
+from rich.markup import escape
+
+from strix.interface.cloud import http
+from strix.interface.cloud.render import json_mode
+from strix.interface.cloud.runner import resolve, run
+from strix.interface.cloud.session import run_session
+from strix.interface.cloud.spec import DEFAULT_VERBS, GROUP_HELP, SPEC
+from strix.interface.cloud.workspaces import run_workspace_use
+from strix.interface.platform_cli import run_login
+from strix.interface.terminal_text import sanitize_terminal_text
+
+
+_USAGE_HEADER = """[bold]Usage:[/] strix cloud <command> [arguments]
+
+[bold]Session commands:[/]
+  login       Sign in to the managed platform and store an API token
+  logout      Remove the stored API token
+  whoami      Show the stored account, workspace, and token state
+  session     Inspect or narrow the remote CLI session
+  credits     Show the credit balance of the workspace
+
+[bold]Resource commands:[/]"""
+
+_USAGE_FOOTER = """
+Run [bold]strix cloud <command> help[/] to list its verbs. Common read-only
+commands may also run their default verb when no verb is given.
+Every REST resource command accepts [bold]--json[/] and [bold]--token[/]. Write
+commands accept [bold]--data[/] with a JSON object of extra request fields.
+Login is an interactive device flow; [bold]whoami[/] and [bold]logout[/] also
+produce JSON automatically when output is redirected.
+API reference: https://docs.app.strix.ai"""
+
+_HELP_TOKENS = frozenset({"-h", "--help", "help"})
+
+
+def _is_help_request(argv: list[str]) -> bool:
+    """Recognize a help token with an optional JSON-output flag in either order."""
+    return sum(argument in _HELP_TOKENS for argument in argv) == 1 and all(
+        argument in _HELP_TOKENS or argument == "--json" for argument in argv
+    )
+
+
+def run_cloud(argv: list[str]) -> int:
+    """Run a managed-cloud command without ever leaking a Ctrl-C traceback."""
+    try:
+        return _run_cloud(argv)
+    except KeyboardInterrupt:
+        if json_mode(flag="--json" in argv):
+            sys.stdout.write(json.dumps({"error": "Interrupted.", "interrupted": True}) + "\n")
+        else:
+            Console(stderr=True).print("[yellow]Interrupted.[/]")
+        return 130
+
+
+def _run_cloud(argv: list[str]) -> int:  # noqa: PLR0911, PLR0912
+    """Entry point for ``strix cloud …``. Returns a process exit code."""
+    console = Console()
+    as_json = json_mode(flag="--json" in argv)
+    if not argv or _is_help_request(argv):
+        if as_json:
+            _print_usage_json()
+        else:
+            _print_usage(console)
+        return 0
+    if argv == ["--json"]:
+        _print_usage_json()
+        return 0
+
+    group, rest = argv[0], argv[1:]
+    if group == "workspace":
+        group = "workspaces"
+    if group in ("login", "logout", "whoami"):
+        return _run_session(console, group, rest)
+    if group == "session":
+        return run_session(rest)
+    if group == "credits":
+        group, rest = "billing", ["credits", *rest]
+    if group == "workspaces" and rest and rest[0] == "use":
+        try:
+            return run_workspace_use(rest[1:])
+        except http.CloudError as exc:
+            if "--json" in rest:
+                sys.stdout.write(json.dumps({"error": str(exc)}) + "\n")
+            else:
+                console.print(f"[red]Error:[/] {escape(sanitize_terminal_text(exc))}")
+            return exc.exit_code
+
+    if group not in SPEC:
+        if as_json:
+            sys.stdout.write(json.dumps({"error": f"unknown command: {group}"}) + "\n")
+            return 2
+        console.print(f"[red]Unknown command:[/] {escape(sanitize_terminal_text(group))}")
+        _print_usage(console)
+        return 2
+    group_help = _is_help_request(rest)
+    resolved = None if group_help else resolve(group, rest)
+    if resolved is None:
+        help_tokens: set[str] = set(_HELP_TOKENS) if group_help else set()
+        invalid = [arg for arg in rest if arg != "--json" and arg not in help_tokens]
+        _print_verbs(console, group, as_json=as_json, error="unknown verb" if invalid else None)
+        return 2 if invalid else 0
+    cmd, remaining = resolved
+    verb_label = " ".join(rest[: len(rest) - len(remaining)]) or DEFAULT_VERBS.get(group, "")
+    return run(group, verb_label, cmd, remaining)
+
+
+def _run_session(_console: Console, group: str, rest: list[str]) -> int:
+    if rest and rest[0] == "help":
+        rest = ["--help", *rest[1:]]
+    session_argv = {
+        "login": rest,
+        "logout": ["logout", *rest],
+        "whoami": ["status", *rest],
+    }
+    return run_login(session_argv[group])
+
+
+def _print_usage(console: Console) -> None:
+    console.print(_USAGE_HEADER)
+    for group in SPEC:
+        console.print(f"  {group:<14}{GROUP_HELP.get(group, '')}")
+    console.print(_USAGE_FOOTER)
+
+
+def _print_verbs(
+    console: Console, group: str, *, as_json: bool = False, error: str | None = None
+) -> None:
+    if as_json:
+        verbs: list[dict[str, str]] = [
+            {"name": verb, "help": command.help} for verb, command in SPEC[group].items()
+        ]
+        if group == "workspaces":
+            verbs.append({"name": "use", "help": "Switch the stored token to another workspace."})
+        payload: dict[str, object] = {
+            "command": f"strix cloud {group}",
+            "verbs": verbs,
+        }
+        if error:
+            payload["error"] = error
+        sys.stdout.write(json.dumps(payload, indent=2) + "\n")
+        return
+    console.print(f"[bold]strix cloud {group}[/] verbs:")
+    for verb, cmd in SPEC[group].items():
+        console.print(f"  {verb:<28}{cmd.help}")
+    if group == "workspaces":
+        console.print(f"  {'use':<28}Switch the stored token to another workspace.")
+
+
+def _print_usage_json() -> None:
+    payload = {
+        "command": "strix cloud",
+        "session_commands": ["login", "logout", "whoami", "session", "credits"],
+        "resource_commands": [{"name": group, "help": GROUP_HELP.get(group, "")} for group in SPEC],
+    }
+    sys.stdout.write(json.dumps(payload, indent=2) + "\n")

strix/interface/cloud/arguments.py

@@ -0,0 +1,18 @@
+"""Argument parsing that reports managed-cloud usage errors through one contract."""
+
+from __future__ import annotations
+
+import argparse
+from typing import NoReturn
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+
+
+class CloudArgumentParser(argparse.ArgumentParser):
+    """Raise a typed usage error instead of printing argparse prose and exiting."""
+
+    def error(self, message: str) -> NoReturn:
+        raise http.CloudError(
+            f"invalid arguments for {self.prog}: {message}",
+            exit_code=http.EXIT_USAGE,
+        )

strix/interface/cloud/billing.py

@@ -0,0 +1,718 @@
+"""Billing top-up and agent-wallet execution for ``strix cloud``."""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+import shutil
+import subprocess
+import sys
+import tempfile
+import webbrowser
+from contextlib import suppress
+from dataclasses import dataclass
+from pathlib import Path
+from typing import TYPE_CHECKING, Any, cast
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+from strix.interface.cloud.payment_proxy import WalletUpstreamResponse, wallet_payment_bridge
+from strix.interface.cloud.render import emit
+from strix.interface.terminal_text import sanitize_terminal_text
+
+
+if TYPE_CHECKING:
+    import argparse
+
+    from rich.console import Console
+
+
+_MAX_WALLET_DETAIL_CHARS = 2_000
+# Keep the wallet client on the exact protocol implementation used by the
+# platform. This version is also old enough to remain installable in npm
+# environments that apply a short package-publication safety window.
+_MPPX_PACKAGE = "mppx@0.8.17"
+# Stripe's own wallet client. It runs the complete challenge flow: it creates a
+# spend request, waits for the person to approve it in the Link app, and retries
+# the payment with the approved credential.
+_LINK_CLI_PACKAGE = "@stripe/link-cli@0.13.1"
+_LINK_CLI_CLIENT_NAME = "Strix CLI"
+_LINK_LOGIN_TIMEOUT_S = 300
+# Poll every 2 seconds while the person approves the spend request in the Link
+# app. 150 attempts give the person 5 minutes.
+_LINK_APPROVAL_POLL_INTERVAL_S = 2
+_LINK_APPROVAL_MAX_ATTEMPTS = 150
+# Bound every wallet subprocess so a stalled npm download or wallet request
+# cannot block the top-up command forever. The poll step gets the full
+# approval window plus this margin.
+_WALLET_STEP_TIMEOUT_S = 300
+_LINK_APPROVAL_TIMEOUT_S = (
+    _LINK_APPROVAL_POLL_INTERVAL_S * _LINK_APPROVAL_MAX_ATTEMPTS + _WALLET_STEP_TIMEOUT_S
+)
+_NPM_REGISTRY = "https://registry.npmjs.org"
+_WALLET_ENV_NAMES = frozenset(
+    {
+        "ALL_PROXY",
+        "APPDATA",
+        "COLORTERM",
+        "COMSPEC",
+        "FORCE_COLOR",
+        "HOME",
+        "HTTPS_PROXY",
+        "HTTP_PROXY",
+        "LANG",
+        "LC_ALL",
+        "LC_CTYPE",
+        "LOCALAPPDATA",
+        "NO_COLOR",
+        "NO_PROXY",
+        "PATH",
+        "PATHEXT",
+        "SSL_CERT_DIR",
+        "SSL_CERT_FILE",
+        "SYSTEMROOT",
+        "TEMP",
+        "TERM",
+        "TMP",
+        "TMPDIR",
+        "USERPROFILE",
+        "XDG_CONFIG_HOME",
+        "XDG_DATA_HOME",
+        "XDG_STATE_HOME",
+        "all_proxy",
+        "http_proxy",
+        "https_proxy",
+        "no_proxy",
+    }
+)
+_AUTHORIZATION_SECRET = re.compile(r"(?i)((?:bearer|payment)\s+)[^\s\"']+")
+_LOOPBACK_NO_PROXY = ("127.0.0.1", "localhost", "::1")
+
+
+@dataclass(frozen=True)
+class _WalletClientResult:
+    process: subprocess.CompletedProcess[str]
+    upstream_responses: tuple[WalletUpstreamResponse, ...]
+
+
+def run_topup(  # noqa: PLR0911, PLR0912, PLR0915
+    console: Console,
+    args: argparse.Namespace,
+    body: dict[str, Any],
+    *,
+    as_json: bool,
+    token: str | None,
+) -> int:
+    """Handle the HTTP 402 challenge and optional agent-wallet payment."""
+    response = http.request("POST", "/billing/topup", token=token, body=body)
+    if response.status_code != 402:
+        emit(console, http.check(response), as_json=as_json)
+        return http.EXIT_OK
+
+    challenge = http.parsed(response)
+    if getattr(args, "no_pay", False):
+        emit(
+            console,
+            {"error": "Payment required", "challenge": challenge},
+            as_json=as_json,
+        )
+        return http.EXIT_PAYMENT
+
+    credit_count = body.get("credits")
+    if not getattr(args, "yes", False):
+        if as_json or not (sys.stdin.isatty() and sys.stdout.isatty()):
+            emit(
+                console,
+                {
+                    "error": (
+                        "Payment requires explicit approval in non-interactive mode. "
+                        "Review the challenge, then re-run with --yes to authorize payment."
+                    ),
+                    "challenge": challenge,
+                },
+                as_json=as_json,
+            )
+            return http.EXIT_PAYMENT
+        answer = console.input(f"Buy {credit_count} credit(s) now? [y/N]: ").strip().lower()
+        if answer not in ("y", "yes"):
+            console.print("[yellow]Payment cancelled.[/]")
+            return http.EXIT_PAYMENT
+
+    npx = shutil.which("npx")
+    if npx is None:
+        message = (
+            "Payment requires a wallet client. Install Node.js and run the command again, "
+            "or pay the challenge with an MPP wallet client."
+        )
+        if as_json:
+            emit(
+                console,
+                {"error": message, "challenge": challenge},
+                as_json=True,
+            )
+        else:
+            emit(console, challenge, as_json=False)
+            console.print(f"[yellow]Payment required.[/] {message}")
+        return http.EXIT_PAYMENT
+
+    payment_method = getattr(args, "payment_method", None) or os.environ.get(
+        "MPPX_STRIPE_PAYMENT_METHOD"
+    )
+    use_link_wallet = payment_method is None and not _mppx_wallet_configured()
+    if use_link_wallet:
+        setup_error = _prepare_link_wallet(console, npx, as_json=as_json)
+        if setup_error is not None:
+            emit(
+                console,
+                {"error": setup_error, "challenge": challenge},
+                as_json=as_json,
+            )
+            return http.EXIT_PAYMENT
+    try:
+        wallet_result = _run_wallet_client(
+            console,
+            npx,
+            args,
+            body,
+            token=token,
+            payment_method=payment_method,
+            use_link_wallet=use_link_wallet,
+            capture_output=as_json,
+        )
+    except KeyboardInterrupt:
+        emit(
+            console,
+            {
+                "error": (
+                    "Payment was interrupted after the wallet started. The outcome is unknown; "
+                    "run `strix cloud billing credits` and check the balance before retrying."
+                ),
+                "interrupted": True,
+                "payment_outcome_unknown": True,
+            },
+            as_json=as_json,
+        )
+        return 130
+    except OSError:
+        emit(
+            console,
+            {
+                "error": "Could not start the wallet client securely.",
+                "challenge": challenge,
+            },
+            as_json=as_json,
+        )
+        return http.EXIT_PAYMENT
+
+    result = wallet_result.process
+    confirmed_receipt = _confirmed_topup_receipt(wallet_result.upstream_responses)
+    if confirmed_receipt is not None:
+        emit(console, confirmed_receipt, as_json=as_json)
+        return http.EXIT_OK
+
+    stdout = str(getattr(result, "stdout", "") or "").strip()
+    stderr = str(getattr(result, "stderr", "") or "").strip()
+    if not as_json:
+        console.print(
+            "[yellow]The wallet exited without a confirmed receipt. The payment outcome is "
+            "unknown; run `strix cloud billing credits` before retrying.[/]"
+        )
+        detail = _wallet_detail(stderr or stdout or "")
+        if detail:
+            console.print(f"[dim]Wallet output: {detail}[/]")
+        return http.EXIT_PAYMENT
+    if result.returncode == 0:
+        try:
+            receipt = json.loads(stdout)
+        except (TypeError, ValueError):
+            emit(
+                console,
+                {
+                    "error": (
+                        "The wallet reported success but did not return JSON. Check the credit "
+                        "balance before retrying payment."
+                    ),
+                    "detail": _wallet_detail(stdout or stderr or "No wallet output was returned."),
+                    "payment_outcome_unknown": True,
+                },
+                as_json=True,
+            )
+            return http.EXIT_PAYMENT
+        if not _valid_topup_receipt(receipt):
+            emit(
+                console,
+                {
+                    "error": (
+                        "The wallet returned an invalid top-up receipt. Check the credit balance "
+                        "before retrying payment."
+                    ),
+                    "detail": _wallet_detail(stdout),
+                    "payment_outcome_unknown": True,
+                },
+                as_json=True,
+            )
+            return http.EXIT_PAYMENT
+        emit(
+            console,
+            {
+                "error": (
+                    "The wallet returned a receipt, but the Strix billing endpoint did not "
+                    "confirm it. Check the credit balance before retrying payment."
+                ),
+                "detail": _wallet_detail(stdout),
+                "payment_outcome_unknown": True,
+            },
+            as_json=True,
+        )
+        return http.EXIT_PAYMENT
+
+    emit(
+        console,
+        {
+            "error": (
+                "The wallet exited without a confirmed receipt. The payment outcome is unknown; "
+                "run `strix cloud billing credits` and check the balance before retrying."
+            ),
+            "detail": _wallet_detail(
+                stderr or stdout or f"Wallet client exited with status {result.returncode}."
+            ),
+            "wallet_exit_code": result.returncode,
+            "payment_outcome_unknown": True,
+        },
+        as_json=True,
+    )
+    return http.EXIT_PAYMENT
+
+
+def _run_wallet_client(
+    console: Console,
+    npx: str,
+    args: argparse.Namespace,
+    body: dict[str, Any],
+    *,
+    token: str | None,
+    payment_method: str | None,
+    use_link_wallet: bool,
+    capture_output: bool,
+) -> _WalletClientResult:
+    """Run the wallet through the loopback bridge without exposing the API token."""
+    upstream_url = f"{http.app_url()}/api/v1/billing/topup"
+    body_json = json.dumps(body)
+    wallet_env = _wallet_environment()
+    upstream_responses: list[WalletUpstreamResponse] = []
+    with tempfile.TemporaryDirectory(prefix="strix-wallet-") as wallet_cwd:
+        wallet_root = Path(wallet_cwd)
+        user_config = wallet_root / "user.npmrc"
+        global_config = wallet_root / "global.npmrc"
+        user_config.touch(mode=0o600)
+        global_config.touch(mode=0o600)
+        npx_prefix = _npx_prefix(npx, wallet_root)
+        with wallet_payment_bridge(
+            upstream_url=upstream_url,
+            api_token=http.api_token(token),
+            workspace_id=http.expected_workspace_id(token_override=token is not None),
+            expected_body=body_json.encode(),
+            timeout=getattr(args, "timeout", None),
+            response_observer=upstream_responses.append,
+        ) as wallet_url:
+            if use_link_wallet:
+                process = _run_link_wallet_flow(
+                    console,
+                    npx_prefix,
+                    wallet_url,
+                    body,
+                    body_json,
+                    wallet_env,
+                    wallet_root,
+                    quiet=capture_output,
+                )
+            else:
+                command = [
+                    *npx_prefix,
+                    _MPPX_PACKAGE,
+                    wallet_url,
+                    "--fail",
+                    "-J",
+                    body_json,
+                ]
+                if payment_method:
+                    command += ["-M", f"paymentMethod={payment_method}"]
+                try:
+                    process = subprocess.run(  # noqa: S603
+                        command,
+                        check=False,
+                        capture_output=capture_output,
+                        text=True,
+                        env=wallet_env,
+                        cwd=wallet_root,
+                        timeout=_LINK_APPROVAL_TIMEOUT_S,
+                    )
+                except subprocess.TimeoutExpired as timeout_error:
+                    process = subprocess.CompletedProcess(
+                        args=command,
+                        returncode=1,
+                        stdout=_decoded_stream(timeout_error.stdout),
+                        stderr=(
+                            "The wallet step did not complete within "
+                            f"{_LINK_APPROVAL_TIMEOUT_S} seconds."
+                        ),
+                    )
+    return _WalletClientResult(process=process, upstream_responses=tuple(upstream_responses))
+
+
+def _run_link_wallet_flow(
+    console: Console,
+    npx_prefix: list[str],
+    wallet_url: str,
+    body: dict[str, Any],
+    body_json: str,
+    wallet_env: dict[str, str],
+    wallet_root: Path,
+    *,
+    quiet: bool,
+) -> subprocess.CompletedProcess[str]:
+    """Create the spend request, wait for approval in the Link app, then pay."""
+
+    def run_step(
+        arguments: list[str],
+        progress_message: str,
+        timeout: int = _WALLET_STEP_TIMEOUT_S,
+    ) -> subprocess.CompletedProcess[str]:
+        command = [*npx_prefix, _LINK_CLI_PACKAGE, *arguments]
+
+        def run() -> subprocess.CompletedProcess[str]:
+            try:
+                return subprocess.run(  # noqa: S603
+                    command,
+                    check=False,
+                    capture_output=True,
+                    text=True,
+                    env=wallet_env,
+                    cwd=wallet_root,
+                    timeout=timeout,
+                )
+            except subprocess.TimeoutExpired as timeout_error:
+                return subprocess.CompletedProcess(
+                    args=command,
+                    returncode=1,
+                    stdout=_decoded_stream(timeout_error.stdout),
+                    stderr=f"The wallet step did not complete within {timeout} seconds.",
+                )
+
+        if quiet:
+            return run()
+        with console.status(progress_message):
+            return run()
+
+    created = run_step(
+        [
+            "mpp",
+            "pay",
+            wallet_url,
+            "--method",
+            "POST",
+            "--data",
+            body_json,
+            "--context",
+            _payment_context(body),
+            "--format",
+            "json",
+        ],
+        "Starting the Stripe Link wallet…",
+    )
+    spend_request = _pending_spend_request(created.stdout)
+    if spend_request is None:
+        return created
+    request_id, approval_url = spend_request
+
+    if not quiet:
+        console.print(f"[yellow]Approve the payment in the Link app:[/] {approval_url}")
+        if sys.stdin.isatty() and sys.stdout.isatty() and approval_url.startswith("https://"):
+            with suppress(Exception):
+                webbrowser.open(approval_url)
+    polled = run_step(
+        [
+            "spend-request",
+            "retrieve",
+            request_id,
+            "--interval",
+            str(_LINK_APPROVAL_POLL_INTERVAL_S),
+            "--max-attempts",
+            str(_LINK_APPROVAL_MAX_ATTEMPTS),
+            "--format",
+            "jsonl",
+        ],
+        "Waiting for the approval in the Link app…",
+        timeout=_LINK_APPROVAL_TIMEOUT_S,
+    )
+    if _final_spend_request_status(polled.stdout) != "approved":
+        return polled
+
+    return run_step(
+        [
+            "mpp",
+            "pay",
+            wallet_url,
+            "--spend-request-id",
+            request_id,
+            "--method",
+            "POST",
+            "--data",
+            body_json,
+            "--format",
+            "json",
+        ],
+        "Completing the payment…",
+    )
+
+
+def _decoded_stream(stream: str | bytes | None) -> str:
+    """Return captured subprocess output as text."""
+    if stream is None:
+        return ""
+    if isinstance(stream, bytes):
+        return stream.decode(errors="replace")
+    return stream
+
+
+def _embedded_json_documents(text: str) -> list[Any]:
+    """Extract JSON documents from wallet output that can contain other text."""
+    documents: list[Any] = []
+    decoder = json.JSONDecoder()
+    position = 0
+    while position < len(text):
+        start_candidates = [
+            index for index in (text.find("[", position), text.find("{", position)) if index != -1
+        ]
+        if not start_candidates:
+            break
+        start = min(start_candidates)
+        try:
+            document, end = decoder.raw_decode(text, start)
+        except ValueError:
+            position = start + 1
+            continue
+        documents.append(document)
+        position = end
+    return documents
+
+
+def _spend_request_records(stdout: str) -> list[dict[str, Any]]:
+    """Parse spend-request records from JSON or JSON-lines wallet output."""
+    records: list[dict[str, Any]] = []
+    for candidate in _embedded_json_documents((stdout or "").strip()):
+        items = candidate if isinstance(candidate, list) else [candidate]
+        for item in items:
+            if not isinstance(item, dict):
+                continue
+            record = cast("dict[str, Any]", item)
+            data = record.get("data")
+            if isinstance(data, dict):
+                record = cast("dict[str, Any]", data)
+            records.append(record)
+    return records
+
+
+def _pending_spend_request(stdout: str) -> tuple[str, str] | None:
+    """Find a spend request that waits for approval in the Link app."""
+    for record in _spend_request_records(stdout):
+        request_id = record.get("id")
+        approval_url = record.get("approval_url")
+        if (
+            record.get("status") == "pending_approval"
+            and isinstance(request_id, str)
+            and request_id
+            and isinstance(approval_url, str)
+        ):
+            return request_id, approval_url
+    return None
+
+
+def _final_spend_request_status(stdout: str) -> str | None:
+    """Return the last reported status from the approval poll output."""
+    status: str | None = None
+    for record in _spend_request_records(stdout):
+        value = record.get("status")
+        if isinstance(value, str):
+            status = value
+    return status
+
+
+def _npx_prefix(npx: str, wallet_root: Path) -> list[str]:
+    """Install the wallet client from a fixed registry without lifecycle scripts."""
+    return [
+        npx,
+        "--yes",
+        f"--registry={_NPM_REGISTRY}",
+        "--ignore-scripts",
+        f"--userconfig={wallet_root / 'user.npmrc'}",
+        f"--globalconfig={wallet_root / 'global.npmrc'}",
+        f"--cache={_wallet_npm_cache()}",
+    ]
+
+
+def _wallet_npm_cache() -> Path:
+    """Keep one private npm cache so the pinned wallet client installs once."""
+    cache = Path.home() / ".strix" / "wallet-npm-cache"
+    cache.mkdir(mode=0o700, parents=True, exist_ok=True)
+    return cache
+
+
+def _payment_context(body: dict[str, Any]) -> str:
+    """Describe the purchase for the person who approves it in the Link app."""
+    credits_requested = body.get("credits")
+    return (
+        f"Strix scan credits. The Strix command line interface asks to buy "
+        f"{credits_requested} scan credit(s) for the selected Strix workspace on "
+        "app.strix.ai. Strix spends the credits on managed penetration test scans "
+        "that the user starts."
+    )
+
+
+def _mppx_wallet_configured() -> bool:
+    """Report whether the person already configured the mppx wallet client."""
+    return bool(os.environ.get("MPPX_ACCOUNT") or os.environ.get("MPPX_STRIPE_SECRET_KEY"))
+
+
+def _run_link_cli(
+    npx: str,
+    arguments: list[str],
+    *,
+    capture_output: bool,
+    timeout: float | None = None,
+) -> subprocess.CompletedProcess[str]:
+    """Run one Stripe Link wallet command in an isolated npm environment."""
+    with tempfile.TemporaryDirectory(prefix="strix-wallet-") as wallet_cwd:
+        wallet_root = Path(wallet_cwd)
+        (wallet_root / "user.npmrc").touch(mode=0o600)
+        (wallet_root / "global.npmrc").touch(mode=0o600)
+        return subprocess.run(  # noqa: S603
+            [*_npx_prefix(npx, wallet_root), _LINK_CLI_PACKAGE, *arguments],
+            check=False,
+            capture_output=capture_output,
+            text=True,
+            env=_wallet_environment(),
+            cwd=wallet_root,
+            timeout=timeout,
+        )
+
+
+def _link_wallet_authenticated(npx: str) -> bool:
+    """Report whether a Link wallet is already connected to this machine."""
+    try:
+        result = _run_link_cli(
+            npx,
+            ["auth", "status", "--format", "json"],
+            capture_output=True,
+            timeout=_LINK_LOGIN_TIMEOUT_S,
+        )
+    except (OSError, subprocess.SubprocessError):
+        return False
+    try:
+        payload = json.loads(result.stdout or "null")
+    except (TypeError, ValueError):
+        return False
+    if isinstance(payload, list):
+        payload = payload[0] if payload else None
+    return bool(isinstance(payload, dict) and payload.get("authenticated"))
+
+
+def _prepare_link_wallet(console: Console, npx: str, *, as_json: bool) -> str | None:
+    """Connect a Link wallet when none is present. Return an error message on failure."""
+    if _link_wallet_authenticated(npx):
+        return None
+
+    manual_setup = (
+        "Payment needs a Stripe Link wallet. Run `strix cloud billing topup` in an "
+        "interactive terminal to connect one, or set up the wallet at "
+        "https://link.com/agents. For a browser checkout instead, run "
+        "`strix cloud billing subscribe --plan strix_top_up`."
+    )
+    if as_json or not (sys.stdin.isatty() and sys.stdout.isatty()):
+        return manual_setup
+
+    console.print(
+        "[yellow]No Stripe Link wallet is connected.[/] Strix starts the Link sign-in now. "
+        "Approve the connection in the Link app, then Strix continues the payment. "
+        "The user approves every payment in the Link app."
+    )
+    try:
+        _run_link_cli(
+            npx,
+            [
+                "auth",
+                "login",
+                "--client-name",
+                _LINK_CLI_CLIENT_NAME,
+                "--interval",
+                "3",
+                "--timeout",
+                str(_LINK_LOGIN_TIMEOUT_S),
+            ],
+            capture_output=False,
+            timeout=_LINK_LOGIN_TIMEOUT_S + 30,
+        )
+    except (OSError, subprocess.SubprocessError):
+        return manual_setup
+    if _link_wallet_authenticated(npx):
+        return None
+    return manual_setup
+
+
+def _wallet_environment() -> dict[str, str]:
+    """Pass only platform essentials and explicit wallet variables to npm/mppx."""
+    environment = {
+        name: value
+        for name, value in os.environ.items()
+        if name in _WALLET_ENV_NAMES or name.startswith(("LINK_", "MPPX_"))
+    }
+    for name in ("NO_PROXY", "no_proxy"):
+        entries = [entry.strip() for entry in environment.get(name, "").split(",") if entry.strip()]
+        normalized = {entry.lower().strip("[]") for entry in entries}
+        entries.extend(host for host in _LOOPBACK_NO_PROXY if host not in normalized)
+        environment[name] = ",".join(entries)
+    return environment
+
+
+def _wallet_detail(value: str) -> str:
+    """Bound and redact third-party wallet diagnostics before returning JSON."""
+    redacted = _AUTHORIZATION_SECRET.sub(r"\1[redacted]", sanitize_terminal_text(value))
+    if len(redacted) <= _MAX_WALLET_DETAIL_CHARS:
+        return redacted
+    return redacted[: _MAX_WALLET_DETAIL_CHARS - 1] + "…"
+
+
+def _valid_topup_receipt(value: Any) -> bool:
+    """Require the documented success shape before reporting a paid top-up."""
+    if not isinstance(value, dict):
+        return False
+    fields = cast("dict[str, Any]", value)
+    credits_granted = fields.get("credits_granted")
+    balance = fields.get("balance")
+    return (
+        isinstance(credits_granted, int)
+        and not isinstance(credits_granted, bool)
+        and credits_granted >= 0
+        and isinstance(fields.get("duplicate"), bool)
+        and isinstance(fields.get("reference"), str)
+        and bool(fields["reference"])
+        and isinstance(balance, int)
+        and not isinstance(balance, bool)
+        and balance >= 0
+    )
+
+
+def _confirmed_topup_receipt(
+    responses: tuple[WalletUpstreamResponse, ...],
+) -> dict[str, Any] | None:
+    """Return a receipt only when the trusted bridge observed its successful response."""
+    for response in reversed(responses):
+        if not 200 <= response.status_code < 300:
+            continue
+        try:
+            receipt = json.loads(response.body)
+        except (TypeError, ValueError):
+            continue
+        if _valid_topup_receipt(receipt):
+            return cast("dict[str, Any]", receipt)
+    return None

strix/interface/cloud/http.py

@@ -0,0 +1,408 @@
+"""HTTP client for the managed Strix platform API (app.strix.ai)."""
+
+from __future__ import annotations
+
+import ipaddress
+import math
+import os
+import re
+from typing import TYPE_CHECKING, Any, cast
+from urllib.parse import SplitResult, urlsplit
+
+import requests
+
+from strix.config import load_settings
+from strix.interface.platform_cli import read_record
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+_DEFAULT_TIMEOUT_S = 120
+_SUPABASE_STORAGE_HOST = re.compile(r"^[a-z0-9-]+\.supabase\.co$")
+_STORAGE_PATH_PREFIX = "/storage/v1/"
+_app_url_override: str | None = None
+_token_override_active = False
+_workspace_id_override: str | None = None
+_timeout_s: float = _DEFAULT_TIMEOUT_S
+
+EXIT_OK = 0
+EXIT_ERROR = 1
+EXIT_USAGE = 2
+EXIT_AUTH = 4
+EXIT_PAYMENT = 5
+
+
+TOPUP_COMMAND = "strix cloud billing topup --credits <count>"
+BALANCE_COMMAND = "strix cloud billing credits"
+
+
+class CloudError(Exception):
+    """A failed cloud command. Carries the process exit code.
+
+    `next_step` is a short recovery instruction that the runner prints on its
+    own line after the error, so a person or an agent can act without reading
+    the docs.
+    """
+
+    def __init__(
+        self,
+        message: str,
+        *,
+        exit_code: int = EXIT_ERROR,
+        payload: Any = None,
+        next_step: str | None = None,
+    ) -> None:
+        super().__init__(message)
+        self.exit_code = exit_code
+        self.payload = payload
+        self.next_step = next_step
+
+
+class CloudTransportError(CloudError):
+    """A request may have reached the platform, but no response was received."""
+
+
+def configure(
+    *,
+    base_url: str | None = None,
+    timeout: float | None = None,
+    token_override: bool = False,
+    workspace_id: str | None = None,
+) -> None:
+    """Set the platform URL and the request timeout for this process."""
+    global _app_url_override, _timeout_s, _token_override_active  # noqa: PLW0603
+    global _workspace_id_override  # noqa: PLW0603
+    _app_url_override = base_url.rstrip("/") if base_url else None
+    _token_override_active = token_override
+    explicit_workspace = workspace_id or os.environ.get("STRIX_WORKSPACE_ID")
+    if explicit_workspace:
+        _workspace_id_override = explicit_workspace.strip()
+    elif not token_override and not os.environ.get("STRIX_API_TOKEN"):
+        record = read_record()
+        stored_workspace = record.get("organization_id") if record is not None else None
+        _workspace_id_override = (
+            stored_workspace.strip()
+            if isinstance(stored_workspace, str) and stored_workspace.strip()
+            else None
+        )
+    else:
+        _workspace_id_override = None
+    if timeout is not None:
+        if not math.isfinite(timeout) or timeout <= 0:
+            raise CloudError(
+                "request timeout must be a finite number greater than 0.",
+                exit_code=EXIT_USAGE,
+            )
+        _timeout_s = timeout
+
+
+def app_url() -> str:
+    if _app_url_override:
+        return _app_url_override
+    viewer = load_settings().viewer
+    configured = viewer.app_url.rstrip("/")
+    explicitly_configured = bool(os.environ.get("STRIX_APP_URL")) or "app_url" in getattr(
+        viewer, "model_fields_set", set[str]()
+    )
+    if explicitly_configured or _token_override_active or os.environ.get("STRIX_API_TOKEN"):
+        return configured
+    record = read_record()
+    stored = record.get("app_url") if record is not None else None
+    if isinstance(stored, str) and stored:
+        try:
+            _parse_origin_url(stored, label="stored platform URL")
+        except CloudError:
+            pass
+        else:
+            return stored.rstrip("/")
+    return configured
+
+
+def api_token(override: str | None = None) -> str:
+    token = override or os.environ.get("STRIX_API_TOKEN")
+    if not token:
+        record = read_record()
+        if record is not None:
+            stored = record.get("api_token")
+            if isinstance(stored, str):
+                _validate_stored_token_origin(record)
+                token = stored
+    if not token or not token.strip():
+        raise CloudError(
+            "not signed in. Run `strix cloud login`, or set STRIX_API_TOKEN.",
+            exit_code=EXIT_AUTH,
+        )
+    return token.strip()
+
+
+def _validate_stored_token_origin(record: dict[str, Any]) -> None:
+    """Never send a stored bearer token to an origin other than its issuer."""
+    stored_url = record.get("app_url")
+    if not isinstance(stored_url, str) or not stored_url:
+        raise CloudError(
+            "the stored sign-in is not bound to a trusted platform. Run `strix cloud login` "
+            "again before using it.",
+            exit_code=EXIT_AUTH,
+        )
+    try:
+        stored_origin = _origin(_parse_origin_url(stored_url, label="stored platform URL"))
+        active_origin = _origin(_parse_origin_url(app_url(), label="configured platform URL"))
+    except CloudError as exc:
+        raise CloudError(
+            "the stored sign-in has an invalid platform binding. Run `strix cloud login` again.",
+            exit_code=EXIT_AUTH,
+        ) from exc
+    if stored_origin != active_origin:
+        raise CloudError(
+            "the stored sign-in belongs to a different platform. Refusing to send its token; "
+            "run `strix cloud login` for the configured platform or supply an explicit token.",
+            exit_code=EXIT_AUTH,
+        )
+
+
+def request(
+    method: str,
+    path: str,
+    *,
+    token: str | None = None,
+    query: dict[str, Any] | None = None,
+    body: dict[str, Any] | None = None,
+    stream: bool = False,
+    idempotency_key: str | None = None,
+) -> requests.Response:
+    url = f"{app_url()}/api/v1{path}"
+    headers = {
+        "Authorization": f"Bearer {api_token(token)}",
+    }
+    workspace_id = expected_workspace_id(token_override=token is not None)
+    if workspace_id:
+        headers["X-Strix-Workspace"] = workspace_id
+    if idempotency_key is not None:
+        headers["Idempotency-Key"] = idempotency_key
+    try:
+        response = requests.request(
+            method,
+            url,
+            headers=headers,
+            params={
+                key: ("true" if value else "false") if isinstance(value, bool) else value
+                for key, value in (query or {}).items()
+                if value is not None
+            }
+            or None,
+            json=body,
+            timeout=_timeout_s,
+            stream=stream,
+            allow_redirects=False,
+        )
+    except requests.RequestException as exc:
+        raise CloudTransportError(f"could not reach {app_url()}: {exc}") from exc
+    return response
+
+
+def expected_workspace_id(*, token_override: bool) -> str | None:
+    """Pin every request in this process to the workspace selected at startup."""
+    if _workspace_id_override:
+        return _workspace_id_override
+    if token_override or _token_override_active or os.environ.get("STRIX_API_TOKEN"):
+        return None
+    return None
+
+
+def upload_file(signed_url: str, upload_token: str, path: Path) -> None:
+    """Stream a file to a platform-issued storage URL."""
+    _validate_upload_url(signed_url)
+    response: requests.Response | None = None
+    try:
+        with path.open("rb") as stream:
+            response = requests.put(
+                signed_url,
+                data=stream,
+                headers={
+                    "Authorization": f"Bearer {upload_token}",
+                    "Content-Type": "application/zip",
+                },
+                timeout=_timeout_s,
+                allow_redirects=False,
+            )
+    except (OSError, requests.RequestException) as exc:
+        raise CloudError(f"source upload failed: {exc}") from exc
+    try:
+        if 300 <= response.status_code < 400:
+            raise CloudError("source upload refused an unexpected redirect")
+        if not response.ok:
+            detail = ""
+            try:
+                payload = response.json()
+                if isinstance(payload, dict):
+                    fields = cast("dict[str, Any]", payload)
+                    detail = str(fields.get("message") or fields.get("error") or "")
+            except ValueError:
+                pass
+            raise CloudError(detail or f"source upload failed (HTTP {response.status_code})")
+    finally:
+        response.close()
+
+
+def _validate_upload_url(signed_url: str) -> None:
+    """Allow uploads only to the trusted app origin or managed Supabase storage."""
+    # Supabase signed upload URLs carry their signature in the query string.
+    # Keep every origin/path restriction below, but allow that opaque query on
+    # this one platform-issued URL type.
+    target = _parse_origin_url(
+        signed_url,
+        label="source upload URL",
+        allow_query=True,
+    )
+    if not target.path.startswith(_STORAGE_PATH_PREFIX):
+        raise CloudError("source upload refused a URL outside the storage API")
+
+    configured_app = _parse_origin_url(app_url(), label="configured platform URL")
+    if _origin(target) == _origin(configured_app):
+        return
+    if _is_loopback_host(configured_app.hostname or "") and _is_loopback_host(
+        target.hostname or ""
+    ):
+        return
+
+    hostname = target.hostname or ""
+    if (
+        target.scheme == "https"
+        and target.port in (None, 443)
+        and _SUPABASE_STORAGE_HOST.fullmatch(hostname)
+    ):
+        return
+    raise CloudError(
+        "source upload refused an untrusted storage origin; only the configured platform "
+        "origin and managed Supabase storage are allowed"
+    )
+
+
+def _parse_origin_url(
+    value: str,
+    *,
+    label: str,
+    allow_query: bool = False,
+) -> SplitResult:
+    try:
+        parsed = urlsplit(value)
+        port = parsed.port
+    except (TypeError, ValueError) as exc:
+        raise CloudError(f"{label} is invalid") from exc
+    hostname = parsed.hostname
+    if (
+        parsed.scheme not in {"http", "https"}
+        or not hostname
+        or parsed.username is not None
+        or parsed.password is not None
+        or (parsed.query and not allow_query)
+        or parsed.fragment
+        or "\\" in value
+        or any(character.isspace() for character in value)
+        or "%" in parsed.netloc
+    ):
+        raise CloudError(f"{label} is invalid")
+    try:
+        hostname.encode("ascii")
+    except UnicodeEncodeError as exc:
+        raise CloudError(f"{label} contains a non-ASCII hostname") from exc
+    if port is not None and not 1 <= port <= 65535:
+        raise CloudError(f"{label} is invalid")
+    return parsed
+
+
+def _origin(parsed: SplitResult) -> tuple[str, str, int]:
+    default_port = 443 if parsed.scheme == "https" else 80
+    return parsed.scheme, (parsed.hostname or "").lower(), parsed.port or default_port
+
+
+def _is_loopback_host(hostname: str) -> bool:
+    normalized = hostname.lower().rstrip(".")
+    if normalized == "localhost" or normalized.endswith(".localhost"):
+        return True
+    try:
+        return ipaddress.ip_address(normalized).is_loopback
+    except ValueError:
+        return False
+
+
+def parsed(response: requests.Response) -> Any:
+    content_type = response.headers.get("content-type", "")
+    if "application/json" in content_type:
+        try:
+            return response.json()
+        except ValueError:
+            return response.text
+    return response.text
+
+
+def check(response: requests.Response) -> Any:
+    data = parsed(response)
+    if 200 <= response.status_code < 300:
+        content_type = response.headers.get("content-type", "").lower()
+        if "application/json" not in content_type:
+            raise CloudError(
+                "the server returned a non-JSON response. Check STRIX_APP_URL and preview "
+                "access, then retry."
+            )
+        try:
+            return response.json()
+        except ValueError as exc:
+            raise CloudError(
+                "the server returned malformed JSON. Check STRIX_APP_URL and preview "
+                "access, then retry."
+            ) from exc
+    detail = ""
+    error_code = ""
+    if isinstance(data, dict):
+        raw = cast("dict[str, Any]", data)
+        detail = str(raw.get("detail") or raw.get("error") or "")
+        error_code = str(raw.get("code") or raw.get("error_code") or "")
+        nested_error = raw.get("error")
+        if isinstance(nested_error, dict):
+            nested = cast("dict[str, Any]", nested_error)
+            error_code = error_code or str(nested.get("code") or "")
+            detail = str(nested.get("message") or detail)
+    message = detail or f"HTTP {response.status_code}"
+    if error_code == "scan_credit_limit_reached" or response.status_code == 402:
+        raise payment_required_error(data, detail=detail)
+    if response.status_code in (401, 403):
+        raise CloudError(message, exit_code=EXIT_AUTH, payload=data)
+    raise CloudError(message, exit_code=EXIT_ERROR, payload=data)
+
+
+def topup_url() -> str:
+    return f"{app_url()}/settings/billing"
+
+
+def topup_next_step(url: str | None = None) -> str:
+    return (
+        f"Buy credits with `{TOPUP_COMMAND}` or at {url or topup_url()}. "
+        f"Run `{BALANCE_COMMAND}` to see the balance. Then retry this command."
+    )
+
+
+def payment_required_error(data: Any, *, detail: str = "") -> CloudError:
+    """Build the error for an exhausted credit balance.
+
+    The platform sends the recovery instruction in `hint` and repeats it inside
+    `detail`. The CLI shows the instruction once, on its own line, and adds its
+    own instruction when the platform sends none.
+    """
+    server_hint = ""
+    server_url: str | None = None
+    if isinstance(data, dict):
+        raw = cast("dict[str, Any]", data)
+        server_hint = str(raw.get("hint") or "").strip()
+        raw_url = raw.get("topup_url")
+        if isinstance(raw_url, str) and raw_url.startswith("https://"):
+            server_url = raw_url
+    message = detail.strip()
+    if server_hint and message.endswith(server_hint):
+        message = message[: -len(server_hint)].strip()
+    if not message:
+        message = "Not enough credits to run this command."
+    next_step = server_hint or topup_next_step(server_url)
+    return CloudError(message, exit_code=EXIT_PAYMENT, payload=data, next_step=next_step)

strix/interface/cloud/payment_proxy.py

@@ -0,0 +1,286 @@
+"""Loopback bridge for wallet clients that only accept secrets in argv.
+
+The ``mppx`` CLI accepts custom HTTP headers through ``-H`` only.  Passing a
+Strix API token that way exposes it to process-listing tools.  This module keeps
+the token in the Strix process and injects it while forwarding the wallet's few
+requests (challenge probes and the paid retry) to the fixed billing endpoint.
+"""
+
+from __future__ import annotations
+
+import secrets
+import threading
+from contextlib import contextmanager, suppress
+from dataclasses import dataclass, field
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+from typing import TYPE_CHECKING, Any
+
+import requests
+
+
+if TYPE_CHECKING:
+    from collections.abc import Callable, Generator
+
+
+_DEFAULT_REQUEST_TIMEOUT_S = 120.0
+_MAX_REQUEST_BODY_BYTES = 64 * 1024
+_MAX_UPSTREAM_RESPONSE_BYTES = 1024 * 1024
+_MAX_WALLET_REQUESTS = 3
+_HOP_BY_HOP_HEADERS = frozenset(
+    {
+        "connection",
+        "keep-alive",
+        "proxy-authenticate",
+        "proxy-authorization",
+        "proxy-connection",
+        "te",
+        "trailer",
+        "transfer-encoding",
+        "upgrade",
+    }
+)
+
+
+@dataclass
+class _BridgeState:
+    upstream_url: str
+    authorization: str
+    workspace_id: str | None
+    expected_body: bytes
+    path: str
+    timeout: float
+    response_observer: Callable[[WalletUpstreamResponse], None] | None = None
+    request_count: int = 0
+    lock: threading.Lock = field(default_factory=threading.Lock)
+
+    def claim_request(self) -> bool:
+        """Allow only the challenge probes and the one paid retry."""
+        with self.lock:
+            if self.request_count >= _MAX_WALLET_REQUESTS:
+                return False
+            self.request_count += 1
+            return True
+
+
+class _ResponseTooLargeError(Exception):
+    """The fixed billing endpoint returned more data than a wallet needs."""
+
+
+@dataclass(frozen=True)
+class WalletUpstreamResponse:
+    """A bounded upstream response observed by the trusted loopback bridge."""
+
+    status_code: int
+    body: bytes
+
+
+def _bounded_response_body(response: requests.Response) -> bytes:
+    content_length = response.headers.get("Content-Length")
+    if content_length:
+        try:
+            if int(content_length) > _MAX_UPSTREAM_RESPONSE_BYTES:
+                raise _ResponseTooLargeError
+        except ValueError:
+            pass
+
+    chunks: list[bytes] = []
+    total = 0
+    for chunk in response.iter_content(chunk_size=64 * 1024):
+        if not chunk:
+            continue
+        total += len(chunk)
+        if total > _MAX_UPSTREAM_RESPONSE_BYTES:
+            raise _ResponseTooLargeError
+        chunks.append(chunk)
+    return b"".join(chunks)
+
+
+def _connection_header_names(handler: BaseHTTPRequestHandler) -> set[str]:
+    value = handler.headers.get("Connection", "")
+    return {item.strip().lower() for item in value.split(",") if item.strip()}
+
+
+def _forward_request_headers(handler: BaseHTTPRequestHandler) -> dict[str, str]:
+    blocked = {
+        *_HOP_BY_HOP_HEADERS,
+        *_connection_header_names(handler),
+        "content-length",
+        "forwarded",
+        "host",
+        "true-client-ip",
+        "x-forwarded-for",
+        "x-forwarded-host",
+        "x-forwarded-proto",
+        "x-real-ip",
+        "x-strix-authorization",
+        "x-strix-workspace",
+        "x-vercel-forwarded-for",
+    }
+    return {name: value for name, value in handler.headers.items() if name.lower() not in blocked}
+
+
+def _send_json_error(handler: BaseHTTPRequestHandler, status: int, message: str) -> None:
+    body = f'{{"error": "{message}"}}'.encode()
+    handler.close_connection = True
+    handler.send_response(status)
+    handler.send_header("Content-Type", "application/json")
+    handler.send_header("Content-Length", str(len(body)))
+    handler.send_header("Cache-Control", "no-store")
+    handler.send_header("Connection", "close")
+    handler.end_headers()
+    with suppress(BrokenPipeError, ConnectionResetError):
+        handler.wfile.write(body)
+
+
+def _make_handler(state: _BridgeState) -> type[BaseHTTPRequestHandler]:
+    class WalletBridgeHandler(BaseHTTPRequestHandler):
+        protocol_version = "HTTP/1.1"
+
+        def log_message(self, format: str, *args: Any) -> None:  # noqa: A002
+            """Do not write wallet request metadata to stderr."""
+            del format, args
+
+        def do_POST(self) -> None:  # noqa: PLR0911, PLR0912
+            if self.path != state.path:
+                _send_json_error(self, 404, "Not found")
+                return
+            if self.headers.get("Transfer-Encoding"):
+                _send_json_error(self, 400, "Chunked request bodies are not supported")
+                return
+            try:
+                content_length = int(self.headers.get("Content-Length", ""))
+            except ValueError:
+                _send_json_error(self, 411, "A valid Content-Length is required")
+                return
+            if content_length < 0 or content_length > _MAX_REQUEST_BODY_BYTES:
+                _send_json_error(self, 413, "Request body is too large")
+                return
+            body = self.rfile.read(content_length)
+            if body != state.expected_body:
+                _send_json_error(self, 403, "Request body did not match the approved top-up")
+                return
+            if not state.claim_request():
+                _send_json_error(self, 429, "Wallet request limit reached")
+                return
+
+            headers = _forward_request_headers(self)
+            headers["X-Strix-Authorization"] = state.authorization
+            if state.workspace_id:
+                headers["X-Strix-Workspace"] = state.workspace_id
+            try:
+                response = requests.request(
+                    "POST",
+                    state.upstream_url,
+                    headers=headers,
+                    data=body,
+                    timeout=state.timeout,
+                    allow_redirects=False,
+                    stream=True,
+                )
+                try:
+                    response_body = _bounded_response_body(response)
+                    response_status = response.status_code
+                    response_headers = dict(response.headers)
+                finally:
+                    response.close()
+            except _ResponseTooLargeError:
+                _send_json_error(self, 502, "Strix billing response was too large")
+                return
+            except requests.RequestException:
+                _send_json_error(self, 502, "Could not reach the Strix billing endpoint")
+                return
+
+            if state.response_observer is not None:
+                with suppress(Exception):
+                    state.response_observer(
+                        WalletUpstreamResponse(status_code=response_status, body=response_body)
+                    )
+
+            if 300 <= response_status < 400:
+                _send_json_error(self, 502, "Strix billing refused an unexpected redirect")
+                return
+
+            self.send_response(response_status)
+            response_connection_headers = {
+                item.strip().lower()
+                for item in response_headers.get("Connection", "").split(",")
+                if item.strip()
+            }
+            blocked_response_headers = {
+                *_HOP_BY_HOP_HEADERS,
+                *response_connection_headers,
+                "cache-control",
+                "content-encoding",
+                "content-length",
+                "location",
+            }
+            for name, value in response_headers.items():
+                if (
+                    name.lower() not in blocked_response_headers
+                    and "\r" not in value
+                    and "\n" not in value
+                ):
+                    self.send_header(name, value)
+            self.send_header("Content-Length", str(len(response_body)))
+            self.send_header("Cache-Control", "no-store")
+            self.end_headers()
+            with suppress(BrokenPipeError, ConnectionResetError):
+                self.wfile.write(response_body)
+
+        def do_GET(self) -> None:
+            _send_json_error(self, 405, "Method not allowed")
+
+        def do_PUT(self) -> None:
+            _send_json_error(self, 405, "Method not allowed")
+
+        def do_PATCH(self) -> None:
+            _send_json_error(self, 405, "Method not allowed")
+
+        def do_DELETE(self) -> None:
+            _send_json_error(self, 405, "Method not allowed")
+
+    return WalletBridgeHandler
+
+
+@contextmanager
+def wallet_payment_bridge(
+    *,
+    upstream_url: str,
+    api_token: str,
+    workspace_id: str | None = None,
+    expected_body: bytes,
+    timeout: float | None = None,
+    response_observer: Callable[[WalletUpstreamResponse], None] | None = None,
+) -> Generator[str]:
+    """Yield a one-run loopback URL that injects the Strix API token upstream.
+
+    The random path prevents accidental cross-process requests and limits local
+    denial-of-service races.  It is not an authentication boundary against a
+    same-user process that can inspect another process's argv.
+    """
+    capability = secrets.token_urlsafe(32)
+    path = f"/topup/{capability}"
+    state = _BridgeState(
+        upstream_url=upstream_url,
+        authorization=f"Bearer {api_token}",
+        workspace_id=workspace_id,
+        expected_body=expected_body,
+        path=path,
+        timeout=timeout or _DEFAULT_REQUEST_TIMEOUT_S,
+        response_observer=response_observer,
+    )
+    server = ThreadingHTTPServer(("127.0.0.1", 0), _make_handler(state))
+    server.daemon_threads = True
+    thread = threading.Thread(
+        target=server.serve_forever,
+        kwargs={"poll_interval": 0.05},
+        name="strix-wallet-bridge",
+        daemon=True,
+    )
+    thread.start()
+    try:
+        yield f"http://127.0.0.1:{server.server_port}{path}"
+    finally:
+        server.shutdown()
+        server.server_close()
+        thread.join(timeout=1)

strix/interface/cloud/session.py

@@ -0,0 +1,167 @@
+"""Inspect and safely narrow a managed Strix CLI session."""
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING, Any, cast
+
+from rich.console import Console
+from rich.markup import escape
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+from strix.interface.cloud.arguments import CloudArgumentParser
+from strix.interface.cloud.render import emit, json_mode
+from strix.interface.platform_cli import read_record, save_record
+from strix.interface.terminal_text import sanitize_terminal_text
+
+
+if TYPE_CHECKING:
+    import argparse
+
+
+def run_session(argv: list[str]) -> int:
+    console = Console()
+    normalized = ["show", *argv] if not argv or argv[0].startswith("-") else list(argv)
+    if normalized[0] == "help":
+        normalized = ["--help", *normalized[1:]]
+    if normalized[0] in {"-h", "--help"}:
+        _print_help(console)
+        return 0
+    verb = normalized.pop(0)
+    if verb == "scopes" and normalized and normalized[0] == "set":
+        normalized.pop(0)
+        return _run_scopes_set(console, normalized)
+    if verb not in {"show", "scopes"}:
+        console.print(f"[red]Unknown session command:[/] {escape(sanitize_terminal_text(verb))}")
+        _print_help(console)
+        return http.EXIT_USAGE
+    return _run_show(console, normalized, scopes_only=verb == "scopes")
+
+
+def _common(parser: argparse.ArgumentParser) -> None:
+    parser.add_argument("--json", action="store_true", help="Print the raw JSON response.")
+    parser.add_argument("--show-scopes", action="store_true", help="Print every granted scope.")
+    parser.add_argument("--token", default=None, help="API token override.")
+    parser.add_argument("--workspace-id", default=None, metavar="ORG_ID")
+    parser.add_argument("--app-url", default=None, metavar="URL")
+    parser.add_argument("--timeout", default=None, type=float, metavar="SECONDS")
+
+
+def _configure(args: argparse.Namespace) -> bool:
+    external = args.token is not None or bool(os.environ.get("STRIX_API_TOKEN", "").strip())
+    http.configure(
+        base_url=args.app_url,
+        timeout=args.timeout,
+        token_override=bool(args.token),
+        workspace_id=args.workspace_id,
+    )
+    return external
+
+
+def _run_show(console: Console, argv: list[str], *, scopes_only: bool) -> int:
+    parser = CloudArgumentParser(prog=f"strix cloud session {'scopes' if scopes_only else 'show'}")
+    _common(parser)
+    as_json = json_mode(flag="--json" in argv)
+    try:
+        args = parser.parse_args(argv)
+        _configure(args)
+        payload = http.check(http.request("GET", "/cli/session", token=args.token))
+    except SystemExit as exc:
+        return int(exc.code or 0)
+    except http.CloudError as exc:
+        return _error(console, exc, as_json=as_json)
+    if not isinstance(payload, dict):
+        return _error(console, http.CloudError("invalid CLI session response"), as_json=as_json)
+    record = cast("dict[str, Any]", payload)
+    if as_json:
+        emit(console, record, as_json=True)
+        return http.EXIT_OK
+    scopes = _string_list(record.get("scopes"))
+    ceiling = _string_list(record.get("scope_ceiling"))
+    profile = str(record.get("scope_profile") or "custom").title()
+    if not scopes_only:
+        device_name = escape(str(record.get("device_name") or "this device"))
+        console.print(f"[green]Active CLI session[/] on [bold]{device_name}[/]")
+        console.print(f"  Workspace: {escape(str(record.get('organization_id') or 'unknown'))}")
+    console.print(f"  Access: {profile} · {len(scopes)} scopes granted · {len(ceiling)} maximum")
+    if args.show_scopes or scopes_only:
+        console.print(f"  Granted: [dim]{escape(' '.join(scopes))}[/]")
+        console.print(f"  Ceiling: [dim]{escape(' '.join(ceiling))}[/]")
+    return http.EXIT_OK
+
+
+def _run_scopes_set(console: Console, argv: list[str]) -> int:
+    parser = CloudArgumentParser(
+        prog="strix cloud session scopes set",
+        description="Change scopes within the access approved at browser sign-in.",
+    )
+    mode = parser.add_mutually_exclusive_group(required=True)
+    mode.add_argument("profile", nargs="?", choices=("minimal", "recommended", "full"))
+    mode.add_argument("--scopes", nargs="+", metavar="SCOPE")
+    _common(parser)
+    as_json = json_mode(flag="--json" in argv)
+    try:
+        args = parser.parse_args(argv)
+        external = _configure(args)
+        body = (
+            {"scope_profile": args.profile}
+            if args.profile
+            else {"scope_profile": "custom", "scopes": args.scopes}
+        )
+        payload = http.check(http.request("PATCH", "/cli/session", token=args.token, body=body))
+    except SystemExit as exc:
+        return int(exc.code or 0)
+    except http.CloudError as exc:
+        return _error(console, exc, as_json=as_json)
+    if not isinstance(payload, dict):
+        return _error(console, http.CloudError("invalid CLI session response"), as_json=as_json)
+    result = cast("dict[str, Any]", payload)
+    if not external:
+        stored = read_record()
+        if stored is not None:
+            stored.update(
+                {
+                    key: result[key]
+                    for key in ("scopes", "requested_scopes", "scope_ceiling", "scope_profile")
+                    if key in result
+                }
+            )
+            save_record(stored)
+    if as_json:
+        emit(console, result, as_json=True)
+    else:
+        scopes = _string_list(result.get("scopes"))
+        profile = str(result.get("scope_profile") or "custom").title()
+        console.print(f"[green]✓ CLI access updated.[/] {profile} · {len(scopes)} scopes granted")
+        if args.show_scopes:
+            console.print(f"  Scopes: [dim]{escape(' '.join(scopes))}[/]")
+    return http.EXIT_OK
+
+
+def _string_list(value: Any) -> list[str]:
+    if not isinstance(value, list):
+        return []
+    items = cast("list[Any]", cast("Any", value))
+    return [str(item) for item in items]
+
+
+def _error(console: Console, error: http.CloudError, *, as_json: bool) -> int:
+    if as_json:
+        raw_payload: Any = error.payload
+        error_payload = cast("dict[str, Any]", raw_payload)
+        payload = dict(error_payload) if isinstance(raw_payload, dict) else {}
+        payload["error"] = str(error)
+        if payload.get("detail") == payload.get("error"):
+            payload.pop("detail", None)
+        emit(console, payload, as_json=True)
+    else:
+        console.print(f"[red]Error:[/] {escape(sanitize_terminal_text(error))}")
+    return error.exit_code
+
+
+def _print_help(console: Console) -> None:
+    console.print("[bold]strix cloud session[/] commands:")
+    console.print("  show                         Show the remote CLI session (default).")
+    console.print("  scopes                       Show granted scopes and consent ceiling.")
+    console.print("  scopes set PROFILE           Use minimal, recommended, or full.")
+    console.print("  scopes set --scopes SCOPE…   Use a custom set within the ceiling.")

strix/interface/cloud/source_scan.py

@@ -0,0 +1,403 @@
+"""Local-source approval, upload, and scan-launch lifecycle."""
+
+from __future__ import annotations
+
+import re
+import sys
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Any, cast
+from urllib.parse import quote
+
+from rich.markup import escape
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+from strix.interface.cloud.render import emit
+from strix.interface.cloud.source_upload import prepare_source, remove_bundle
+from strix.interface.terminal_text import sanitize_terminal_text
+
+
+if TYPE_CHECKING:
+    import argparse
+    from typing import NoReturn
+
+    from rich.console import Console
+
+    from strix.interface.cloud.source_upload import SourceBundle
+
+
+_SHA256 = re.compile(r"^[0-9a-fA-F]{64}$")
+
+
+@dataclass
+class LocalSourceScan:
+    """Own one local bundle and its staged upload through a scan launch."""
+
+    bundle: SourceBundle | None = None
+    upload_id: str | None = None
+    idempotency_key: str | None = None
+    _launch_started: bool = False
+
+    def prepare_and_attach(
+        self,
+        console: Console,
+        args: argparse.Namespace,
+        body: dict[str, Any],
+        *,
+        as_json: bool,
+        token: str | None,
+    ) -> bool:
+        """Prepare source, emit a dry run, or upload and attach it to ``body``.
+
+        Returns ``True`` when a dry run was emitted and request execution should stop.
+        """
+        self.bundle = prepare_scan_source(console, args, as_json=as_json)
+        if self.bundle is None:
+            return False
+        if getattr(args, "dry_run", False):
+            emit(
+                console,
+                {"source": self.bundle.summary(show_files=getattr(args, "show_files", False))},
+                as_json=as_json,
+                view="source_manifest",
+            )
+            return True
+        self.upload_id = _upload_scan_source(self.bundle, token=token)
+        existing = body.get("upload_ids")
+        body["upload_ids"] = [
+            *(existing if isinstance(existing, list) else []),
+            self.upload_id,
+        ]
+        return False
+
+    def mark_launch_started(self) -> None:
+        """Record that the scan-creation request may have reached the platform."""
+        self._launch_started = self.upload_id is not None
+
+    def handle_request_failure(self, error: BaseException, *, token: str | None) -> None:
+        """Clean or retain a staged upload according to request ambiguity."""
+        if self.upload_id is None:
+            return
+        if self._launch_started:
+            if isinstance(error, KeyboardInterrupt):
+                raise _interrupted_source_upload_error(
+                    self.upload_id, self.idempotency_key
+                ) from None
+            if isinstance(error, Exception):
+                raise _retained_source_upload_error(
+                    self.upload_id, error, self.idempotency_key
+                ) from error
+            return
+        try:
+            _delete_upload(self.upload_id, token=token)
+        except (http.CloudError, KeyboardInterrupt) as cleanup_error:
+            if isinstance(error, Exception):
+                raise _source_cleanup_error(self.upload_id, error, cleanup_error) from error
+            interrupted = http.CloudError("source upload interrupted.", exit_code=130)
+            raise _source_cleanup_error(self.upload_id, interrupted, cleanup_error) from None
+
+    def handle_response_failure(
+        self,
+        error: BaseException,
+        *,
+        definitive: bool,
+        token: str | None,
+    ) -> None:
+        """Clean a rejected upload or retain one whose scan result is ambiguous."""
+        if self.upload_id is None:
+            return
+        if definitive:
+            try:
+                _delete_upload(self.upload_id, token=token)
+            except (http.CloudError, KeyboardInterrupt) as cleanup_error:
+                if isinstance(error, Exception):
+                    raise _source_cleanup_error(self.upload_id, error, cleanup_error) from error
+                interrupted = http.CloudError("source upload interrupted.", exit_code=130)
+                raise _source_cleanup_error(self.upload_id, interrupted, cleanup_error) from None
+            return
+        if isinstance(error, Exception):
+            raise _retained_source_upload_error(
+                self.upload_id, error, self.idempotency_key
+            ) from error
+
+    def wrap_result(self, result: Any, args: argparse.Namespace) -> Any:
+        """Attach the approved source manifest to a successful scan response."""
+        if self.bundle is None:
+            return result
+        return {
+            "source": self.bundle.summary(show_files=getattr(args, "show_files", False)),
+            "upload_id": self.upload_id,
+            "scan": result,
+        }
+
+    def close(self) -> None:
+        """Remove the private temporary bundle, if one was built."""
+        if self.bundle is not None:
+            remove_bundle(self.bundle)
+
+
+def prepare_scan_source(
+    console: Console, args: argparse.Namespace, *, as_json: bool
+) -> SourceBundle | None:
+    """Build and approve the exact local-source snapshot for one invocation."""
+    source = getattr(args, "source", None)
+    source_flags = (
+        "dry_run",
+        "show_files",
+        "include_hidden",
+        "include_sensitive",
+        "include_archives",
+        "approve_sha256",
+    )
+    if source is None:
+        if any(getattr(args, name, False) for name in source_flags) or getattr(args, "exclude", []):
+            raise http.CloudError("source upload options require --source DIRECTORY.")
+        return None
+    bundle = prepare_source(
+        source,
+        include_hidden=bool(getattr(args, "include_hidden", False)),
+        include_sensitive=bool(getattr(args, "include_sensitive", False)),
+        include_archives=bool(getattr(args, "include_archives", False)),
+        exclude=cast("list[str]", getattr(args, "exclude", [])),
+    )
+    keep_bundle = False
+    try:
+        approved_digest = _validate_source_digest_approval(args, bundle)
+        if getattr(args, "dry_run", False):
+            keep_bundle = True
+            return bundle
+        if getattr(args, "yes", False) or approved_digest is not None:
+            keep_bundle = True
+            return bundle
+        if as_json or not (sys.stdin.isatty() and sys.stdout.isatty()):
+            _source_approval_error(
+                "source upload requires explicit approval in non-interactive mode. "
+                "Review with --dry-run --show-files, then rerun with "
+                "--approve-sha256 <reviewed hash>; use --yes only for a deliberate "
+                "one-shot approval of the snapshot built by that invocation."
+            )
+        console.print(
+            "[bold]Local source upload[/]\n"
+            f"  {len(bundle.manifest.files):,} file(s), "
+            f"{_format_bytes(bundle.manifest.total_bytes)} "
+            f"({_format_bytes(bundle.archive_bytes)} compressed)\n"
+            f"  {sum(bundle.manifest.excluded.values()):,} path(s) excluded\n"
+            "  Only the selected files will be sent to Strix Cloud."
+        )
+        if getattr(args, "show_files", False):
+            console.print(f"\n[bold]Selected files ({len(bundle.manifest.files):,})[/]")
+            for selected in bundle.manifest.files:
+                console.print(
+                    f"  {escape(sanitize_terminal_text(selected.archive_name))}", soft_wrap=True
+                )
+        answer = (
+            console.input("Upload this source and start the scan? [y/N]: ", markup=False)
+            .strip()
+            .lower()
+        )
+        if answer not in ("y", "yes"):
+            _source_approval_error("source upload cancelled.")
+        keep_bundle = True
+        return bundle
+    finally:
+        if not keep_bundle:
+            remove_bundle(bundle)
+
+
+def _validate_source_digest_approval(args: argparse.Namespace, bundle: SourceBundle) -> str | None:
+    approved_digest = getattr(args, "approve_sha256", None)
+    if approved_digest is None:
+        return None
+    if not isinstance(approved_digest, str) or not _SHA256.fullmatch(approved_digest):
+        _source_approval_error("--approve-sha256 must be exactly 64 hexadecimal characters.")
+    if bundle.archive_sha256 != approved_digest.lower():
+        _source_approval_error(
+            "source archive SHA-256 does not match --approve-sha256; review a fresh "
+            "--dry-run before uploading."
+        )
+    return approved_digest
+
+
+def _source_approval_error(message: str) -> NoReturn:
+    raise http.CloudError(message)
+
+
+def _upload_scan_source(bundle: SourceBundle, *, token: str | None) -> str:
+    file_name = f"strix-source-{bundle.archive_sha256[:12]}.zip"
+    requested = http.check(
+        http.request(
+            "POST",
+            "/uploads/request",
+            token=token,
+            body={
+                "file_name": file_name,
+                "file_size": bundle.archive_bytes,
+                "category": "repository",
+            },
+        )
+    )
+    if not isinstance(requested, dict):
+        raise http.CloudError("the platform returned an invalid source upload response.")
+    fields = cast("dict[str, Any]", requested)
+    upload_id = fields.get("upload_id")
+    signed_url = fields.get("signed_url")
+    upload_token = fields.get("token")
+    if not all(isinstance(value, str) and value for value in (upload_id, signed_url, upload_token)):
+        error = http.CloudError("the platform did not return complete source upload credentials.")
+        if isinstance(upload_id, str) and upload_id:
+            try:
+                _delete_upload(upload_id, token=token)
+            except (http.CloudError, KeyboardInterrupt) as cleanup_error:
+                raise _source_cleanup_error(upload_id, error, cleanup_error) from error
+        raise error
+    try:
+        http.upload_file(cast("str", signed_url), cast("str", upload_token), bundle.archive_path)
+        completed = http.check(
+            http.request(
+                "POST",
+                "/uploads/complete",
+                token=token,
+                body={"upload_id": upload_id},
+            )
+        )
+        _validate_completed_upload(completed, expected_id=cast("str", upload_id))
+    except BaseException as error:
+        try:
+            _delete_upload(cast("str", upload_id), token=token)
+        except (http.CloudError, KeyboardInterrupt) as cleanup_error:
+            if isinstance(error, Exception):
+                raise _source_cleanup_error(cast("str", upload_id), error, cleanup_error) from error
+            interrupted = http.CloudError("source upload interrupted.", exit_code=130)
+            raise _source_cleanup_error(
+                cast("str", upload_id), interrupted, cleanup_error
+            ) from None
+        raise
+    return cast("str", upload_id)
+
+
+def _validate_completed_upload(completed: Any, *, expected_id: str) -> None:
+    fields = cast("dict[str, Any]", completed) if isinstance(completed, dict) else {}
+    if fields.get("id") != expected_id:
+        raise http.CloudError("the platform returned an invalid source upload completion response.")
+
+
+def _delete_upload(upload_id: str, *, token: str | None) -> None:
+    response = http.request("DELETE", f"/uploads/{quote(upload_id, safe='')}", token=token)
+    if response.status_code == 404 or 200 <= response.status_code < 300:
+        return
+    http.check(response)
+
+
+def _source_cleanup_note(upload_id: str, cleanup_error: BaseException) -> str:
+    return (
+        f"Cleanup of source upload {upload_id} could not be confirmed: {cleanup_error}. "
+        f"Retry with `strix cloud uploads delete {upload_id}`."
+    )
+
+
+def _source_cleanup_error(
+    upload_id: str, error: Exception, cleanup_error: BaseException
+) -> http.CloudError:
+    """Report a staged source object whenever automatic deletion is uncertain."""
+    message = f"{error} {_source_cleanup_note(upload_id, cleanup_error)}"
+    payload: dict[str, Any] = {}
+    exit_code = http.EXIT_ERROR
+    if isinstance(error, http.CloudError):
+        exit_code = error.exit_code
+        raw_payload: Any = error.payload
+        if isinstance(raw_payload, dict):
+            payload.update(cast("dict[str, Any]", raw_payload))
+        elif raw_payload is not None:
+            payload["detail"] = raw_payload
+    payload.update(
+        {
+            "error": message,
+            "upload_id": upload_id,
+            "upload_retained": True,
+            "cleanup_unknown": True,
+        }
+    )
+    return http.CloudError(message, exit_code=exit_code, payload=payload)
+
+
+def _interrupted_source_upload_error(
+    upload_id: str, idempotency_key: str | None = None
+) -> http.CloudError:
+    retry_note = _idempotency_retry_note(idempotency_key)
+    message = (
+        "Interrupted while starting the scan. The launch outcome is unknown, so source upload "
+        f"{upload_id} was retained. Check `strix cloud scans list` before retrying; if no scan "
+        f"was created, run `strix cloud uploads delete {upload_id}`.{retry_note}"
+    )
+    payload: dict[str, Any] = {
+        "error": message,
+        "interrupted": True,
+        "upload_id": upload_id,
+        "upload_retained": True,
+        "launch_outcome_unknown": True,
+    }
+    _attach_idempotency_recovery(payload, idempotency_key)
+    return http.CloudError(message, exit_code=130, payload=payload)
+
+
+def _retained_source_upload_error(
+    upload_id: str,
+    error: Exception,
+    idempotency_key: str | None = None,
+) -> http.CloudError:
+    """Preserve source when the platform may already have accepted its scan."""
+    retry_note = _idempotency_retry_note(idempotency_key)
+    message = (
+        f"{error} The scan launch outcome is unknown, so source upload {upload_id} was retained. "
+        "Check `strix cloud scans list` before retrying; if no scan was created, clean it up "
+        f"with `strix cloud uploads delete {upload_id}`. Linked uploads cannot be deleted."
+        f"{retry_note}"
+    )
+    payload: dict[str, Any] = {}
+    exit_code = http.EXIT_ERROR
+    if isinstance(error, http.CloudError):
+        exit_code = error.exit_code
+        raw_payload: Any = error.payload
+        error_payload = cast("dict[str, Any]", raw_payload)
+        if isinstance(raw_payload, dict):
+            payload.update(error_payload)
+        elif raw_payload is not None:
+            payload["detail"] = raw_payload
+    payload.update(
+        {
+            "error": message,
+            "upload_id": upload_id,
+            "upload_retained": True,
+            "launch_outcome_unknown": True,
+        }
+    )
+    _attach_idempotency_recovery(payload, idempotency_key)
+    return http.CloudError(message, exit_code=exit_code, payload=payload)
+
+
+def _idempotency_retry_note(idempotency_key: str | None) -> str:
+    if not idempotency_key:
+        return ""
+    return (
+        " An exact retry is safe only with the same request body and "
+        f"`--idempotency-key {idempotency_key}`."
+    )
+
+
+def _attach_idempotency_recovery(payload: dict[str, Any], idempotency_key: str | None) -> None:
+    if not idempotency_key:
+        return
+    payload.update(
+        {
+            "idempotency_key": idempotency_key,
+            "retry_safe": True,
+            "retry_same_request": True,
+        }
+    )
+
+
+def _format_bytes(value: int) -> str:
+    if value < 1024:
+        return f"{value} B"
+    if value < 1024 * 1024:
+        return f"{value / 1024:.1f} KB"
+    return f"{value / (1024 * 1024):.1f} MB"

strix/interface/cloud/source_upload.py

@@ -0,0 +1,734 @@
+"""Privacy-conscious local source packaging for managed scans."""
+
+from __future__ import annotations
+
+import fnmatch
+import hashlib
+import os
+import shutil
+import stat
+import subprocess  # nosec B404
+import tempfile
+import zipfile
+from collections import Counter
+from dataclasses import dataclass
+from pathlib import Path, PurePosixPath
+from typing import TYPE_CHECKING
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from typing import Protocol
+
+    class _ScandirIterator(Iterator[os.DirEntry[str]], Protocol):
+        def close(self) -> None: ...
+
+
+MAX_FILES = 20_000
+MAX_FILE_BYTES = 25 * 1024 * 1024
+MAX_TOTAL_BYTES = 250 * 1024 * 1024
+MAX_ARCHIVE_BYTES = 50 * 1024 * 1024
+MAX_CANDIDATE_PATHS = 200_000
+MAX_IGNORE_BYTES = 64 * 1024
+MAX_IGNORE_PATTERNS = 1_000
+MAX_IGNORE_PATTERN_CHARS = 1_024
+
+_ALWAYS_EXCLUDED_DIRS = frozenset(
+    {
+        ".git",
+        ".hg",
+        ".svn",
+        "node_modules",
+        "vendor",
+        "venv",
+        ".venv",
+        "env",
+        "__pycache__",
+        ".tox",
+        ".pytest_cache",
+        ".mypy_cache",
+        ".ruff_cache",
+        "dist",
+        "build",
+        "coverage",
+        "target",
+        ".next",
+        ".nuxt",
+        ".gradle",
+    }
+)
+_SENSITIVE_NAMES = frozenset(
+    {
+        "id_rsa",
+        "id_dsa",
+        "id_ecdsa",
+        "id_ed25519",
+        "credentials.json",
+        "service-account.json",
+        "service_account.json",
+        ".env",
+        ".npmrc",
+        ".pypirc",
+        ".netrc",
+        ".git-credentials",
+        "application_default_credentials.json",
+    }
+)
+_SENSITIVE_PATTERNS = (
+    "*.pem",
+    "*.key",
+    "*.p12",
+    "*.pfx",
+    "*.keystore",
+    "*.jks",
+    "secrets.*",
+    "secret.*",
+    ".env.*",
+)
+_SENSITIVE_PATH_SUFFIXES = (
+    (".aws", "credentials"),
+    (".aws", "config"),
+    (".docker", "config.json"),
+    (".config", "gcloud", "credentials.db"),
+    (".azure", "accesstokens.json"),
+    (".azure", "azureprofile.json"),
+    (".kube", "config"),
+)
+_ARCHIVE_SUFFIXES = (
+    ".zip",
+    ".tar",
+    ".tgz",
+    ".tar.gz",
+    ".tar.bz2",
+    ".tar.xz",
+    ".7z",
+    ".rar",
+    ".gz",
+    ".bz2",
+    ".xz",
+    ".jar",
+    ".war",
+    ".whl",
+    ".nupkg",
+    ".apk",
+    ".ipa",
+)
+_ARCHIVE_MAGIC_PREFIXES = (
+    b"PK\x03\x04",
+    b"PK\x05\x06",
+    b"PK\x07\x08",
+    b"\x1f\x8b",
+    b"BZh",
+    b"\xfd7zXZ\x00",
+    b"7z\xbc\xaf\x27\x1c",
+    b"Rar!\x1a\x07",
+)
+
+
+@dataclass(frozen=True)
+class SelectedFile:
+    path: Path
+    archive_name: str
+    size: int
+    device: int
+    inode: int
+    mtime_ns: int
+    ctime_ns: int
+
+
+@dataclass(frozen=True)
+class SourceManifest:
+    source: Path
+    files: tuple[SelectedFile, ...]
+    excluded: Counter[str]
+    include_hidden: bool
+    include_sensitive: bool
+    include_archives: bool
+
+    @property
+    def total_bytes(self) -> int:
+        return sum(item.size for item in self.files)
+
+    def as_dict(
+        self,
+        *,
+        show_files: bool,
+        archive_bytes: int | None = None,
+        archive_sha256: str | None = None,
+    ) -> dict[str, object]:
+        result: dict[str, object] = {
+            "source": str(self.source),
+            "file_count": len(self.files),
+            "uncompressed_bytes": self.total_bytes,
+            "excluded_count": sum(self.excluded.values()),
+            "excluded_by_reason": dict(sorted(self.excluded.items())),
+            "include_hidden": self.include_hidden,
+            "include_sensitive": self.include_sensitive,
+            "include_archives": self.include_archives,
+        }
+        if archive_bytes is not None:
+            result["archive_bytes"] = archive_bytes
+        if archive_sha256 is not None:
+            result["archive_sha256"] = archive_sha256
+        if show_files:
+            result["files"] = [item.archive_name for item in self.files]
+        return result
+
+
+@dataclass(frozen=True)
+class SourceBundle:
+    manifest: SourceManifest
+    archive_path: Path
+    archive_bytes: int
+    archive_sha256: str
+
+    def summary(self, *, show_files: bool) -> dict[str, object]:
+        return self.manifest.as_dict(
+            show_files=show_files,
+            archive_bytes=self.archive_bytes,
+            archive_sha256=self.archive_sha256,
+        )
+
+
+def prepare_source(
+    value: str,
+    *,
+    include_hidden: bool,
+    include_sensitive: bool,
+    include_archives: bool,
+    exclude: list[str],
+) -> SourceBundle:
+    """Select safe source files and build a bounded temporary ZIP archive."""
+    source = Path(value).expanduser().resolve()
+    if not source.is_dir():
+        if source.is_file() and (
+            source.name.lower().endswith(_ARCHIVE_SUFFIXES) or _has_archive_magic(source)
+        ):
+            raise http.CloudError(
+                f"--source must be a directory, not an archive: {source}",
+                next_step=(
+                    "Extract the archive and pass the directory to --source. Strix packs the "
+                    "directory and excludes dependencies, build output, and secret-like files. "
+                    "Add --dry-run --show-files to review the selection first."
+                ),
+            )
+        raise http.CloudError(f"--source must be a directory: {source}")
+    manifest = select_source(
+        source,
+        include_hidden=include_hidden,
+        include_sensitive=include_sensitive,
+        include_archives=include_archives,
+        exclude=exclude,
+    )
+    if not manifest.files:
+        raise http.CloudError("no files remain after applying source upload exclusions.")
+
+    with tempfile.NamedTemporaryFile(prefix="strix-source-", suffix=".zip", delete=False) as handle:
+        archive_path = Path(handle.name)
+    try:
+        _write_archive(archive_path, manifest.files)
+    except BaseException:
+        archive_path.unlink(missing_ok=True)
+        raise
+    archive_bytes = archive_path.stat().st_size
+    if archive_bytes > MAX_ARCHIVE_BYTES:
+        archive_path.unlink(missing_ok=True)
+        raise _archive_too_large_error(manifest, archive_bytes)
+    digest = _sha256(archive_path)
+    return SourceBundle(manifest, archive_path, archive_bytes, digest)
+
+
+_LARGEST_FILES_SHOWN = 5
+
+
+def _format_mib(size: int) -> str:
+    return f"{size / (1024 * 1024):.1f} MiB"
+
+
+def _archive_too_large_error(manifest: SourceManifest, archive_bytes: int) -> http.CloudError:
+    """Name the largest selected files so the user knows what to exclude."""
+    largest = sorted(manifest.files, key=lambda item: item.size, reverse=True)
+    listed = ", ".join(
+        f"{item.archive_name} ({_format_mib(item.size)})" for item in largest[:_LARGEST_FILES_SHOWN]
+    )
+    return http.CloudError(
+        f"the source archive is {_format_mib(archive_bytes)}, larger than the "
+        f"{_format_mib(MAX_ARCHIVE_BYTES)} upload limit. Largest files: {listed}.",
+        next_step=(
+            "Add --exclude patterns for large files or directories, or point --source at a "
+            "smaller directory. Run with --dry-run --show-files to review the selection."
+        ),
+    )
+
+
+def select_source(
+    source: Path,
+    *,
+    include_hidden: bool = False,
+    include_sensitive: bool = False,
+    include_archives: bool = False,
+    exclude: list[str] | None = None,
+) -> SourceManifest:
+    excluded: Counter[str] = Counter()
+    selected: list[SelectedFile] = []
+    patterns = [*_load_ignore_patterns(source), *(exclude or [])]
+    _validate_patterns(patterns)
+    total_bytes = 0
+    for relative in _candidate_paths(
+        source,
+        include_hidden=include_hidden,
+        patterns=patterns,
+        excluded=excluded,
+    ):
+        archive_name = relative.as_posix()
+        reason = _exclusion_reason(
+            relative,
+            include_hidden=include_hidden,
+            include_sensitive=include_sensitive,
+            include_archives=include_archives,
+            patterns=patterns,
+        )
+        if reason:
+            excluded[reason] += 1
+            continue
+        path = source / relative
+        try:
+            info = path.lstat()
+        except OSError:
+            excluded["unreadable"] += 1
+            continue
+        if not stat.S_ISREG(info.st_mode):
+            excluded["symlink_or_non_file"] += 1
+            continue
+        if not include_archives and _has_archive_magic(path):
+            excluded["nested_archive"] += 1
+            continue
+        if info.st_size > MAX_FILE_BYTES:
+            raise http.CloudError(
+                f"{archive_name} is larger than the 25 MB per-file limit; exclude it explicitly."
+            )
+        selected.append(
+            SelectedFile(
+                path=path,
+                archive_name=archive_name,
+                size=info.st_size,
+                device=info.st_dev,
+                inode=info.st_ino,
+                mtime_ns=info.st_mtime_ns,
+                ctime_ns=info.st_ctime_ns,
+            )
+        )
+        total_bytes += info.st_size
+        if len(selected) > MAX_FILES:
+            raise http.CloudError(
+                f"source contains more than {MAX_FILES:,} files; narrow --source or add exclusions."
+            )
+        if total_bytes > MAX_TOTAL_BYTES:
+            raise http.CloudError(
+                "selected source is larger than the 250 MB expanded-size limit; narrow --source "
+                "or add --exclude patterns."
+            )
+    selected.sort(key=lambda item: item.archive_name)
+    return SourceManifest(
+        source,
+        tuple(selected),
+        excluded,
+        include_hidden,
+        include_sensitive,
+        include_archives,
+    )
+
+
+def remove_bundle(bundle: SourceBundle) -> None:
+    bundle.archive_path.unlink(missing_ok=True)
+
+
+def _candidate_paths(
+    source: Path,
+    *,
+    include_hidden: bool,
+    patterns: list[str],
+    excluded: Counter[str],
+) -> Iterator[Path]:
+    git_root = _git_root(source)
+    if git_root is not None:
+        git = shutil.which("git")
+        if git is not None:
+            yield from _git_candidate_paths(git, git_root, source)
+            return
+    yield from _walk_candidate_paths(
+        source,
+        include_hidden=include_hidden,
+        patterns=patterns,
+        excluded=excluded,
+    )
+
+
+def _git_candidate_paths(git: str, git_root: Path, source: Path) -> Iterator[Path]:
+    """Stream Git's NUL-delimited manifest without buffering an unbounded repository."""
+    relative_source = source.relative_to(git_root)
+    command = [
+        git,
+        "-C",
+        str(git_root),
+        "ls-files",
+        "-z",
+        "--cached",
+        "--others",
+        "--exclude-standard",
+        "--",
+    ]
+    if relative_source != Path():
+        command.append(relative_source.as_posix())
+    try:
+        process = subprocess.Popen(  # noqa: S603  # nosec B603
+            command,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.DEVNULL,
+        )
+    except OSError as exc:
+        raise http.CloudError(f"could not enumerate Git source files: {exc}") from exc
+    assert process.stdout is not None
+    buffer = b""
+    count = 0
+    try:
+        while chunk := process.stdout.read(64 * 1024):
+            buffer += chunk
+            records = buffer.split(b"\0")
+            buffer = records.pop()
+            for raw in records:
+                relative = _git_relative_path(raw, relative_source)
+                if relative is None:
+                    continue
+                count += 1
+                _check_candidate_limit(count)
+                yield relative
+        if buffer:
+            raise http.CloudError("Git returned a malformed source file manifest.")
+        if process.wait() != 0:
+            raise http.CloudError("Git could not enumerate the source directory.")
+    finally:
+        process.stdout.close()
+        if process.poll() is None:
+            process.terminate()
+            try:
+                process.wait(timeout=1)
+            except subprocess.TimeoutExpired:
+                process.kill()
+                process.wait()
+
+
+def _git_relative_path(raw: bytes, relative_source: Path) -> Path | None:
+    repo_relative = Path(os.fsdecode(raw))
+    try:
+        relative = repo_relative.relative_to(relative_source)
+    except ValueError:
+        return None
+    if relative.is_absolute() or ".." in relative.parts:
+        raise http.CloudError("Git returned an unsafe source path.")
+    return relative
+
+
+def _walk_candidate_paths(
+    source: Path,
+    *,
+    include_hidden: bool,
+    patterns: list[str],
+    excluded: Counter[str],
+) -> Iterator[Path]:
+    """Walk top-down so excluded dependency, VCS, and hidden trees are never traversed."""
+    count = 0
+    stack: list[tuple[Path, _ScandirIterator]] = []
+    try:
+        stack.append((source, os.scandir(source)))
+        while stack:
+            root_path, entries = stack[-1]
+            try:
+                entry = next(entries)
+            except StopIteration:
+                entries.close()
+                stack.pop()
+                continue
+            count += 1
+            _check_candidate_limit(count)
+            path = root_path / entry.name
+            relative = path.relative_to(source)
+            try:
+                is_directory = entry.is_dir(follow_symlinks=False)
+                is_symlink = entry.is_symlink()
+            except OSError:
+                excluded["unreadable"] += 1
+                continue
+            if is_directory:
+                reason = _pruned_directory_reason(
+                    relative,
+                    include_hidden=include_hidden,
+                    patterns=patterns,
+                )
+                if reason:
+                    excluded[reason] += 1
+                    continue
+                try:
+                    stack.append((path, os.scandir(path)))
+                except OSError:
+                    excluded["unreadable"] += 1
+                continue
+            if is_symlink:
+                excluded["symlink_or_non_file"] += 1
+                continue
+            yield relative
+    except OSError as exc:
+        raise http.CloudError(f"could not enumerate source directory {source}: {exc}") from exc
+    finally:
+        for _, entries in stack:
+            entries.close()
+
+
+def _pruned_directory_reason(
+    relative: Path,
+    *,
+    include_hidden: bool,
+    patterns: list[str],
+) -> str | None:
+    lower_parts = tuple(part.lower() for part in relative.parts)
+    if any(part == ".git" for part in lower_parts):
+        return "git_metadata"
+    if any(part in _ALWAYS_EXCLUDED_DIRS for part in lower_parts):
+        return "dependency_or_build_output"
+    if not include_hidden and any(part.startswith(".") for part in relative.parts):
+        return "hidden"
+    if any(_matches_user_pattern(relative, pattern) for pattern in patterns):
+        return "user_pattern"
+    return None
+
+
+def _check_candidate_limit(count: int) -> None:
+    if count > MAX_CANDIDATE_PATHS:
+        raise http.CloudError(
+            f"source enumeration exceeded {MAX_CANDIDATE_PATHS:,} paths before filtering; "
+            "narrow --source or add directory exclusions."
+        )
+
+
+def _git_root(source: Path) -> Path | None:
+    git = shutil.which("git")
+    if git is None:
+        return None
+    result = subprocess.run(  # noqa: S603  # nosec B603
+        [git, "-C", str(source), "rev-parse", "--show-toplevel"],
+        check=False,
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0:
+        return None
+    try:
+        return Path(result.stdout.strip()).resolve()
+    except OSError:
+        return None
+
+
+def _exclusion_reason(  # noqa: PLR0911
+    relative: Path,
+    *,
+    include_hidden: bool,
+    include_sensitive: bool,
+    include_archives: bool,
+    patterns: list[str],
+) -> str | None:
+    parts = relative.parts
+    lower_parts = tuple(part.lower() for part in parts)
+    if any(part == ".git" for part in lower_parts):
+        return "git_metadata"
+    if any(part in _ALWAYS_EXCLUDED_DIRS for part in lower_parts[:-1]):
+        return "dependency_or_build_output"
+    if not include_hidden and any(part.startswith(".") for part in parts):
+        return "hidden"
+    if any(_matches_user_pattern(relative, pattern) for pattern in patterns):
+        return "user_pattern"
+    name = relative.name.lower()
+    if not include_sensitive and (
+        name in _SENSITIVE_NAMES
+        or any(fnmatch.fnmatch(name, pattern) for pattern in _SENSITIVE_PATTERNS)
+        or any(
+            lower_parts[-len(suffix) :] == suffix
+            for suffix in _SENSITIVE_PATH_SUFFIXES
+            if len(lower_parts) >= len(suffix)
+        )
+    ):
+        return "sensitive_filename"
+    if not include_archives and name.endswith(_ARCHIVE_SUFFIXES):
+        return "nested_archive"
+    return None
+
+
+def _matches_user_pattern(relative: Path, pattern: str) -> bool:
+    """Match exclude globs, including intuitive trailing-slash directory rules."""
+    relative_posix = relative.as_posix()
+    posix = PurePosixPath(relative_posix)
+    if pattern.endswith("/"):
+        directory_pattern = pattern.rstrip("/")
+        if not directory_pattern:
+            return False
+        return (
+            posix.match(directory_pattern)
+            or fnmatch.fnmatch(relative_posix, directory_pattern)
+            or any(
+                PurePosixPath(parent.as_posix()).match(directory_pattern)
+                or fnmatch.fnmatch(parent.as_posix(), directory_pattern)
+                for parent in posix.parents
+                if parent != PurePosixPath(".")
+            )
+        )
+    return posix.match(pattern) or fnmatch.fnmatch(relative_posix, pattern)
+
+
+def _write_archive(destination: Path, files: tuple[SelectedFile, ...]) -> None:
+    with zipfile.ZipFile(
+        destination, "w", compression=zipfile.ZIP_DEFLATED, compresslevel=6
+    ) as archive:
+        for item in files:
+            flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0)
+            try:
+                descriptor = os.open(item.path, flags)
+            except OSError as exc:
+                raise http.CloudError(f"could not safely read {item.archive_name}: {exc}") from exc
+            with os.fdopen(descriptor, "rb") as source_file:
+                current = os.fstat(source_file.fileno())
+                if (
+                    not stat.S_ISREG(current.st_mode)
+                    or current.st_size != item.size
+                    or current.st_dev != item.device
+                    or current.st_ino != item.inode
+                    or current.st_mtime_ns != item.mtime_ns
+                    or current.st_ctime_ns != item.ctime_ns
+                ):
+                    raise http.CloudError(
+                        f"{item.archive_name} changed while the source archive was being built; "
+                        "retry."
+                    )
+                info = zipfile.ZipInfo(item.archive_name)
+                info.compress_type = zipfile.ZIP_DEFLATED
+                info.external_attr = 0o100644 << 16
+                with archive.open(info, "w", force_zip64=True) as target:
+                    remaining = item.size
+                    while remaining:
+                        chunk = source_file.read(min(1024 * 1024, remaining))
+                        if not chunk:
+                            raise http.CloudError(
+                                f"{item.archive_name} changed while the source archive was being "
+                                "built; retry."
+                            )
+                        target.write(chunk)
+                        remaining -= len(chunk)
+                    final = os.fstat(source_file.fileno())
+                    if (
+                        source_file.read(1)
+                        or not stat.S_ISREG(final.st_mode)
+                        or final.st_size != item.size
+                        or final.st_dev != item.device
+                        or final.st_ino != item.inode
+                        or final.st_mtime_ns != item.mtime_ns
+                        or final.st_ctime_ns != item.ctime_ns
+                    ):
+                        raise http.CloudError(
+                            f"{item.archive_name} changed while the source archive was being "
+                            "built; retry."
+                        )
+
+
+def _sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as stream:
+        for chunk in iter(lambda: stream.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _has_archive_magic(path: Path) -> bool:
+    """Recognize common archive containers even when their suffix is disguised."""
+    flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0)
+    try:
+        descriptor = os.open(path, flags)
+        with os.fdopen(descriptor, "rb") as stream:
+            header = stream.read(512)
+    except OSError:
+        return False
+    return header.startswith(_ARCHIVE_MAGIC_PREFIXES) or header[257:262] == b"ustar"
+
+
+def _load_ignore_patterns(source: Path) -> list[str]:
+    path = source / ".strixignore"
+    raw_text = _read_ignore_file(path)
+    if raw_text is None:
+        return []
+    if len(raw_text) > MAX_IGNORE_BYTES:
+        raise http.CloudError(f"{path} is larger than the {MAX_IGNORE_BYTES:,}-byte limit.")
+    try:
+        lines = raw_text.decode("utf-8").splitlines()
+    except UnicodeDecodeError as exc:
+        raise http.CloudError(f"{path} must be UTF-8 text.") from exc
+    patterns: list[str] = []
+    for line_number, raw in enumerate(lines, start=1):
+        value = raw.strip()
+        if not value or value.startswith("#"):
+            continue
+        if value.startswith("!"):
+            raise http.CloudError(
+                f"{path}:{line_number}: negated patterns are not supported; use exclude-only globs."
+            )
+        patterns.append(value)
+        if len(patterns) > MAX_IGNORE_PATTERNS:
+            raise http.CloudError(
+                f"{path} contains more than {MAX_IGNORE_PATTERNS:,} exclusion patterns."
+            )
+    return patterns
+
+
+def _read_ignore_file(path: Path) -> bytes | None:
+    """Read a bounded regular ignore file without blocking on a FIFO or device."""
+    try:
+        descriptor = os.open(
+            path,
+            os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0) | getattr(os, "O_NONBLOCK", 0),
+        )
+    except FileNotFoundError:
+        return None
+    except OSError as exc:
+        raise http.CloudError(f"could not read {path}: {exc}") from exc
+    try:
+        info = os.fstat(descriptor)
+    except OSError as exc:
+        os.close(descriptor)
+        raise http.CloudError(f"could not inspect {path}: {exc}") from exc
+    if not stat.S_ISREG(info.st_mode):
+        os.close(descriptor)
+        raise http.CloudError(f"{path} must be a regular file.")
+    try:
+        stream = os.fdopen(descriptor, "rb")
+    except OSError as exc:
+        os.close(descriptor)
+        raise http.CloudError(f"could not read {path}: {exc}") from exc
+    try:
+        return stream.read(MAX_IGNORE_BYTES + 1)
+    except OSError as exc:
+        raise http.CloudError(f"could not read {path}: {exc}") from exc
+    finally:
+        stream.close()
+
+
+def _validate_patterns(patterns: list[str]) -> None:
+    if len(patterns) > MAX_IGNORE_PATTERNS:
+        raise http.CloudError(
+            f"source upload accepts at most {MAX_IGNORE_PATTERNS:,} exclusion patterns."
+        )
+    for pattern in patterns:
+        if len(pattern) > MAX_IGNORE_PATTERN_CHARS:
+            raise http.CloudError(
+                "source exclusion patterns must be at most "
+                f"{MAX_IGNORE_PATTERN_CHARS:,} characters each."
+            )
+        if "\x00" in pattern:
+            raise http.CloudError("source exclusion patterns cannot contain NUL bytes.")

strix/interface/cloud/workspaces.py

@@ -0,0 +1,291 @@
+"""`strix cloud workspaces use` — switch the stored token to another workspace.
+
+The command lists the workspaces of the account, finds the requested one by
+ID or by exact name, asks the platform to rotate that token in place, and
+stores the returned workspace metadata. The bearer secret and expiry stay the
+same; the account's role in the target workspace limits the granted scopes.
+"""
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING, Any, cast
+
+from rich.console import Console
+from rich.markup import escape
+
+import strix.interface.cloud.http as http  # noqa: PLR0402
+from strix.interface.cloud.arguments import CloudArgumentParser
+from strix.interface.cloud.render import emit, json_mode
+from strix.interface.platform_cli import AUTH_PATH, read_record, save_record
+from strix.interface.platform_identity import read_or_create_identity
+from strix.interface.terminal_text import sanitize_terminal_text
+
+
+if TYPE_CHECKING:
+    import argparse
+
+
+def run_workspace_use(argv: list[str]) -> int:
+    """Entry point for ``strix cloud workspaces use``. Returns an exit code."""
+    console = Console()
+    parser = CloudArgumentParser(
+        prog="strix cloud workspaces use",
+        description="Switch the stored API token to another workspace.",
+    )
+    parser.add_argument(
+        "workspace",
+        metavar="WORKSPACE",
+        help="Workspace number from `workspaces list`, ID, or exact name.",
+    )
+    scope_mode = parser.add_mutually_exclusive_group()
+    scope_mode.add_argument(
+        "--scopes",
+        nargs="+",
+        metavar="SCOPE",
+        default=None,
+        help=(
+            "Use a custom scope set within the login-approved ceiling. "
+            "Without this option, preserve the server-side scope preference."
+        ),
+    )
+    scope_mode.add_argument(
+        "--scope-profile",
+        choices=("minimal", "recommended", "full"),
+        default=None,
+        help="Change to a profile within the authority approved at login.",
+    )
+    parser.add_argument("--show-scopes", action="store_true", help="Print every granted scope.")
+    parser.add_argument("--json", action="store_true", help="Print the raw JSON response.")
+    parser.add_argument("--token", default=None, help="API token override.")
+    parser.add_argument(
+        "--workspace-id",
+        default=None,
+        metavar="ORG_ID",
+        help="Expected workspace for an override CLI token.",
+    )
+    parser.add_argument("--app-url", default=None, metavar="URL", help="Platform URL override.")
+    parser.add_argument(
+        "--timeout", default=None, type=float, metavar="SECONDS", help="Request timeout in seconds."
+    )
+    as_json = json_mode(flag="--json" in argv)
+    try:
+        args = parser.parse_args(argv)
+    except SystemExit as exc:
+        return exc.code if isinstance(exc.code, int) else 2
+    except http.CloudError as exc:
+        _emit_cloud_error(console, exc, as_json=as_json)
+        return exc.exit_code
+
+    as_json = json_mode(flag=bool(args.json))
+    try:
+        http.configure(
+            base_url=args.app_url,
+            timeout=args.timeout,
+            token_override=bool(args.token),
+            workspace_id=args.workspace_id,
+        )
+        return _use(console, args, as_json=as_json)
+    except http.CloudError as exc:
+        _emit_cloud_error(console, exc, as_json=as_json)
+        return exc.exit_code
+
+
+def _use(  # noqa: PLR0912, PLR0915
+    console: Console, args: argparse.Namespace, *, as_json: bool
+) -> int:
+    workspace = _find_workspace(args.workspace, token=args.token)
+    stored_record: dict[str, Any] = read_record() or {}
+    # An override token may belong to a different account. Never mix its new
+    # workspace state with identity or scope preferences from the stored sign-in.
+    external_token = args.token is not None or bool(os.environ.get("STRIX_API_TOKEN", "").strip())
+    record: dict[str, Any] = {} if external_token else dict(stored_record)
+    body: dict[str, Any] = {}
+    if args.scopes:
+        body["scopes"] = args.scopes
+        body["scope_profile"] = "custom"
+    elif args.scope_profile:
+        body["scope_profile"] = args.scope_profile
+    if not external_token:
+        try:
+            body.update(read_or_create_identity())
+        except (OSError, ValueError) as exc:
+            raise http.CloudError(f"could not load the CLI device identity: {exc}") from exc
+    switched = _switch_workspace_token(
+        str(workspace["id"]),
+        token=args.token,
+        body=body or None,
+    )
+    if not isinstance(switched, dict):
+        raise _workspace_switch_unknown("the platform returned an invalid response")
+    switched_record = cast("dict[str, Any]", switched)
+    switched_token = switched_record.get("api_token")
+    if not isinstance(switched_token, str) or not switched_token.strip():
+        raise _workspace_switch_unknown("the platform response omitted the token")
+    switched_scopes = switched_record.get("scopes")
+    switched_scope_items = cast("list[Any]", cast("Any", switched_scopes))
+    if not isinstance(switched_scopes, list) or not all(
+        isinstance(scope, str) for scope in switched_scope_items
+    ):
+        raise _workspace_switch_unknown("the platform response contained invalid scopes")
+    validated_scopes = cast("list[str]", switched_scope_items)
+
+    record.update(
+        {
+            "api_token": switched_token,
+            "organization_id": switched_record.get("organization_id", workspace["id"]),
+            "organization_name": switched_record.get(
+                "organization_name", workspace.get("name", "")
+            ),
+            "expires_at": switched_record.get("expires_at") or stored_record.get("expires_at"),
+            "scopes": validated_scopes,
+            "requested_scopes": switched_record.get("requested_scopes", validated_scopes),
+            "scope_ceiling": switched_record.get("scope_ceiling", []),
+            "scope_profile": switched_record.get("scope_profile", "custom"),
+            "token_id": switched_record.get("token_id"),
+            "credential_source": switched_record.get("credential_source", "api"),
+            "device_name": switched_record.get("device_name"),
+            "app_url": http.app_url(),
+        }
+    )
+    if switched_record.get("email"):
+        record["email"] = switched_record["email"]
+    if not external_token:
+        try:
+            save_record(record)
+        except OSError as exc:
+            raise http.CloudError(
+                "the platform switched the token, but the local workspace metadata could not be "
+                f"stored in {AUTH_PATH}: {exc}. The bearer is still valid; fix the file and safely "
+                "rerun the same workspace use command.",
+                payload={
+                    "workspace_switched": True,
+                    "local_record_updated": False,
+                    "retry_safe": True,
+                },
+            ) from exc
+
+    result = {
+        "workspace_id": record["organization_id"],
+        "workspace_name": record["organization_name"],
+        "scopes": record["scopes"],
+        "requested_scopes": record.get("requested_scopes", record["scopes"]),
+        "scope_ceiling": record.get("scope_ceiling", []),
+        "scope_profile": record.get("scope_profile", "custom"),
+        "expires_at": record.get("expires_at"),
+        "token_id": record.get("token_id"),
+        "credential_source": record.get("credential_source", "api"),
+        "device_name": record.get("device_name"),
+        "stored": not external_token,
+    }
+    if as_json:
+        emit(console, result, as_json=True)
+        return http.EXIT_OK
+    workspace_name = escape(sanitize_terminal_text(record["organization_name"]))
+    console.print(f"[green]✓ Switched to workspace [bold]{workspace_name}[/].[/]")
+    scopes = record.get("scopes")
+    if isinstance(scopes, list) and scopes:
+        scope_items = cast("list[Any]", cast("Any", scopes))
+        scope_names = [scope for scope in scope_items if isinstance(scope, str)]
+        if scope_names and args.show_scopes:
+            rendered_scopes = escape(sanitize_terminal_text(" ".join(scope_names)))
+            console.print(f"  Scopes: [dim]{rendered_scopes}[/]")
+        elif scope_names:
+            profile = str(record.get("scope_profile") or "custom").title()
+            console.print(f"  Access: [dim]{profile} · {len(scope_names)} scopes granted[/]")
+    if external_token:
+        console.print("  Token:  [dim]override used for this command only; not stored[/]")
+    else:
+        console.print(f"  Token:  stored in [dim]{escape(sanitize_terminal_text(AUTH_PATH))}[/]")
+    return http.EXIT_OK
+
+
+def _switch_workspace_token(
+    workspace_id: str,
+    *,
+    token: str | None,
+    body: dict[str, Any] | None,
+) -> Any:
+    """Switch in place, distinguishing definitive rejections from lost outcomes."""
+    try:
+        response = http.request(
+            "POST",
+            f"/workspaces/{workspace_id}/token",
+            token=token,
+            body=body,
+        )
+    except http.CloudError as exc:
+        raise _workspace_switch_unknown(str(exc)) from exc
+
+    # Client/auth/conflict responses prove the rotation did not return success.
+    # A 5xx or malformed success may arrive after the database commit, but the
+    # server preserves the bearer so replaying this exact command is safe.
+    if response.status_code in {400, 401, 403, 404, 409, 422}:
+        return http.check(response)
+    try:
+        return http.check(response)
+    except http.CloudError as exc:
+        raise _workspace_switch_unknown(str(exc)) from exc
+
+
+def _workspace_switch_unknown(detail: str) -> http.CloudError:
+    return http.CloudError(
+        "workspace switch outcome is unknown: "
+        f"{sanitize_terminal_text(detail)}. The bearer secret is unchanged; safely rerun the "
+        "same workspace use command, or list workspaces to check the current one.",
+        payload={
+            "switch_outcome_unknown": True,
+            "retry_safe": True,
+        },
+    )
+
+
+def _emit_cloud_error(console: Console, error: http.CloudError, *, as_json: bool) -> None:
+    if as_json:
+        raw_payload: Any = error.payload
+        error_payload = cast("dict[str, Any]", raw_payload)
+        payload = dict(error_payload) if isinstance(raw_payload, dict) else {}
+        payload["error"] = str(error)
+        emit(console, payload, as_json=True)
+        return
+    console.print(f"[red]Error:[/] {escape(sanitize_terminal_text(error))}")
+
+
+def _find_workspace(selector: str, *, token: str | None) -> dict[str, Any]:
+    listed = http.check(http.request("GET", "/workspaces", token=token))
+    listed_record = cast("dict[str, Any]", listed) if isinstance(listed, dict) else {}
+    items = listed_record.get("workspaces")
+    item_values = cast("list[Any]", cast("Any", items)) if isinstance(items, list) else []
+    workspaces = [
+        cast("dict[str, Any]", cast("Any", item)) for item in item_values if isinstance(item, dict)
+    ]
+    if not workspaces:
+        raise http.CloudError("no workspaces found for this account.")
+    wanted = selector.strip()
+    if wanted.isdigit():
+        index = int(wanted)
+        if 1 <= index <= len(workspaces):
+            return workspaces[index - 1]
+        raise http.CloudError(
+            f"workspace number must be between 1 and {len(workspaces)}. "
+            "Run `strix cloud workspaces` to see the numbered list."
+        )
+    by_id = [w for w in workspaces if w.get("id") == wanted]
+    if by_id:
+        return by_id[0]
+    by_name = [w for w in workspaces if str(w.get("name", "")).casefold() == wanted.casefold()]
+    if len(by_name) == 1:
+        return by_name[0]
+    if len(by_name) > 1:
+        numbers = ", ".join(
+            str(index)
+            for index, workspace in enumerate(workspaces, start=1)
+            if workspace in by_name
+        )
+        raise http.CloudError(
+            f"multiple workspaces are named {wanted!r}. Use its list number: {numbers}"
+        )
+    names = ", ".join(
+        f"{index}: {workspace.get('name')}" for index, workspace in enumerate(workspaces, start=1)
+    )
+    raise http.CloudError(f"no workspace matches {wanted!r}. Your workspaces: {names}")

strix/interface/completions.py

@@ -0,0 +1,373 @@
+"""Shell completion scripts and candidates for the Strix CLI."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+from typing import Any
+
+from strix.interface.cloud.spec import DEFAULT_VERBS, SPEC, Cmd
+from strix.interface.terminal_text import has_terminal_control, sanitize_terminal_text
+
+
+_ROOT_COMMANDS = ("cloud", "auth", "view", "completions", "completion")
+_SESSION_COMMANDS = ("login", "logout", "whoami", "session", "credits")
+_COMMON_FLAGS = (
+    "--json",
+    "--token",
+    "--workspace-id",
+    "--app-url",
+    "--timeout",
+    "-h",
+    "--help",
+)
+_COMMON_VALUE_FLAGS = frozenset({"--token", "--workspace-id", "--app-url", "--timeout"})
+_WORKSPACE_USE_FLAGS = (*_COMMON_FLAGS, "--scopes", "--scope-profile", "--show-scopes")
+
+
+def run_completions(argv: list[str]) -> int:
+    """Print a shell integration script or hidden completion candidates."""
+    if argv and argv[0] == "--candidates":
+        for candidate in completion_candidates(argv[1:]):
+            sys.stdout.write(candidate + "\n")
+        return 0
+    if not argv or argv[0] in ("-h", "--help", "help"):
+        sys.stdout.write(
+            "Usage: strix completions <zsh|bash|fish>\n\n"
+            "Enable tab completion for the current shell:\n"
+            "  zsh:  source <(strix completions zsh)\n"
+            "  bash: source <(strix completions bash)\n"
+            "  fish: strix completions fish | source\n"
+        )
+        return 0
+    shell = argv[0].lower()
+    scripts = {"zsh": _zsh_script, "bash": _bash_script, "fish": _fish_script}
+    generator = scripts.get(shell)
+    if generator is None:
+        sys.stderr.write(
+            f"Unknown shell: {sanitize_terminal_text(shell)}. Choose zsh, bash, or fish.\n"
+        )
+        return 2
+    sys.stdout.write(generator())
+    return 0
+
+
+def completion_candidates(words: list[str]) -> list[str]:
+    """Return candidates for words after the ``strix`` executable."""
+    prior, current = _split_cursor(words)
+    if not prior:
+        candidates = _matching(_ROOT_COMMANDS, current)
+    elif prior[0] != "cloud":
+        candidates = []
+    else:
+        candidates = _cloud_candidates(prior[1:], current)
+    # The line-oriented shell protocol cannot represent these names safely.
+    # Omitting them is preferable to returning a sanitized path that does not exist.
+    return [candidate for candidate in candidates if not has_terminal_control(candidate)]
+
+
+def _split_cursor(words: list[str]) -> tuple[list[str], str]:
+    if not words:
+        return [], ""
+    return words[:-1], words[-1]
+
+
+def _cloud_candidates(prior: list[str], current: str) -> list[str]:  # noqa: PLR0911
+    groups = (*_SESSION_COMMANDS, *SPEC, "workspace")
+    if not prior:
+        return _matching(groups, current)
+    group = "workspaces" if prior[0] == "workspace" else prior[0]
+    rest = prior[1:]
+    if group in _SESSION_COMMANDS:
+        return _session_candidates(group, rest, current)
+    commands = SPEC.get(group)
+    if commands is None:
+        return _matching(groups, current)
+    default_verb = DEFAULT_VERBS.get(group)
+    default_is_active = (rest and rest[0].startswith("-")) or (not rest and current.startswith("-"))
+    if default_verb is not None and default_is_active:
+        return _command_candidates(commands[default_verb], rest, current)
+
+    command_paths = sorted(
+        ((verb.split(), cmd) for verb, cmd in commands.items()),
+        key=lambda item: len(item[0]),
+        reverse=True,
+    )
+    for path, cmd in command_paths:
+        if rest[: len(path)] == path:
+            command_candidates = _command_candidates(cmd, rest[len(path) :], current)
+            if rest == path:
+                nested_words = {
+                    candidate_path[len(path)]
+                    for candidate_path, _candidate_cmd in command_paths
+                    if len(candidate_path) > len(path) and candidate_path[: len(path)] == path
+                }
+                return sorted({*command_candidates, *_matching(nested_words, current)})
+            return command_candidates
+    if group == "workspaces" and rest[:1] == ["use"]:
+        return _flag_candidates(
+            _WORKSPACE_USE_FLAGS,
+            rest[1:],
+            current,
+            value_flags=_COMMON_VALUE_FLAGS | {"--scopes"},
+        )
+
+    verb_paths = [path for path, _cmd in command_paths]
+    if group == "workspaces":
+        verb_paths.append(["use"])
+    matching_paths = [path for path in verb_paths if path[: len(rest)] == rest]
+    if not matching_paths:
+        return []
+    next_words = sorted({path[len(rest)] for path in matching_paths if len(path) > len(rest)})
+    return _matching(next_words, current)
+
+
+def _session_candidates(group: str, prior: list[str], current: str) -> list[str]:
+    if group == "session":
+        if not prior:
+            return _matching(("show", "scopes", "help", *_COMMON_FLAGS, "--show-scopes"), current)
+        if prior[:1] == ["scopes"] and len(prior) == 1:
+            return _matching(("set", *_COMMON_FLAGS, "--show-scopes"), current)
+        if prior[:2] == ["scopes", "set"]:
+            return _matching(
+                ("minimal", "recommended", "full", "--scopes", *_COMMON_FLAGS, "--show-scopes"),
+                current,
+            )
+        return _flag_candidates(
+            (*_COMMON_FLAGS, "--show-scopes"),
+            prior,
+            current,
+            value_flags=_COMMON_VALUE_FLAGS | {"--scopes"},
+        )
+    flags = _session_flags(group)
+    value_flags: frozenset[str] = frozenset()
+    if group == "login":
+        value_flags = frozenset({"--scopes", "--scope-profile", "--workspace", "--device-name"})
+    elif group == "credits":
+        value_flags = _COMMON_VALUE_FLAGS
+    return _flag_candidates(flags, prior, current, value_flags=value_flags)
+
+
+def _session_flags(group: str) -> tuple[str, ...]:
+    if group == "login":
+        return (
+            "--no-browser",
+            "--scopes",
+            "--scope-profile",
+            "--workspace",
+            "--device-name",
+            "-h",
+            "--help",
+        )
+    if group == "whoami":
+        return ("--json", "--show-scopes", "-h", "--help")
+    if group == "logout":
+        return ("--json", "--local-only", "-h", "--help")
+    if group == "credits":
+        return _COMMON_FLAGS
+    return ("-h", "--help")
+
+
+def _command_candidates(cmd: Cmd, prior: list[str], current: str) -> list[str]:
+    filesystem = _filesystem_candidates(cmd, prior, current)
+    if filesystem is not None:
+        return filesystem
+    return _flag_candidates(
+        _command_flags(cmd),
+        prior,
+        current,
+        value_flags=_command_value_flags(cmd),
+    )
+
+
+def _flag_candidates(
+    flags: tuple[str, ...],
+    prior: list[str],
+    current: str,
+    *,
+    value_flags: frozenset[str],
+) -> list[str]:
+    if prior and prior[-1] in value_flags and not current.startswith("-"):
+        return []
+    return _matching(flags, current)
+
+
+def _command_flags(cmd: Cmd) -> tuple[str, ...]:
+    flags: list[str] = list(_COMMON_FLAGS)
+    for param in cmd.query + cmd.body:
+        flag = "--" + (param.flag or _kebab(param.name))
+        flags.append(flag)
+        if param.kind == "bool":
+            flags.append("--no-" + flag.removeprefix("--"))
+    if cmd.method in ("POST", "PUT", "PATCH"):
+        flags.append("--data")
+    if cmd.idempotent:
+        flags.append("--idempotency-key")
+    if cmd.binary or cmd.path == "/audit":
+        flags.extend(("--output", "--force"))
+    if cmd.link:
+        flags.append("--no-browser")
+    if cmd.wait_path or cmd.wait_self:
+        flags.extend(("--wait", "--wait-timeout"))
+    if cmd.path == "/billing/topup":
+        flags.extend(("--yes", "--no-pay", "--payment-method"))
+    if cmd.path == "/scans" and cmd.method == "POST":
+        flags.extend(
+            (
+                "--source",
+                "--approve-sha256",
+                "--dry-run",
+                "--yes",
+                "--show-files",
+                "--exclude",
+                "--include-hidden",
+                "--include-sensitive",
+                "--include-archives",
+            )
+        )
+    if cmd.path == "/billing/auto-topup" and cmd.method == "PUT":
+        flags.append("--no-monthly-cap")
+    return tuple(dict.fromkeys(flags))
+
+
+def _command_value_flags(cmd: Cmd) -> frozenset[str]:
+    flags = set(_COMMON_VALUE_FLAGS)
+    for param in cmd.query + cmd.body:
+        if param.kind != "bool":
+            flags.add("--" + (param.flag or _kebab(param.name)))
+    if cmd.method in ("POST", "PUT", "PATCH"):
+        flags.add("--data")
+    if cmd.idempotent:
+        flags.add("--idempotency-key")
+    if cmd.binary or cmd.path == "/audit":
+        flags.add("--output")
+    if cmd.wait_path or cmd.wait_self:
+        flags.add("--wait-timeout")
+    if cmd.path == "/billing/topup":
+        flags.add("--payment-method")
+    if cmd.path == "/scans" and cmd.method == "POST":
+        flags.update(("--source", "--approve-sha256", "--exclude"))
+    return frozenset(flags)
+
+
+def _filesystem_candidates(  # noqa: PLR0911
+    cmd: Cmd, prior: list[str], current: str
+) -> list[str] | None:
+    inline = (
+        ("--source=", True, ""),
+        ("--output=", False, ""),
+        ("--data=@", False, "@"),
+    )
+    for option, directories_only, marker in inline:
+        if current.startswith(option):
+            value = current.removeprefix(option)
+            return [
+                option + candidate.removeprefix(marker)
+                for candidate in _path_candidates(
+                    marker + value,
+                    directories_only=directories_only,
+                    marker=marker,
+                )
+            ]
+
+    if not prior or current.startswith("-"):
+        return None
+    option = prior[-1]
+    if option == "--source" and cmd.path == "/scans" and cmd.method == "POST":
+        return _path_candidates(current, directories_only=True)
+    if option == "--output" and (cmd.binary or cmd.path == "/audit"):
+        return _path_candidates(current)
+    if option == "--data" and cmd.method in ("POST", "PUT", "PATCH"):
+        if not current:
+            return ["@"]
+        if current.startswith("@"):
+            return _path_candidates(current, marker="@")
+        return []
+    return None
+
+
+def _path_candidates(
+    value: str,
+    *,
+    directories_only: bool = False,
+    marker: str = "",
+) -> list[str]:
+    raw = value.removeprefix(marker) if marker else value
+    ends_with_separator = raw.endswith(("/", "\\"))
+    expanded = Path(raw or ".").expanduser()
+    directory = expanded if ends_with_separator else expanded.parent
+    name_prefix = "" if ends_with_separator else expanded.name
+    raw_base = raw if ends_with_separator else raw[: len(raw) - len(name_prefix)]
+    try:
+        entries = directory.iterdir()
+        matches = [
+            entry
+            for entry in entries
+            if entry.name.startswith(name_prefix) and (not directories_only or entry.is_dir())
+        ]
+    except OSError:
+        return []
+
+    candidates: list[str] = []
+    for entry in sorted(matches, key=lambda item: item.name.casefold()):
+        candidate = marker + raw_base + entry.name
+        if entry.is_dir():
+            candidate += "/"
+        candidates.append(candidate)
+    return candidates
+
+
+def _kebab(value: str) -> str:
+    output: list[str] = []
+    for char in value:
+        if char.isupper():
+            output.extend(("-", char.lower()))
+        else:
+            output.append("-" if char == "_" else char)
+    return "".join(output)
+
+
+def _matching(candidates: Any, prefix: str) -> list[str]:
+    return sorted({str(candidate) for candidate in candidates if str(candidate).startswith(prefix)})
+
+
+def _zsh_script() -> str:
+    return r"""#compdef strix
+_strix() {
+  local -a candidates
+  candidates=("${(@f)$($words[1] completions --candidates "${words[@]:2}")}")
+  _describe 'strix' candidates
+}
+compdef _strix strix
+"""
+
+
+def _bash_script() -> str:
+    return r"""_strix_completion() {
+  local -a candidates
+  local candidate
+  while IFS= read -r candidate; do
+    candidates+=("$candidate")
+  done < <(strix completions --candidates "${COMP_WORDS[@]:1:$COMP_CWORD}")
+  COMPREPLY=("${candidates[@]}")
+  for candidate in "${COMPREPLY[@]}"; do
+    if [[ $candidate == */ ]]; then
+      if type compopt >/dev/null 2>&1; then
+        compopt -o nospace
+      fi
+      break
+    fi
+  done
+}
+complete -F _strix_completion strix
+"""
+
+
+def _fish_script() -> str:
+    return r"""function __strix_candidates
+  set -l words (commandline -opc)
+  set -e words[1]
+  command strix completions --candidates $words (commandline -ct)
+end
+complete -c strix -f -a '(__strix_candidates)'
+"""

strix/interface/environment.py

@@ -8,17 +8,29 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode
+from strix.config import IntegrationSettings, codex, load_settings
 from strix.interface.utils import (
     check_docker_connection,
     image_exists,
     process_pull_line,
 )
+from strix.telemetry import report_error
 
 
 logger = logging.getLogger(__name__)
 
 
+def _missing_web_search_vars(integrations: IntegrationSettings) -> list[str]:
+    """Mirror the web_search provider rules: which key(s) the selected provider needs."""
+    if integrations.web_search_provider == "exa":
+        return [] if integrations.exa_api_key else ["EXA_API_KEY"]
+    if integrations.web_search_provider == "perplexity":
+        return [] if integrations.perplexity_api_key else ["PERPLEXITY_API_KEY"]
+    if integrations.exa_api_key or integrations.perplexity_api_key:
+        return []
+    return ["EXA_API_KEY", "PERPLEXITY_API_KEY"]
+
+
 def validate_environment() -> None:
     logger.info("Validating environment")
     console = Console()
@@ -33,21 +45,11 @@ def validate_environment() -> None:
                 f"[red]STRIX_LLM={settings.llm.model} uses your ChatGPT subscription, "
                 "but you're not signed in.[/] Run [cyan]strix auth login chatgpt[/] first."
             )
+            report_error("subscription_not_signed_in")
             sys.exit(1)
         logger.info("Environment OK (ChatGPT subscription)")
         return
 
-    oc = opencode.subscription_model(settings.llm.model)
-    if oc:
-        if not opencode.is_authenticated():
-            console.print(
-                f"[red]STRIX_LLM={settings.llm.model} runs on {oc.label}, "
-                "but you're not signed in.[/] Run [cyan]strix auth login opencode[/] first."
-            )
-            sys.exit(1)
-        logger.info("Environment OK (%s)", oc.label)
-        return
-
     if not settings.llm.model:
         missing_required_vars.append("STRIX_LLM")
 
@@ -57,8 +59,7 @@ def validate_environment() -> None:
     if not settings.llm.api_base:
         missing_optional_vars.append("LLM_API_BASE")
 
-    if not settings.integrations.perplexity_api_key:
-        missing_optional_vars.append("PERPLEXITY_API_KEY")
+    missing_optional_vars.extend(_missing_web_search_vars(settings.integrations))
 
     if missing_required_vars:
         error_text = Text()
@@ -81,7 +82,7 @@ def validate_environment() -> None:
                 error_text.append("• ", style="white")
                 error_text.append("STRIX_LLM", style="bold cyan")
                 error_text.append(
-                    " - Model name to use (e.g., 'openai/gpt-5.4' or "
+                    " - Model name to use (e.g., 'openrouter/z-ai/glm-5.3' or "
                     "'anthropic/claude-opus-4-7')\n",
                     style="white",
                 )
@@ -100,7 +101,14 @@ def validate_environment() -> None:
                     error_text.append("• ", style="white")
                     error_text.append("PERPLEXITY_API_KEY", style="bold cyan")
                     error_text.append(
-                        " - API key for Perplexity AI web search (enables real-time research)\n",
+                        " - API key for Perplexity AI web search (alternative to Exa)\n",
+                        style="white",
+                    )
+                elif var == "EXA_API_KEY":
+                    error_text.append("• ", style="white")
+                    error_text.append("EXA_API_KEY", style="bold cyan")
+                    error_text.append(
+                        " - API key for Exa web search (enables real-time research)\n",
                         style="white",
                     )
                 elif var == "STRIX_REASONING_EFFORT":
@@ -113,7 +121,7 @@ def validate_environment() -> None:
                     )
 
         error_text.append("\nExample setup:\n", style="white")
-        error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")
+        error_text.append("export STRIX_LLM='openrouter/z-ai/glm-5.3'\n", style="dim white")
 
         if missing_optional_vars:
             for var in missing_optional_vars:
@@ -127,6 +135,8 @@ def validate_environment() -> None:
                     error_text.append(
                         "export PERPLEXITY_API_KEY='your-perplexity-key-here'\n", style="dim white"
                     )
+                elif var == "EXA_API_KEY":
+                    error_text.append("export EXA_API_KEY='your-exa-key-here'\n", style="dim white")
                 elif var == "STRIX_REASONING_EFFORT":
                     error_text.append(
                         "export STRIX_REASONING_EFFORT='high'\n",
@@ -145,6 +155,7 @@ def validate_environment() -> None:
         console.print("\n")
         console.print(panel)
         console.print()
+        report_error("missing_required_config")
         sys.exit(1)
     logger.info(
         "Environment OK (optional missing: %s)",
@@ -172,6 +183,7 @@ def check_docker_installed() -> None:
             padding=(1, 2),
         )
         console.print("\n", panel, "\n")
+        report_error("docker_not_installed")
         sys.exit(1)
     logger.debug("Docker CLI present")
 
@@ -219,6 +231,7 @@ def pull_docker_image() -> None:
                 padding=(1, 2),
             )
             console.print(panel, "\n")
+            report_error("image_pull_failed", e)
             sys.exit(1)
 
     logger.info("Docker image %s ready", image)

strix/interface/main.py

@@ -13,7 +13,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode, persist_current
+from strix.config import codex, load_settings, persist_current
 from strix.core.paths import run_dir_for
 from strix.interface.cli_args import parse_arguments
 from strix.interface.environment import (
@@ -41,7 +41,8 @@ from strix.interface.update_check import (
 from strix.interface.utils import (
     build_final_stats_text,
 )
-from strix.telemetry import posthog, scarf
+from strix.llm.warmup import start_import_warmup, wait_for_import_warmup
+from strix.telemetry import posthog, report_error, scarf, set_scan_phase
 from strix.telemetry.logging import configure_dependency_logging
 
 
@@ -62,6 +63,14 @@ import logging  # noqa: E402
 
 logger = logging.getLogger(__name__)
 
+_ROOT_SUBCOMMAND_HELP = """
+Additional commands:
+  strix cloud ...          Use the managed Strix platform
+  strix auth ...           Manage model-subscription sign-in
+  strix view [RUN]         View a completed or running scan
+  strix completions SHELL  Generate zsh, bash, or fish tab completion
+"""
+
 
 def _exception_messages(exc: BaseException) -> tuple[str, ...]:
     messages: list[str] = []
@@ -104,14 +113,8 @@ def _provider_import_hint(exc: BaseException, model: str) -> str | None:
 
 
 def _subscription_error_hint(exc: BaseException) -> str | None:
-    """Return an actionable hint for a known subscription error, or None."""
-    model = load_settings().llm.model
-    if opencode.subscription_model(model):
-        joined = " ".join(_exception_messages(exc)).lower()
-        if "error code: 401" in joined or "http 401" in joined or "unauthorized" in joined:
-            return "Your OpenCode API key was rejected. Sign in again:\n  strix auth login opencode"
-        return None
-    if not codex.subscription_model(model):
+    """Return an actionable hint for a known ChatGPT-subscription error, or None."""
+    if not codex.subscription_model(load_settings().llm.model):
         return None
     joined = " ".join(_exception_messages(exc)).lower()
     if "not supported when using codex with a chatgpt account" in joined:
@@ -330,6 +333,11 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
         "[#60a5fa]docs.strix.ai[/]  [dim]·[/]  "
         "[#60a5fa]discord.gg/strix-ai[/]"
     )
+    if not args.non_interactive:
+        console.print(
+            "[dim]Run a pentest in Strix Cloud[/]  [#60a5fa]app.strix.ai[/]  [dim]·[/]  "
+            "[dim]Enterprise[/]  [#60a5fa]strix.ai/demo[/]"
+        )
     console.print()
     if not args.non_interactive:
         notify_update(console)
@@ -389,22 +397,22 @@ def _print_model_connection_error(exc: BaseException, model_name: str) -> None:
 def _bootstrap_scan(args: argparse.Namespace) -> None:
     """Warm up the model and prepare the run for a non-interactive scan.
 
-    Interactive launches only validate the environment here; the model
-    preflight and run preparation happen inside the TUI so the interface
-    paints immediately instead of waiting on a model round trip.
+    Interactive launches skip this: the model preflight and run preparation
+    happen inside the TUI so the interface paints immediately instead of
+    waiting on a model round trip.
     """
-    validate_environment()
-    if not args.non_interactive:
-        return
+    set_scan_phase("preflight")
     try:
         asyncio.run(warm_up_llm(show_model_warning=True))
     except ModelConnectionError as exc:
+        report_error("model_connection_failed", exc)
         _print_model_connection_error(exc, exc.model_name)
         sys.exit(1)
     persist_current()
     try:
         prepare_run(args)
     except ValueError as e:
+        report_error("scan_preparation_failed", e)
         _print_error_panel("SCAN PREPARATION FAILED", str(e))
         sys.exit(1)
     telemetry_start(args)
@@ -416,6 +424,13 @@ def main() -> None:
     if sys.platform == "win32":
         asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
 
+    if len(sys.argv) == 2 and sys.argv[1] in ("-h", "--help"):
+        try:
+            parse_arguments()
+        except SystemExit as exc:
+            Console().print(_ROOT_SUBCOMMAND_HELP.strip(), markup=False)
+            raise SystemExit(exc.code) from None
+
     # `strix view [<run>]` is a viewer-only subcommand, dispatched before the
     # scan argument parser (which requires a target) and before any scan setup.
     if len(sys.argv) > 1 and sys.argv[1] == "view":
@@ -431,7 +446,18 @@ def main() -> None:
 
         sys.exit(run_auth(sys.argv[2:]))
 
-    from strix.llm.warmup import start_import_warmup
+    # Generate native shell completion scripts before scan argument parsing.
+    if len(sys.argv) > 1 and sys.argv[1] in ("completion", "completions"):
+        from strix.interface.completions import run_completions
+
+        sys.exit(run_completions(sys.argv[2:]))
+
+    # `strix cloud …` drives the managed platform (app.strix.ai) and exits;
+    # it needs no target, Docker, or scan setup.
+    if len(sys.argv) > 1 and sys.argv[1] == "cloud":
+        from strix.interface.cloud import run_cloud
+
+        sys.exit(run_cloud(sys.argv[2:]))
 
     start_import_warmup()
 
@@ -445,10 +471,12 @@ def main() -> None:
 
     check_docker_installed()
     pull_docker_image()
+    validate_environment()
 
-    # In setup mode the TUI collects the target, then runs prepare_run(),
-    # warm-up, and telemetry itself once the user starts the scan.
-    if not args.needs_setup:
+    # Everything below imports the scan engine; do not race the warm-up thread.
+    wait_for_import_warmup()
+
+    if args.non_interactive:
         _bootstrap_scan(args)
 
     from strix.report.state import get_global_report_state
@@ -459,18 +487,21 @@ def main() -> None:
             from strix.interface.cli import run_cli
 
             asyncio.run(run_cli(args))
+            # Headless runs have no user to quit: the agent either finished
+            # (already beaconed as finished_by_tool) or stopped on its own.
+            exit_reason = "agent_stopped"
         else:
             asyncio.run(run_tui(args))
     except InteractiveSetupUnavailableError as exc:
         exit_reason = "error"
+        report_error("interactive_setup_unavailable", exc)
         _print_error_panel("INTERACTIVE SETUP UNAVAILABLE", str(exc))
         sys.exit(1)
     except KeyboardInterrupt:
         exit_reason = "interrupted"
-    except Exception:
+    except Exception as exc:
         exit_reason = "error"
-        posthog.error("unhandled_exception")
-        scarf.error("unhandled_exception")
+        report_error("unhandled_exception", exc)
         raise
     finally:
         report_state = get_global_report_state()
@@ -489,6 +520,7 @@ def main() -> None:
 
     if not args.run_name:
         # Setup mode where the user quit before starting a scan: nothing ran.
+        notify_update(Console())
         return
 
     results_path = run_dir_for(args.run_name)

strix/interface/platform_cli.py

@@ -0,0 +1,798 @@
+"""`strix cloud login` — managed platform sign-in (app.strix.ai).
+
+Signing in runs an OAuth 2.0 device authorization flow in the browser, creates
+the Strix account and workspace when they do not exist yet, and stores a
+personal API token in ``~/.strix/platform-auth.json``. The token drives the
+managed REST API (scans, credits, top-ups) without a dashboard visit.
+"""
+
+from __future__ import annotations
+
+import argparse
+import contextlib
+import json
+import sys
+import time
+import webbrowser
+from pathlib import Path
+from typing import Any, NoReturn, cast
+from urllib.parse import urlparse, urlsplit, urlunsplit
+
+import requests
+from rich.console import Console
+from rich.markup import escape
+from rich.panel import Panel
+from rich.text import Text
+
+from strix.config import load_settings
+from strix.interface.platform_identity import read_or_create_identity
+from strix.interface.terminal_text import sanitize_terminal_text
+from strix.interface.url_safety import is_safe_web_url
+from strix.utils.secret_files import write_secret_text
+
+
+AUTH_PATH = Path.home() / ".strix" / "platform-auth.json"
+
+_HTTP_TIMEOUT_S = 30
+_DEFAULT_POLL_INTERVAL_S = 5
+_MAX_POLL_INTERVAL_S = 60
+_MAX_EXPIRES_IN_S = 30 * 60
+
+_ROLE_RANK = {"viewer": 0, "analyst": 1, "admin": 2}
+
+
+class PlatformAuthError(Exception):
+    """Raised when the device authorization flow fails."""
+
+
+class _SessionUsageError(Exception):
+    """A session subcommand received invalid arguments."""
+
+
+class _SessionArgumentParser(argparse.ArgumentParser):
+    def error(self, message: str) -> NoReturn:
+        raise _SessionUsageError(f"invalid arguments for {self.prog}: {message}")
+
+
+def _terminal_markup(value: object) -> str:
+    return escape(sanitize_terminal_text(value))
+
+
+def _app_url() -> str:
+    return load_settings().viewer.app_url.rstrip("/")
+
+
+def read_record() -> dict[str, Any] | None:
+    try:
+        data = json.loads(AUTH_PATH.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return None
+    if not isinstance(data, dict):
+        return None
+    record = cast("dict[str, Any]", data)
+    if not record.get("api_token"):
+        return None
+    return record
+
+
+def save_record(record: dict[str, Any]) -> None:
+    write_secret_text(AUTH_PATH, json.dumps(record, indent=2))
+
+
+def logout() -> bool:
+    try:
+        AUTH_PATH.unlink()
+    except FileNotFoundError:
+        return True
+    except OSError:
+        return False
+    return True
+
+
+def run_login(argv: list[str]) -> int:
+    """Entry point for ``strix cloud login``. Returns a process exit code."""
+    console = Console()
+    subcommand = argv[0] if argv else None
+
+    if subcommand == "status":
+        return _status(console, argv[1:])
+    if subcommand == "logout":
+        return _logout(console, argv[1:])
+    return _login(console, argv)
+
+
+def _login(console: Console, argv: list[str]) -> int:
+    parser = argparse.ArgumentParser(prog="strix cloud login", add_help=True)
+    parser.add_argument(
+        "--no-browser",
+        action="store_true",
+        help="Do not open the browser. Print the verification URL instead.",
+    )
+    scope_mode = parser.add_mutually_exclusive_group()
+    scope_mode.add_argument(
+        "--scopes",
+        nargs="+",
+        metavar="SCOPE",
+        default=None,
+        help=(
+            "API scopes for the token, for example scans:read billing:write. "
+            "The server always includes a minimum scope set. "
+            "Without this option, an interactive picker opens after the browser step."
+        ),
+    )
+    scope_mode.add_argument(
+        "--scope-profile",
+        choices=("minimal", "recommended", "full"),
+        default=None,
+        help="Scope profile to approve. Defaults to an interactive choice in a TTY.",
+    )
+    parser.add_argument(
+        "--device-name",
+        default=None,
+        metavar="NAME",
+        help="Privacy-safe label shown for this CLI session in the dashboard.",
+    )
+    parser.add_argument(
+        "--workspace",
+        metavar="WORKSPACE",
+        default=None,
+        help=(
+            "Workspace that receives the token, by ID or by exact name. "
+            "Without this option, an interactive picker opens when you have "
+            "more than one workspace."
+        ),
+    )
+    previous_record = read_record()
+    try:
+        args = parser.parse_args(argv)
+    except SystemExit as exc:  # argparse already printed the message
+        return exc.code if isinstance(exc.code, int) else 2
+
+    console.print()
+    host = urlparse(_app_url()).netloc or _app_url()
+    console.print(f"[bold]Signing in to the Strix platform[/] [dim]({_terminal_markup(host)})[/]")
+    console.print(
+        "[dim]This creates your account and workspace when needed, and stores an API token.[/]"
+    )
+    console.print()
+
+    try:
+        record = _run_device_flow(
+            console,
+            open_browser=not args.no_browser,
+            scopes=args.scopes,
+            scope_profile=args.scope_profile,
+            workspace=args.workspace,
+            device_name=args.device_name,
+        )
+    except PlatformAuthError as exc:
+        console.print(f"[red]Sign-in failed:[/] {_terminal_markup(exc)}")
+        return 1
+    except KeyboardInterrupt:
+        console.print("\n[yellow]Sign-in cancelled.[/]")
+        return 130
+
+    try:
+        save_record(record)
+    except OSError as exc:
+        console.print(
+            f"[red]Sign-in succeeded, but the token could not be stored:[/] {_terminal_markup(exc)}"
+        )
+        console.print(
+            f"[dim]Check that {_terminal_markup(AUTH_PATH.parent)} is writable, "
+            "then run `strix cloud login` again.[/]"
+        )
+        return 1
+    _revoke_replaced_legacy_session(previous_record, record)
+    _print_success(console, record)
+    return 0
+
+
+def _run_device_flow(  # noqa: PLR0912, PLR0915
+    console: Console,
+    *,
+    open_browser: bool,
+    scopes: list[str] | None = None,
+    scope_profile: str | None = None,
+    workspace: str | None = None,
+    device_name: str | None = None,
+) -> dict[str, Any]:
+    app_url = _app_url()
+    interactive = workspace is not None or (
+        sys.stdin.isatty() and scopes is None and scope_profile is None
+    )
+    try:
+        identity = read_or_create_identity(device_name=device_name)
+    except (OSError, ValueError) as exc:
+        raise PlatformAuthError(f"could not prepare the CLI device identity: {exc}") from exc
+
+    try:
+        response = requests.post(
+            f"{app_url}/api/v1/cli/login",
+            timeout=_HTTP_TIMEOUT_S,
+            allow_redirects=False,
+        )
+    except requests.RequestException as exc:
+        raise PlatformAuthError(f"could not reach {app_url}: {exc}") from exc
+    if not 200 <= response.status_code < 300:
+        raise PlatformAuthError(_error_detail(response))
+    authorization = _json_object(response)
+
+    user_code = str(authorization.get("user_code") or "")
+    verification_uri = str(
+        authorization.get("verification_uri_complete")
+        or authorization.get("verification_uri")
+        or ""
+    )
+    device_code = str(authorization.get("device_code") or "")
+    expires_in = _as_positive_int(
+        authorization.get("expires_in"), default=300, maximum=_MAX_EXPIRES_IN_S
+    )
+    interval = _as_positive_int(
+        authorization.get("interval"),
+        default=_DEFAULT_POLL_INTERVAL_S,
+        maximum=_MAX_POLL_INTERVAL_S,
+    )
+    if not device_code or not verification_uri:
+        raise PlatformAuthError("the server returned an incomplete device authorization")
+    if not is_safe_web_url(verification_uri, trusted_origin=app_url):
+        raise PlatformAuthError("the server returned an invalid verification URL")
+
+    console.print(
+        Panel.fit(
+            Text.assemble(
+                ("Confirmation code: ", "dim"),
+                (sanitize_terminal_text(user_code), "bold cyan"),
+            ),
+            title="Verify this device",
+        )
+    )
+    console.print("Open this URL in your browser and confirm the code:")
+    console.print(sanitize_terminal_text(verification_uri), markup=False, soft_wrap=True)
+
+    if open_browser:
+        with contextlib.suppress(Exception):
+            webbrowser.open(verification_uri)
+
+    console.print("[dim]Waiting for browser confirmation…[/]")
+
+    poll_body: dict[str, Any] = {"device_code": device_code, **identity}
+    if interactive:
+        poll_body["interactive"] = True
+    elif scopes:
+        poll_body["scopes"] = scopes
+    elif scope_profile:
+        poll_body["scope_profile"] = scope_profile
+
+    deadline = time.monotonic() + expires_in
+    while time.monotonic() < deadline:
+        remaining = deadline - time.monotonic()
+        if remaining <= 0:
+            break
+        time.sleep(min(interval, remaining))
+        try:
+            poll = requests.post(
+                f"{app_url}/api/v1/cli/login/poll",
+                json=poll_body,
+                timeout=_HTTP_TIMEOUT_S,
+                allow_redirects=False,
+            )
+        except requests.RequestException:
+            continue
+        if 200 <= poll.status_code < 300:
+            return _finish_login(
+                console,
+                app_url,
+                poll,
+                scopes=scopes,
+                scope_profile=scope_profile,
+                workspace=workspace,
+            )
+        delta = _handle_poll_error(poll)
+        if delta is None:
+            break
+        interval = min(interval + delta, _MAX_POLL_INTERVAL_S)
+
+    raise PlatformAuthError("the sign-in request expired. Run `strix cloud login` again.")
+
+
+def _handle_poll_error(poll: requests.Response) -> int | None:
+    """Return the interval increase, or None when the device code expired."""
+    error = ""
+    with contextlib.suppress(ValueError, AttributeError):
+        error = str(poll.json().get("error", ""))
+    if error == "authorization_pending":
+        return 0
+    if error == "slow_down":
+        return 5
+    if error == "access_denied":
+        raise PlatformAuthError("the sign-in request was denied in the browser")
+    if error == "expired_token":
+        return None
+    raise PlatformAuthError(_error_detail(poll))
+
+
+def _finish_login(
+    console: Console,
+    app_url: str,
+    poll: requests.Response,
+    *,
+    scopes: list[str] | None,
+    scope_profile: str | None,
+    workspace: str | None,
+) -> dict[str, Any]:
+    result = _json_object(poll)
+    if result.get("selection_required"):
+        return _complete_selection(
+            console,
+            app_url,
+            result,
+            scopes=scopes,
+            scope_profile=scope_profile,
+            workspace=workspace,
+        )
+    return _bind_login_record(_require_api_token(result), app_url)
+
+
+def _signed_in_record(
+    response: requests.Response,
+    *,
+    app_url: str,
+) -> dict[str, Any]:
+    return _bind_login_record(
+        _require_api_token(_json_object(response)),
+        app_url,
+    )
+
+
+def _require_api_token(record: dict[str, Any]) -> dict[str, Any]:
+    api_token = record.get("api_token")
+    if not isinstance(api_token, str) or not api_token.strip():
+        raise PlatformAuthError("the server returned a sign-in response without an API token")
+    return record
+
+
+def _bind_login_record(record: dict[str, Any], app_url: str) -> dict[str, Any]:
+    """Bind a stored credential to its issuer and preserve its scope preference."""
+    parsed = urlsplit(app_url)
+    if (
+        parsed.scheme not in {"http", "https"}
+        or not parsed.netloc
+        or parsed.username is not None
+        or parsed.password is not None
+        or parsed.query
+        or parsed.fragment
+        or "\\" in app_url
+        or any(character.isspace() for character in app_url)
+        or "%" in parsed.netloc
+    ):
+        raise PlatformAuthError("the configured platform URL is invalid")
+    bound = dict(record)
+    bound["app_url"] = urlunsplit(
+        (parsed.scheme.lower(), parsed.netloc.lower(), parsed.path.rstrip("/"), "", "")
+    )
+    preference: Any = record.get("requested_scopes", record.get("scopes"))
+    preference_items = cast("list[Any]", preference)
+    if isinstance(preference, list) and all(isinstance(scope, str) for scope in preference_items):
+        bound["requested_scopes"] = list(dict.fromkeys(cast("list[str]", preference_items)))
+    return bound
+
+
+def _complete_selection(
+    console: Console,
+    app_url: str,
+    selection: dict[str, Any],
+    *,
+    scopes: list[str] | None,
+    scope_profile: str | None,
+    workspace: str | None,
+) -> dict[str, Any]:
+    organizations = _dict_items(selection.get("organizations"))
+    catalog = _dict_items(selection.get("scopes"))
+    selection_token = str(selection.get("selection_token") or "")
+    if not selection_token or not organizations:
+        raise PlatformAuthError("the server returned an incomplete selection response")
+
+    chosen_org = _choose_workspace(console, organizations, workspace)
+    role = str(chosen_org.get("role") or "admin")
+    chosen_scopes = scopes
+    chosen_profile = scope_profile
+    if chosen_scopes is None and chosen_profile is None and sys.stdin.isatty():
+        chosen_profile, chosen_scopes = _choose_scopes(console, catalog, role)
+
+    body: dict[str, Any] = {
+        "selection_token": selection_token,
+        "organization_id": chosen_org.get("id"),
+    }
+    if chosen_scopes is not None:
+        body["scopes"] = chosen_scopes
+        body["scope_profile"] = "custom"
+    elif chosen_profile is not None:
+        body["scope_profile"] = chosen_profile
+    try:
+        response = requests.post(
+            f"{app_url}/api/v1/cli/login/complete",
+            json=body,
+            timeout=_HTTP_TIMEOUT_S,
+            allow_redirects=False,
+        )
+    except requests.RequestException as exc:
+        raise PlatformAuthError(f"could not reach {app_url}: {exc}") from exc
+    if not 200 <= response.status_code < 300:
+        raise PlatformAuthError(_error_detail(response))
+    return _signed_in_record(
+        response,
+        app_url=app_url,
+    )
+
+
+def _dict_items(value: Any) -> list[dict[str, Any]]:
+    if not isinstance(value, list):
+        return []
+    items = cast("list[Any]", cast("Any", value))
+    return [cast("dict[str, Any]", cast("Any", item)) for item in items if isinstance(item, dict)]
+
+
+def _choose_workspace(
+    console: Console, organizations: list[dict[str, Any]], workspace: str | None
+) -> dict[str, Any]:
+    if workspace is not None:
+        wanted = workspace.strip().casefold()
+        by_id = [org for org in organizations if str(org.get("id", "")).casefold() == wanted]
+        if by_id:
+            return by_id[0]
+        by_name = [
+            org for org in organizations if str(org.get("name", "")).strip().casefold() == wanted
+        ]
+        if len(by_name) == 1:
+            return by_name[0]
+        if len(by_name) > 1:
+            matching_ids = ", ".join(str(org.get("id", "")) for org in by_name)
+            raise PlatformAuthError(
+                f"multiple workspaces are named {workspace!r}; use an exact workspace ID: "
+                f"{matching_ids}"
+            )
+        names = ", ".join(str(org.get("name", "")) for org in organizations)
+        raise PlatformAuthError(f"no workspace matches {workspace!r}. Your workspaces: {names}")
+    if len(organizations) == 1:
+        return organizations[0]
+    if not sys.stdin.isatty():
+        choices = ", ".join(f"{org.get('name', '')} ({org.get('id', '')})" for org in organizations)
+        raise PlatformAuthError(
+            "more than one workspace is available; rerun with --workspace NAME_OR_ID. "
+            f"Available workspaces: {choices}"
+        )
+
+    console.print()
+    console.print("[bold]Select a workspace for the API token:[/]")
+    for index, org in enumerate(organizations, start=1):
+        name = _terminal_markup(org.get("name", ""))
+        org_role = _terminal_markup(org.get("role", ""))
+        console.print(f"  [cyan]{index}[/]. {name} [dim]({org_role})[/]")
+    while True:
+        answer = console.input(f"Workspace [1-{len(organizations)}] (1): ").strip() or "1"
+        if answer.isdigit() and 1 <= int(answer) <= len(organizations):
+            return organizations[int(answer) - 1]
+        console.print("[yellow]Enter a number from the list.[/]")
+
+
+def _choose_scopes(
+    console: Console, catalog: list[dict[str, Any]], role: str
+) -> tuple[str, list[str] | None]:
+    """Prompt for a named scope profile or a custom scope list."""
+    rank = _ROLE_RANK.get(role, 2)
+    allowed = [
+        item for item in catalog if _ROLE_RANK.get(str(item.get("min_role", "viewer")), 0) <= rank
+    ]
+    if not allowed:
+        return "recommended", None
+
+    console.print()
+    console.print("[bold]Select token scopes:[/]")
+    console.print(
+        "  [cyan]1[/]. Recommended [dim](scans, findings, schedules, assets, uploads, "
+        "workspace switching, billing/top-ups; no token creation)[/]"
+    )
+    console.print("  [cyan]2[/]. Full access [dim](every scope your role allows)[/]")
+    console.print("  [cyan]3[/]. Minimal [dim](scan read/write and billing read)[/]")
+    console.print("  [cyan]4[/]. Custom [dim](pick individual scopes)[/]")
+    while True:
+        answer = console.input("Scopes [1-4] (1): ").strip() or "1"
+        if answer == "1":
+            return "recommended", None
+        if answer == "2":
+            return "full", None
+        if answer == "3":
+            return "minimal", None
+        if answer == "4":
+            return "custom", _choose_custom_scopes(console, allowed)
+        console.print("[yellow]Enter a number from 1 to 4.[/]")
+
+
+def _choose_custom_scopes(console: Console, allowed: list[dict[str, Any]]) -> list[str]:
+    selected = {
+        str(item["scope"])
+        for item in allowed
+        if item.get("scope") and (item.get("default") or item.get("minimum"))
+    }
+    while True:
+        console.print()
+        for index, item in enumerate(allowed, start=1):
+            scope = str(item.get("scope", ""))
+            mark = "[green]x[/]" if scope in selected else " "
+            required = " [dim](always included)[/]" if item.get("minimum") else ""
+            rendered_scope = _terminal_markup(scope)
+            description = _terminal_markup(item.get("description", ""))
+            console.print(
+                f"  [{mark}] [cyan]{index:>2}[/]. {rendered_scope}{required}"
+                f"\n         [dim]{description}[/]"
+            )
+        answer = console.input(
+            "Toggle scopes by number (comma separated), or press Enter to confirm: "
+        ).strip()
+        if not answer:
+            return sorted(selected)
+        for part in answer.replace(",", " ").split():
+            if not part.isdigit() or not 1 <= int(part) <= len(allowed):
+                console.print(
+                    f"[yellow]Ignored {_terminal_markup(part)!r}: not a number from the list.[/]"
+                )
+                continue
+            item = allowed[int(part) - 1]
+            scope = str(item.get("scope", ""))
+            if item.get("minimum"):
+                console.print(f"[yellow]{_terminal_markup(scope)} is always included.[/]")
+                continue
+            if scope in selected:
+                selected.discard(scope)
+            else:
+                selected.add(scope)
+
+
+def _json_object(response: requests.Response) -> dict[str, Any]:
+    try:
+        data = response.json()
+    except ValueError as exc:
+        raise PlatformAuthError("the server returned a response that is not JSON") from exc
+    if not isinstance(data, dict):
+        raise PlatformAuthError("the server returned an unexpected response shape")
+    return cast("dict[str, Any]", data)
+
+
+def _as_positive_int(value: Any, *, default: int, maximum: int) -> int:
+    try:
+        parsed = int(value)
+    except (TypeError, ValueError, OverflowError):
+        return default
+    if parsed <= 0:
+        return default
+    return min(parsed, maximum)
+
+
+def _error_detail(response: requests.Response) -> str:
+    with contextlib.suppress(ValueError, AttributeError):
+        detail = response.json().get("detail")
+        if detail:
+            return str(detail)
+    return f"HTTP {response.status_code}"
+
+
+def _session_headers(record: dict[str, Any]) -> dict[str, str]:
+    headers = {"Authorization": f"Bearer {record['api_token']}"}
+    workspace_id = record.get("organization_id")
+    if isinstance(workspace_id, str) and workspace_id:
+        headers["X-Strix-Workspace"] = workspace_id
+    return headers
+
+
+def _revoke_stored_session(record: dict[str, Any]) -> tuple[bool, str | None]:
+    """Revoke one server session; return (definitively_inactive, error)."""
+    app_url = record.get("app_url")
+    if not isinstance(app_url, str) or not app_url:
+        return False, (
+            "the stored sign-in has no trusted platform URL; use --local-only to remove it"
+        )
+    try:
+        response = requests.delete(
+            f"{app_url.rstrip('/')}/api/v1/cli/session",
+            headers=_session_headers(record),
+            timeout=_HTTP_TIMEOUT_S,
+            allow_redirects=False,
+        )
+    except requests.RequestException as exc:
+        return False, f"could not revoke the remote CLI session: {exc}"
+    if response.status_code in {200, 204, 401}:
+        return True, None
+    return False, f"could not revoke the remote CLI session: {_error_detail(response)}"
+
+
+def _print_logout_failure(console: Console, message: str, *, as_json: bool) -> int:
+    if as_json:
+        sys.stdout.write(json.dumps({"error": message, "removed": False}) + "\n")
+    else:
+        console.print(f"[red]Sign-out failed:[/] {_terminal_markup(message)}")
+        console.print("[dim]The local token was kept so you can safely retry.[/]")
+    return 1
+
+
+def _revoke_replaced_legacy_session(
+    previous: dict[str, Any] | None, current: dict[str, Any]
+) -> None:
+    """Best-effort cleanup when the first device-aware login replaces a legacy token."""
+    if not previous or previous.get("api_token") == current.get("api_token"):
+        return
+    if previous.get("app_url") != current.get("app_url"):
+        return
+    with contextlib.suppress(KeyError, requests.RequestException):
+        requests.delete(
+            f"{previous['app_url']}/api/v1/cli/session",
+            headers=_session_headers(previous),
+            timeout=_HTTP_TIMEOUT_S,
+            allow_redirects=False,
+        )
+
+
+def _print_success(console: Console, record: dict[str, Any]) -> None:
+    email = record.get("email", "")
+    organization = record.get("organization_name") or record.get("organization_id", "")
+    console.print()
+    console.print("[green]✓ Signed in to the Strix platform.[/]")
+    if email:
+        console.print(f"  Account:   [bold]{_terminal_markup(email)}[/]")
+    if organization:
+        console.print(f"  Workspace: [bold]{_terminal_markup(organization)}[/]")
+    scopes = record.get("scopes")
+    if isinstance(scopes, list) and scopes:
+        console.print(f"  Access:    [dim]{_terminal_markup(_scope_summary(record))}[/]")
+    console.print(f"  Token:     stored in [dim]{_terminal_markup(AUTH_PATH)}[/]")
+    console.print()
+    console.print(
+        "[dim]The managed platform is ready. Run `strix cloud` to list the commands. "
+        "See https://docs.app.strix.ai for the API reference.[/]"
+    )
+
+
+def _status(console: Console, argv: list[str]) -> int:  # noqa: PLR0912
+    parser = _SessionArgumentParser(
+        prog="strix cloud whoami",
+        description="Show the stored managed-platform account, workspace, scopes, and expiry.",
+    )
+    parser.add_argument("--json", action="store_true", help="Print the session as JSON.")
+    parser.add_argument("--show-scopes", action="store_true", help="Print every granted scope.")
+    as_json = "--json" in argv or not sys.stdout.isatty()
+    try:
+        args = parser.parse_args(argv)
+    except _SessionUsageError as exc:
+        if as_json:
+            sys.stdout.write(json.dumps({"error": str(exc)}) + "\n")
+        else:
+            console.print(f"[red]Error:[/] {_terminal_markup(exc)}")
+        return 2
+    except SystemExit as exc:
+        return exc.code if isinstance(exc.code, int) else 2
+
+    as_json = bool(args.json) or not sys.stdout.isatty()
+    record = read_record()
+    if record is None:
+        if as_json:
+            sys.stdout.write(json.dumps({"signed_in": False, "error": "Not signed in"}) + "\n")
+            return 1
+        console.print("[yellow]Not signed in.[/] Run [bold]strix cloud login[/] to sign in.")
+        return 1
+    email = record.get("email", "unknown")
+    organization = record.get("organization_name") or record.get("organization_id", "")
+    expires_at = record.get("expires_at", "")
+    if as_json:
+        payload = {
+            "signed_in": True,
+            "email": email,
+            "organization_id": record.get("organization_id"),
+            "organization_name": record.get("organization_name"),
+            "scopes": record.get("scopes", []),
+            "expires_at": expires_at or None,
+            **({"app_url": record["app_url"]} if record.get("app_url") else {}),
+        }
+        sys.stdout.write(json.dumps(payload, indent=2, default=str) + "\n")
+        return 0
+    console.print(f"[green]Signed in[/] as [bold]{_terminal_markup(email)}[/]")
+    if organization:
+        console.print(f"  Workspace: {_terminal_markup(organization)}")
+    if expires_at:
+        console.print(f"  Token expires: {_terminal_markup(expires_at)}")
+    if record.get("app_url"):
+        console.print(f"  Platform: {_terminal_markup(record['app_url'])}")
+    scopes = record.get("scopes")
+    if isinstance(scopes, list) and scopes:
+        scope_items = cast("list[Any]", cast("Any", scopes))
+        if args.show_scopes:
+            console.print(
+                f"  Scopes: {_terminal_markup(' '.join(str(scope) for scope in scope_items))}"
+            )
+        else:
+            console.print(f"  Access: {_terminal_markup(_scope_summary(record))}")
+    return 0
+
+
+def _scope_summary(record: dict[str, Any]) -> str:
+    scopes = record.get("scopes")
+    scope_items = cast("list[Any]", cast("Any", scopes)) if isinstance(scopes, list) else []
+    count = len(scope_items)
+    profile = str(record.get("scope_profile") or "custom").replace("_", " ").title()
+    return f"{profile} · {count} scope{'s' if count != 1 else ''} granted"
+
+
+def _logout(console: Console, argv: list[str]) -> int:  # noqa: PLR0911, PLR0912
+    parser = _SessionArgumentParser(
+        prog="strix cloud logout",
+        description="Revoke this CLI session and remove its token from this machine.",
+    )
+    parser.add_argument("--json", action="store_true", help="Print the result as JSON.")
+    parser.add_argument(
+        "--local-only",
+        action="store_true",
+        help="Remove only the local token, leaving the remote session active.",
+    )
+    as_json = "--json" in argv or not sys.stdout.isatty()
+    try:
+        args = parser.parse_args(argv)
+    except _SessionUsageError as exc:
+        if as_json:
+            sys.stdout.write(json.dumps({"error": str(exc)}) + "\n")
+        else:
+            console.print(f"[red]Error:[/] {_terminal_markup(exc)}")
+        return 2
+    except SystemExit as exc:
+        return exc.code if isinstance(exc.code, int) else 2
+    as_json = bool(args.json) or not sys.stdout.isatty()
+    if read_record() is None and not AUTH_PATH.exists():
+        if as_json:
+            sys.stdout.write(json.dumps({"signed_in": False, "removed": False}) + "\n")
+            return 0
+        console.print("[yellow]Not signed in.[/]")
+        return 0
+    record = read_record()
+    remotely_revoked = False
+    if record is not None and not args.local_only:
+        remotely_revoked, revoke_error = _revoke_stored_session(record)
+        if revoke_error:
+            return _print_logout_failure(console, revoke_error, as_json=as_json)
+
+    if not logout():
+        if as_json:
+            sys.stdout.write(
+                json.dumps(
+                    {
+                        "error": "Could not remove the stored API token",
+                        "signed_in": True,
+                        "removed": False,
+                    }
+                )
+                + "\n"
+            )
+            return 1
+        console.print(
+            f"[red]Could not remove the stored API token.[/] Delete "
+            f"{_terminal_markup(AUTH_PATH)} manually."
+        )
+        return 1
+    if as_json:
+        sys.stdout.write(
+            json.dumps(
+                {
+                    "signed_in": False,
+                    "removed": True,
+                    "remotely_revoked": remotely_revoked,
+                    "local_only": bool(args.local_only),
+                }
+            )
+            + "\n"
+        )
+        return 0
+    if args.local_only:
+        console.print(
+            "[yellow]Local sign-out only.[/] The remote CLI session is still active; "
+            "revoke it from API Access if needed."
+        )
+    else:
+        console.print("[green]Signed out.[/] The CLI session was revoked and removed locally.")
+    return 0

strix/interface/platform_identity.py

@@ -0,0 +1,46 @@
+"""Stable, privacy-safe identity for this Strix CLI installation."""
+
+from __future__ import annotations
+
+import json
+import platform
+from pathlib import Path
+from typing import Any, cast
+from uuid import uuid4
+
+from strix.utils.secret_files import write_secret_text
+
+
+IDENTITY_PATH = Path.home() / ".strix" / "cli-identity.json"
+
+
+def _default_device_name(instance_id: str) -> str:
+    system = {"Darwin": "macOS", "Windows": "Windows", "Linux": "Linux"}.get(
+        platform.system(), "Computer"
+    )
+    return f"{system} CLI · {instance_id[:8]}"
+
+
+def read_or_create_identity(*, device_name: str | None = None) -> dict[str, str]:
+    """Return one installation ID, optionally updating its user-facing label."""
+    record: dict[str, Any] = {}
+    try:
+        raw = json.loads(IDENTITY_PATH.read_text(encoding="utf-8"))
+        if isinstance(raw, dict):
+            record = cast("dict[str, Any]", raw)
+    except (OSError, json.JSONDecodeError):
+        pass
+
+    instance_id = record.get("client_instance_id")
+    if not isinstance(instance_id, str) or len(instance_id) < 8:
+        instance_id = str(uuid4())
+    label = device_name.strip() if device_name is not None else record.get("device_name")
+    if not isinstance(label, str) or not label.strip():
+        label = _default_device_name(instance_id)
+    label = " ".join(label.split())
+    if not 1 <= len(label) <= 80:
+        raise ValueError("device name must be 1-80 printable characters")
+
+    identity = {"client_instance_id": instance_id, "device_name": label}
+    write_secret_text(IDENTITY_PATH, json.dumps(identity, indent=2))
+    return identity

strix/interface/scan_setup.py

@@ -14,7 +14,7 @@ import logging
 from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any
 
-from strix.config import Settings, load_settings, opencode
+from strix.config import Settings, codex, load_settings
 from strix.core.paths import run_dir_for
 from strix.interface.utils import (
     assign_workspace_subdirs,
@@ -226,7 +226,7 @@ def telemetry_start(args: argparse.Namespace) -> None:
     model = load_settings().llm.model
     kwargs = {
         "model": model,
-        "auth_mode": opencode.auth_mode(model),
+        "auth_mode": codex.auth_mode(model),
         "scan_mode": args.scan_mode,
         "is_whitebox": is_whitebox_scan(args.targets_info),
         "interactive": not args.non_interactive,
@@ -247,8 +247,7 @@ def _persist_run_record(args: argparse.Namespace) -> None:
         "status": "running",
         "start_time": datetime.now(UTC).isoformat(),
         "end_time": None,
-        "auth_mode": opencode.auth_mode(load_settings().llm.model),
-        "subscription_provider": opencode.subscription_provider(load_settings().llm.model),
+        "auth_mode": codex.auth_mode(load_settings().llm.model),
         "targets_info": args.targets_info,
         "scan_mode": args.scan_mode,
         "instruction": args.instruction,

strix/interface/terminal_text.py

@@ -0,0 +1,21 @@
+"""Safe rendering of untrusted text in a terminal."""
+
+from __future__ import annotations
+
+import re
+
+
+_TERMINAL_CONTROL = re.compile(r"[\x00-\x1f\x7f-\x9f]")
+
+
+def has_terminal_control(value: object) -> bool:
+    """Return whether text contains bytes that can alter terminal state/protocols."""
+    return _TERMINAL_CONTROL.search(str(value)) is not None
+
+
+def sanitize_terminal_text(value: object) -> str:
+    """Make C0/C1 control bytes visible so they cannot operate a terminal."""
+    return _TERMINAL_CONTROL.sub(
+        lambda match: f"\\x{ord(match.group()):02x}",
+        str(value),
+    )

strix/interface/tui/backend/controller.py

@@ -24,7 +24,7 @@ from strix.interface.tui.backend.projection import (
     sanitize_terminal_text,
     terminal_projection,
 )
-from strix.interface.utils import is_subscription_run, subscription_label
+from strix.interface.utils import is_subscription_run
 
 
 if TYPE_CHECKING:
@@ -36,7 +36,8 @@ if TYPE_CHECKING:
 _STOPPABLE_AGENT_STATUSES = frozenset({"running", "waiting", "budget_paused"})
 
 ChangeCallback = Callable[[], None]
-StartCallback = Callable[[bool], Awaitable[None]]
+StartCallback = Callable[[], Awaitable[None]]
+VerifyCallback = Callable[[], Awaitable[None]]
 QuitCallback = Callable[[], Awaitable[None]]
 
 
@@ -51,6 +52,7 @@ class TuiController:
         coordinator: Any = None,
         report_state: ReportState | None = None,
         on_start: StartCallback | None = None,
+        on_verify: VerifyCallback | None = None,
         on_quit: QuitCallback | None = None,
         on_change: ChangeCallback | None = None,
     ) -> None:
@@ -99,7 +101,6 @@ class TuiController:
         # A target-less launch enters the live view and asks there before
         # anything is prepared; this holds the directory awaiting that answer.
         self.pending_workspace_mount: str | None = None
-        self._pending_verify = True
         self.messages: list[dict[str, str]] = []
         self._next_message_id = 1
         self.error: str | None = None
@@ -112,6 +113,7 @@ class TuiController:
         self.viewer_url: str | None = None
         self._viewer_httpd: Any = None
         self._on_start = on_start
+        self._on_verify = on_verify
         self._on_quit = on_quit
         self._on_change = on_change
 
@@ -187,14 +189,10 @@ class TuiController:
         subscription = False
         with contextlib.suppress(Exception):
             subscription = is_subscription_run(self.report_state)
-        label = ""
-        if subscription:
-            with contextlib.suppress(Exception):
-                label = subscription_label()
         model_warning = ""
         if model and not is_recommended_or_frontier_model(model):
             model_warning = (
-                f"{model} is not a recommended frontier model; pentest quality could be degraded"
+                f"{model} is not a recommended frontier model. Pentest quality could be degraded."
             )
         state = {
             "setup_mode": self.setup_mode,
@@ -227,7 +225,6 @@ class TuiController:
             ],
             "usage": terminal_projection(usage, max_string=256, max_items=20),
             "subscription": subscription,
-            "subscription_label": label,
             "connections": [
                 {
                     "name": terminal_projection(entry["name"], max_string=64),
@@ -333,12 +330,6 @@ class TuiController:
     async def _start(self, payload: dict[str, Any]) -> dict[str, Any]:
         if self.scan_started or self._start_in_progress:
             raise RuntimeError("Scan is already starting or running")
-        # A bare prompt launches optimistically, like a coding agent: it skips
-        # the network model preflight and surfaces any model error live. A named
-        # target keeps the preflight so a real scan does not commit blind.
-        verify = payload.get("verify", True)
-        if not isinstance(verify, bool):
-            raise TypeError("verify must be a boolean")
         # Launching with no target mounts the working directory, so it requires
         # the user's explicit confirmation rather than happening silently.
         mount_working_dir = payload.get("mount_working_dir", False)
@@ -349,27 +340,44 @@ class TuiController:
             raise ValueError("No model configured. Set STRIX_LLM first.")
         if self._on_start is None:
             raise RuntimeError("Scan start is unavailable")
+        if not self.targets and not mount_working_dir:
+            raise ValueError("No target set. Add a target first.")
+        # The model check runs while still on the start screen, for a bare
+        # prompt as much as for a named target, so a failure lands in the setup
+        # log where the user can fix it and retry rather than in a dead run.
+        await self._verify_model()
         if not self.targets:
-            if not mount_working_dir:
-                raise ValueError("No target set. Add a target first.")
             # Mounting the working directory needs the user's confirmation, and
             # that is asked in the live view. Enter it now and prepare nothing
             # until the answer arrives, so declining leaves no run behind.
             self.pending_workspace_mount = str(Path.cwd())
-            self._pending_verify = verify
             self.setup_mode = False
             self.scan_started = True
             self.scan_state = "preparing"
             return {"started": True}
-        await self._begin_scan(verify)
+        await self._begin_scan()
         return {"started": True}
 
-    async def _begin_scan(self, verify: bool) -> None:
+    async def _verify_model(self) -> None:
+        if self._on_verify is None:
+            return
+        self._start_in_progress = True
+        try:
+            await self._on_verify()
+        finally:
+            self._start_in_progress = False
+
+    async def _begin_scan(self) -> None:
         if self._on_start is None:
             raise RuntimeError("Scan start is unavailable")
         self._start_in_progress = True
         try:
-            await self._on_start(verify)
+            await self._on_start()
+        except Exception as exc:
+            if not self.setup_mode:
+                # The live view is already up, so the failure has to show there.
+                self.fail_preparation(str(exc))
+            raise
         finally:
             self._start_in_progress = False
         self.setup_mode = False
@@ -389,7 +397,7 @@ class TuiController:
         # the whole of the input either way; the working directory is only an
         # extra the agent may look at, so the run goes ahead without one.
         self.workspace_mount = mount if approved else None
-        await self._begin_scan(self._pending_verify)
+        await self._begin_scan()
         return {"approved": approved}
 
     async def _send_message(self, payload: dict[str, Any]) -> dict[str, Any]:

strix/interface/tui/internal/app/model_test.go

@@ -370,6 +370,17 @@ func TestStartedSnapshotTransitionsToLiveView(t *testing.T) {
 	}
 }
 
+func TestSplashModelWarningRendersTheBackendSentenceOnce(t *testing.T) {
+	warning := "openai/glm-5.3 is not a recommended frontier model. Pentest quality could be degraded."
+	got := ansi.Strip(splashModelWarning("openai/glm-5.3", warning))
+	if got != "⚠ "+warning {
+		t.Fatalf("splash warning = %q, want %q", got, "⚠ "+warning)
+	}
+	if got := ansi.Strip(splashModelWarning("other/model", warning)); got != "⚠ "+warning {
+		t.Fatalf("splash warning with unrelated model = %q", got)
+	}
+}
+
 func TestSetupStartScreenFitsNarrowTerminal(t *testing.T) {
 	model := New(nil)
 	model.width, model.height = 40, 18

strix/interface/tui/internal/app/setup.go

@@ -45,23 +45,20 @@ func (m *Model) submitSetupPrompt(value string) (tea.Model, tea.Cmd) {
 	if len(fields) > targets {
 		commands = append(commands, send(m.client, "setup.set_instruction", map[string]any{"instruction": value}))
 	}
-	// With a target, verify the model connection before the scan commits to it.
-	// A bare prompt launches optimistically, like a coding agent, and mounts the
-	// working directory - the backend asks about that from the live view, so the
-	// prompt is held here in case it is declined.
-	verify := targets > 0 || len(m.snapshot.Targets) > 0
-	payload := map[string]any{"verify": verify}
-	if verify {
-		m.setupMsg("Verifying model connection...", render.Col(amber))
-	} else {
+	// The backend verifies the model connection before either kind of launch
+	// and reports on it through the setup log. A bare prompt mounts the working
+	// directory - the backend asks about that from the live view, so the prompt
+	// is held here in case it is declined.
+	payload := map[string]any{}
+	if targets == 0 && len(m.snapshot.Targets) == 0 {
 		m.pendingPrompt = value
 		payload["mount_working_dir"] = true
 	}
 	commands = append(commands, send(m.client, "setup.start", payload))
 	// Ordered, not batched: setup.start leaves setup mode, so it must be the
-	// last command to reach the backend. Batched sends race, and once the
-	// preflight is skipped setup.start wins, making the target and instruction
-	// commands land after the guard closes and fail with a red error.
+	// last command to reach the backend. Batched sends race, and if setup.start
+	// wins the target and instruction commands land after the guard closes and
+	// fail with a red error.
 	return *m, tea.Sequence(commands...)
 }
 

strix/interface/tui/internal/app/setup_prompt_test.go

@@ -94,25 +94,6 @@ func commandTypes(envelopes []protocol.Envelope) []string {
 	return types
 }
 
-// startVerify returns the verify flag on the setup.start command, and whether
-// a setup.start command was present at all.
-func startVerify(t *testing.T, envelopes []protocol.Envelope) (verify, found bool) {
-	t.Helper()
-	for _, envelope := range envelopes {
-		if envelope.Type != "setup.start" {
-			continue
-		}
-		var payload struct {
-			Verify bool `json:"verify"`
-		}
-		if err := json.Unmarshal(envelope.Payload, &payload); err != nil {
-			t.Fatal(err)
-		}
-		return payload.Verify, true
-	}
-	return false, false
-}
-
 func contains(values []string, want string) bool {
 	for _, value := range values {
 		if value == want {
@@ -160,10 +141,6 @@ func TestSetupPromptWithoutTargetLaunchesAndRequestsMount(t *testing.T) {
 	if mount, found := startPayloadFlag(t, envelopes, "mount_working_dir"); !found || !mount {
 		t.Fatalf("mount was not requested: mount_working_dir=%v found=%v", mount, found)
 	}
-	// A bare prompt launches optimistically: no model preflight.
-	if verify, found := startVerify(t, envelopes); !found || verify {
-		t.Fatalf("bare prompt should launch with verify=false, got verify=%v found=%v", verify, found)
-	}
 	// setup.start leaves setup mode, so it must be the last command sent.
 	if start, instr := firstIndex(types, "setup.start"), lastIndex(types, "setup.set_instruction"); start < instr {
 		t.Fatalf("setup.start (%d) must come after setup.set_instruction (%d): %v", start, instr, types)
@@ -273,9 +250,8 @@ func TestSetupPromptWithTargetLaunches(t *testing.T) {
 			t.Fatalf("missing %s in %v", want, types)
 		}
 	}
-	// A named target keeps the upfront model check.
-	if verify, found := startVerify(t, envelopes); !found || !verify {
-		t.Fatalf("targeted prompt should launch with verify=true, got verify=%v found=%v", verify, found)
+	if _, found := startPayloadFlag(t, envelopes, "mount_working_dir"); found {
+		t.Fatalf("a targeted prompt must not ask to mount the working directory: %v", types)
 	}
 	// The target and instruction must reach the backend before setup.start
 	// closes the setup guard.

strix/interface/tui/internal/app/view.go

@@ -411,7 +411,7 @@ func (m Model) splashView() string {
 		welcome + "\n" + version + "\n" + tagline + "\n\n" +
 		start.String() + "\n\n" + url
 	if warn := m.snapshot.ModelWarning; warn != "" {
-		content += "\n\n" + splashModelWarning(warn)
+		content += "\n\n" + splashModelWarning(m.snapshot.Model, warn)
 	}
 	panel := lipgloss.NewStyle().Border(lipgloss.RoundedBorder()).BorderForeground(green).Padding(1, 6).Align(lipgloss.Center).Render(content)
 	// #splash_screen background is solid black.
@@ -419,12 +419,16 @@ func (m Model) splashView() string {
 		lipgloss.WithWhitespaceBackground(black))
 }
 
-// splashModelWarning ports SplashScreen._build_model_warning_text.
-func splashModelWarning(model string) string {
+// splashModelWarning renders the backend's full warning sentence, with the
+// model name highlighted when the sentence leads with it.
+func splashModelWarning(model, warning string) string {
 	yellow := lipgloss.Color("#eab308")
-	return lipgloss.NewStyle().Bold(true).Foreground(yellow).Render("⚠ ") +
-		lipgloss.NewStyle().Bold(true).Foreground(render.Cyan).Render(model) +
-		lipgloss.NewStyle().Foreground(yellow).Render(" is not a recommended frontier model - pentest quality could be degraded")
+	out := lipgloss.NewStyle().Bold(true).Foreground(yellow).Render("⚠ ")
+	if model != "" && strings.HasPrefix(warning, model) {
+		out += lipgloss.NewStyle().Bold(true).Foreground(render.Cyan).Render(model)
+		warning = strings.TrimPrefix(warning, model)
+	}
+	return out + lipgloss.NewStyle().Foreground(yellow).Render(warning)
 }
 
 // chatPaneKey identifies everything the bordered trace depends on.
@@ -617,11 +621,7 @@ func (m Model) statsView() string {
 		if b.Len() > 0 {
 			b.WriteString("\n")
 		}
-		label := m.snapshot.SubscriptionLabel
-		if label == "" {
-			label = "ChatGPT subscription"
-		}
-		b.WriteString(lipgloss.NewStyle().Foreground(green).Render(label))
+		b.WriteString(lipgloss.NewStyle().Foreground(green).Render("ChatGPT subscription"))
 	}
 	total := numberValue(m.snapshot.Usage["total_tokens"])
 	if total > 0 {

strix/interface/tui/internal/protocol/protocol.go

@@ -79,7 +79,6 @@ type Snapshot struct {
 	Vulnerabilities     []map[string]any `json:"-"`
 	Usage               map[string]any   `json:"usage"`
 	Subscription        bool             `json:"subscription"`
-	SubscriptionLabel   string           `json:"subscription_label"`
 	Connections         []Connection     `json:"connections"`
 	ViewerStatus        string           `json:"viewer_status"`
 	ViewerURL           *string          `json:"viewer_url"`

strix/interface/tui/internal/render/coverage_test.go

@@ -194,3 +194,28 @@ func TestVulnerabilityReportRendersCalibrationFields(t *testing.T) {
 		"Fix Verification", "bypass review reasoned only",
 	)
 }
+
+func TestVulnerabilityReportUpdateRendersReportAndReason(t *testing.T) {
+	out := ansi.Strip(Tool(tool("update_vulnerability_report",
+		map[string]any{
+			"report_id":       "vuln-0009",
+			"update_reason":   "built a working unauthenticated file write against the endpoint",
+			"poc_script_code": "curl -X PATCH https://target/files/uuid",
+		},
+		map[string]any{
+			"success":        true,
+			"action":         "updated",
+			"report_id":      "vuln-0009",
+			"severity":       "critical",
+			"cvss_score":     9.3,
+			"updated_fields": []any{"poc_script_code"},
+		},
+		"completed")))
+	requireContains(t, out,
+		"Vulnerability Report Updated",
+		"vuln-0009",
+		"built a working unauthenticated file write",
+		"CRITICAL",
+		"9.3",
+	)
+}

strix/interface/tui/internal/render/registry.go

@@ -84,6 +84,8 @@ func Tool(data map[string]any) string {
 		return renderViewImage(args, result)
 	case "create_vulnerability_report":
 		return renderVulnerabilityReport(args, result)
+	case "update_vulnerability_report":
+		return renderVulnerabilityReportUpdate(args, result)
 	case "create_dependency_report":
 		return renderDependencyReport(args, result)
 	case "list_reports":

strix/interface/tui/internal/render/report.go

@@ -12,15 +12,27 @@ import (
 // ---------------------------------------------------------------------------
 
 func renderVulnerabilityReport(args map[string]any, result any) string {
+	return renderReport(args, result, "Vulnerability Report", "Creating report...")
+}
+
+// A revision names the report it changes and carries only the fields it
+// replaces, so it renders the same sections with the ones it left alone absent.
+func renderVulnerabilityReportUpdate(args map[string]any, result any) string {
+	return renderReport(args, result, "Vulnerability Report Updated", "Updating report...")
+}
+
+func renderReport(args map[string]any, result any, heading, pending string) string {
 	resultMap, _ := result.(map[string]any)
 	var b strings.Builder
-	b.WriteString("🐞 " + Bold(ReportHdr).Render("Vulnerability Report"))
+	b.WriteString("🐞 " + Bold(ReportHdr).Render(heading))
 
 	field := func(label, value string) {
 		if value != "" {
 			b.WriteString("\n\n" + Bold(Field).Render(label+": ") + value)
 		}
 	}
+	reportID := StringValue(args["report_id"])
+	field("Report", reportID)
 	title := StringValue(args["title"])
 	field("Title", title)
 
@@ -59,6 +71,7 @@ func renderVulnerabilityReport(args map[string]any, result any) string {
 		}
 	}
 
+	section("Reason", StringValue(args["update_reason"]))
 	section("Description", StringValue(args["description"]))
 	section("Impact", StringValue(args["impact"]))
 	section("Technical Analysis", StringValue(args["technical_analysis"]))
@@ -76,8 +89,8 @@ func renderVulnerabilityReport(args map[string]any, result any) string {
 	// was verified belongs next to it rather than in the artifact alone.
 	section("Fix Verification", StringValue(args["fix_verification"]))
 
-	if title == "" {
-		b.WriteString("\n  " + Dim().Render("Creating report..."))
+	if title == "" && reportID == "" {
+		b.WriteString("\n  " + Dim().Render(pending))
 	}
 	return "\n\n" + b.String() + "\n\n"
 }

strix/interface/tui/runtime.py

@@ -37,6 +37,7 @@ from strix.interface.tui.sidecar import (
 )
 from strix.interface.utils import read_workspace_files
 from strix.report.state import ReportState, set_global_report_state
+from strix.telemetry import report_error, set_scan_phase
 from strix.utils.resource_paths import get_strix_resource_path
 
 
@@ -48,6 +49,11 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
+def _revision_count(report: dict[str, Any]) -> int:
+    history = report.get("update_history")
+    return len(history) if isinstance(history, list) else 0
+
+
 class GoTuiPreActivationError(RuntimeError):
     """A sidecar failure raised before the Go TUI activates."""
 
@@ -63,11 +69,14 @@ class GoTuiRuntime:
         self.scan_error: BaseException | None = None
         self._last_sync_fingerprint = ""
         self._error_noted_agents: set[str] = set()
+        self.model_verified = False
+        self._setup_preflight: asyncio.Task[None] | None = None
         self.controller = TuiController(
             args,
             live_view=self.live_view,
             coordinator=self.coordinator,
             on_start=self.start_from_setup,
+            on_verify=self.ensure_model_verified,
             on_quit=self.quit,
         )
         self.server = TuiBackendServer(self.controller)
@@ -102,9 +111,58 @@ class GoTuiRuntime:
         self.report_state.vulnerability_found_callback = lambda _report: (
             self.controller.notify_changed()
         )
+        self.report_state.vulnerability_updated_callback = lambda _report: (
+            self.controller.notify_changed()
+        )
         self.controller.notify_changed()
 
-    async def start_from_setup(self, verify: bool = True) -> None:
+    async def check_setup_model(self) -> None:
+        """Verify the model route as soon as the start screen is up.
+
+        The same round trip a direct launch makes in prepare_and_start, run in
+        the background so the screen paints first and the outcome lands in the
+        setup log before the user has finished typing.
+        """
+        if not (load_settings().llm.model or "").strip():
+            return
+        try:
+            await self._preflight_model()
+        except Exception as exc:
+            logger.exception("Go TUI setup model preflight failed")
+            self.controller.add_message(f"Model connection failed: {exc}", "error")
+            return
+        self.controller.add_message("Model connection verified")
+
+    async def ensure_model_verified(self) -> None:
+        """Hold a setup launch until the model has answered once."""
+        preflight = self._setup_preflight
+        if preflight is not None and not preflight.done():
+            await asyncio.shield(preflight)
+        if self.model_verified:
+            return
+        try:
+            await self._preflight_model()
+        except Exception as exc:
+            logger.exception("Go TUI setup model preflight failed")
+            report_error("model_connection_failed", exc)
+            raise RuntimeError(f"Model connection failed: {exc}") from exc
+
+    async def _preflight_model(self) -> None:
+        model = (load_settings().llm.model or "").strip()
+        self.controller.add_message("Verifying model connection...")
+        set_scan_phase("preflight")
+        await preflight_model_connection(model)
+        self.model_verified = True
+
+    def _start_preparation(self) -> asyncio.Task[None]:
+        """Kick off the work that runs behind the freshly painted TUI."""
+        if self.controller.setup_mode:
+            self._setup_preflight = asyncio.create_task(self.check_setup_model())
+            return self._setup_preflight
+        self.controller.begin_preparation()
+        return asyncio.create_task(self.prepare_and_start())
+
+    async def start_from_setup(self) -> None:
         candidate = deepcopy(self.args)
         candidate.scan_mode = self.controller.scan_mode
         candidate.instruction = self.controller.instruction
@@ -121,16 +179,7 @@ class GoTuiRuntime:
             if isinstance(target, dict) and target.get("original")
         ]
         targets_changed = self.controller.targets != existing_targets
-        model = (load_settings().llm.model or "").strip()
-        # A bare prompt launches optimistically: it skips the network preflight
-        # and lets any model error surface once the agent starts, like a coding
-        # agent. A named target keeps the upfront check.
-        if verify:
-            try:
-                await preflight_model_connection(model)
-            except Exception as exc:
-                logger.exception("Go TUI setup model preflight failed")
-                raise RuntimeError(f"Model connection failed: {exc}") from exc
+        persist_current()
         # A confirmed target-less launch mounts the working directory for the
         # agent to work in, without making it a scan target.
         candidate.workspace_mount = self.controller.workspace_mount
@@ -140,7 +189,11 @@ class GoTuiRuntime:
             candidate.target = list(self.controller.targets)
             candidate.target_list = []
             build_targets_info(candidate)
-        prepare_run(candidate)
+        try:
+            prepare_run(candidate)
+        except Exception as exc:
+            report_error("scan_preparation_failed", exc)
+            raise
         telemetry_start(candidate)
 
         vars(self.args).update(vars(candidate))
@@ -154,13 +207,21 @@ class GoTuiRuntime:
         launch so the interface appears immediately.
         """
         model = (load_settings().llm.model or "").strip()
+        set_scan_phase("preflight")
         try:
             await preflight_model_connection(model)
+        except Exception as exc:
+            logger.exception("Go TUI scan preparation failed")
+            report_error("model_connection_failed", exc)
+            self.controller.fail_preparation(str(exc))
+            return
+        try:
             persist_current()
             prepare_run(self.args)
             telemetry_start(self.args)
         except Exception as exc:
             logger.exception("Go TUI scan preparation failed")
+            report_error("scan_preparation_failed", exc)
             self.controller.fail_preparation(str(exc))
             return
         self.controller.scan_state = "running"
@@ -199,6 +260,9 @@ class GoTuiRuntime:
             self.controller.scan_state = "completed" if report_status == "completed" else "stopped"
         except Exception as exc:
             logger.exception("Go TUI scan failed")
+            report_error("unhandled_exception", exc)
+            if self.report_state is not None and self.report_state.scan_ended_exit_reason is None:
+                self.report_state.scan_ended_exit_reason = "error"
             self.scan_error = exc
             self.controller.error = str(exc)
             self.controller.scan_state = "failed"
@@ -280,7 +344,9 @@ class GoTuiRuntime:
         if self.report_state is not None:
             usage = dict(self.report_state.get_total_llm_usage())
             vulnerabilities = [
-                report.get("id", index) if isinstance(report, dict) else index
+                (report.get("id", index), _revision_count(report))
+                if isinstance(report, dict)
+                else index
                 for index, report in enumerate(self.report_state.vulnerability_reports)
             ]
         return json.dumps(
@@ -373,9 +439,7 @@ class GoTuiRuntime:
                 )
             process, backend_socket = await launch_tui_process(command, env, cwd)
             await self.server.start(backend_socket)
-            if not self.controller.setup_mode:
-                self.controller.begin_preparation()
-                prepare_task = asyncio.create_task(self.prepare_and_start())
+            prepare_task = self._start_preparation()
             sync_task = asyncio.create_task(self.sync_state())
             return_code = await wait_process(process)
             check_return_code(return_code)

strix/interface/url_safety.py

@@ -0,0 +1,85 @@
+"""Validation for URLs printed or opened on behalf of a remote service."""
+
+from __future__ import annotations
+
+import ipaddress
+from urllib.parse import SplitResult, urlsplit
+
+from strix.interface.terminal_text import has_terminal_control
+
+
+def is_safe_web_url(
+    value: object,
+    *,
+    trusted_origin: str | None = None,
+    require_trusted_origin: bool = False,
+) -> bool:
+    """Accept a strict HTTP(S) URL, optionally only on a pre-trusted origin."""
+    parsed = _parse(value)
+    if parsed is None:
+        return False
+    trusted = _parse(trusted_origin) if trusted_origin is not None else None
+    same_origin = trusted is not None and _origin(parsed) == _origin(trusted)
+    if require_trusted_origin:
+        return same_origin
+    if same_origin:
+        return True
+    return _is_safe_external_https(parsed)
+
+
+def _is_safe_external_https(parsed: SplitResult) -> bool:
+    """Reject local, numeric-looking, or otherwise ambiguous external hosts."""
+    hostname = (parsed.hostname or "").lower().rstrip(".")
+    if (
+        parsed.scheme != "https"
+        or hostname == "localhost"
+        or hostname.endswith((".localhost", ".local"))
+    ):
+        return False
+    try:
+        return ipaddress.ip_address(hostname).is_global
+    except ValueError:
+        pass
+    labels = hostname.split(".")
+    return len(labels) >= 2 and not all(_looks_numeric(label) for label in labels)
+
+
+def _parse(value: object) -> SplitResult | None:
+    if not isinstance(value, str) or not value or has_terminal_control(value):
+        return None
+    if "\\" in value or any(character.isspace() for character in value):
+        return None
+    try:
+        parsed = urlsplit(value)
+        port = parsed.port
+    except ValueError:
+        return None
+    hostname = parsed.hostname
+    if (
+        parsed.scheme not in {"http", "https"}
+        or not hostname
+        or parsed.username is not None
+        or parsed.password is not None
+        or parsed.fragment
+        or "%" in parsed.netloc
+    ):
+        return None
+    try:
+        hostname.encode("ascii")
+    except UnicodeEncodeError:
+        return None
+    return parsed if port is None or 1 <= port <= 65535 else None
+
+
+def _origin(parsed: SplitResult) -> tuple[str, str, int]:
+    default_port = 443 if parsed.scheme == "https" else 80
+    return parsed.scheme, (parsed.hostname or "").lower().rstrip("."), parsed.port or default_port
+
+
+def _looks_numeric(label: str) -> bool:
+    lowered = label.lower()
+    if lowered.startswith("0x"):
+        return len(lowered) > 2 and all(
+            character in "0123456789abcdef" for character in lowered[2:]
+        )
+    return bool(lowered) and all(character.isdigit() for character in lowered)

strix/interface/utils.py

@@ -19,6 +19,7 @@ from rich.panel import Panel
 from rich.text import Text
 
 from strix.config import load_settings
+from strix.telemetry import report_error
 from strix.utils.api_spec import detect_spec_format
 
 
@@ -281,27 +282,9 @@ def is_subscription_run(report_state: Any) -> bool:
     record = getattr(report_state, "run_record", None)
     if isinstance(record, dict) and record.get("auth_mode"):
         return record.get("auth_mode") == "subscription"
-    from strix.config import opencode
+    from strix.config import codex
 
-    return opencode.auth_mode(load_settings().llm.model) == "subscription"
-
-
-def subscription_label() -> str:
-    """Display name of the subscription behind the configured model."""
-    from strix.config import opencode
-
-    oc = opencode.subscription_model(load_settings().llm.model)
-    if oc:
-        return oc.label
-    return "ChatGPT subscription"
-
-
-def subscription_is_metered() -> bool:
-    """Whether the run spends per-request credits rather than a flat plan."""
-    from strix.config import opencode
-
-    oc = opencode.subscription_model(load_settings().llm.model)
-    return oc is not None and oc.metered
+    return codex.auth_mode(load_settings().llm.model) == "subscription"
 
 
 def _int_stat(usage: dict[str, Any], key: str) -> int:
@@ -344,9 +327,7 @@ def _build_llm_usage_stats(
     if not usage or _int_stat(usage, "requests") <= 0:
         stats_text.append("\n")
         stats_text.append("Cost ", style="dim")
-        if subscription and subscription_is_metered():
-            stats_text.append("credits ", style="#22c55e")
-        elif subscription:
+        if subscription:
             stats_text.append("$0.00 ", style="#22c55e")
             stats_text.append("(subscription) ", style="dim")
         else:
@@ -375,19 +356,7 @@ def _build_llm_usage_stats(
     stats_text.append("Output Tokens ", style="dim")
     stats_text.append(format_token_count(output_tokens), style="white")
 
-    if subscription and subscription_is_metered():
-        # Zen spends prepaid credits per request, so a run is not free. Its
-        # Anthropic route runs through LiteLLM and yields a real charge; the
-        # OpenAI-SDK routes report none, and an unpriced run says so rather
-        # than claiming $0.00.
-        stats_text.append("  ·  ", style="dim white")
-        stats_text.append("Cost ", style="dim")
-        if cost > 0:
-            stats_text.append(f"${cost:.4f}", style="#22c55e")
-            stats_text.append(" (credits)", style="dim")
-        else:
-            stats_text.append("credits", style="#22c55e")
-    elif subscription:
+    if subscription:
         stats_text.append("  ·  ", style="dim white")
         stats_text.append("Cost ", style="dim")
         stats_text.append("$0.00", style="#22c55e")
@@ -419,7 +388,7 @@ def build_live_stats_text(report_state: Any) -> Text:
     stats_text.append(str(model), style="white")
     if is_subscription_run(report_state):
         stats_text.append("  ·  ", style="dim white")
-        stats_text.append(subscription_label(), style="#22c55e")
+        stats_text.append("ChatGPT subscription", style="#22c55e")
     stats_text.append("\n")
 
     vuln_count = len(report_state.vulnerability_reports)
@@ -465,7 +434,7 @@ def build_tui_stats_text(report_state: Any) -> Text:
     subscription = is_subscription_run(report_state)
     if subscription:
         stats_text.append("\n")
-        stats_text.append(subscription_label(), style="#22c55e")
+        stats_text.append("ChatGPT subscription", style="#22c55e")
 
     usage = _llm_usage(report_state)
     if usage and _int_stat(usage, "total_tokens") > 0:
@@ -1634,7 +1603,8 @@ def check_docker_connection() -> Any:
 
     try:
         return docker.from_env()
-    except DockerException:
+    except DockerException as exc:
+        report_error("docker_unavailable", exc)
         console = Console()
         error_text = Text()
         error_text.append("DOCKER NOT AVAILABLE", style="bold red")

strix/interface/viewer/cli.py

@@ -87,7 +87,7 @@ def run_view(argv: list[str]) -> None:
 
     posthog.viewer_opened(source="cli", live=live)
 
-    state_label = "[#eab308]live[/]" if live else "[#22c55e]finished[/]"
+    state_label = _state_label(summary)
     console.print()
     console.print(f"Serving [bold white]{run_name}[/] ({state_label}) at:")
     # Print the URL alone on its own line with soft_wrap so Rich never inserts a
@@ -107,6 +107,18 @@ def run_view(argv: list[str]) -> None:
         httpd.server_close()
 
 
+def _state_label(summary: dict[str, object]) -> str:
+    if not summary.get("finished", False):
+        return "[#eab308]live[/]"
+
+    status = summary.get("status")
+    if status == "failed":
+        return "[#ef4444]failed[/]"
+    if status in {"stopped", "interrupted"}:
+        return f"[#eab308]{status}[/]"
+    return "[#22c55e]finished[/]"
+
+
 def _resolve_run_dir(run: str | None, console: Console) -> Path:
     if run:
         run_dir = run_dir_for(run)

strix/interface/viewer/frontend/src/App.tsx

@@ -8,6 +8,7 @@ import {
   Radar,
   Rocket,
   ArrowUpRight,
+  Building2,
   History,
 } from "lucide-react";
 import type { Vulnerability, VulnerabilitySeverity } from "@/types/issues";
@@ -35,7 +36,7 @@ import {
   type LoadedRun,
   type RunsPayload,
 } from "@/data/serverSource";
-import { SIGNUP_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
 import { runTitle } from "@/lib/target-utils";
 import Sidebar from "@/components/Sidebar";
 import PastRunsView from "@/components/PastRunsView";
@@ -706,6 +707,31 @@ function OverviewTab({
         </div>
       )}
 
+      {finished && (
+        <div className="animate-card-in rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5">
+          <p className="text-sm font-semibold text-white">Strix Cloud</p>
+          <p className="mt-0.5 text-xs text-[#666]">Run your next pentest in Strix Cloud.</p>
+          <div className="mt-3 flex flex-wrap gap-2.5">
+            <ProInlineCta
+              label="Run a pentest in Strix Cloud"
+              desc="Validated findings, autofix, and PR reviews."
+              slug="overview_cloud"
+              surface="overview"
+              icon={Rocket}
+              primary
+            />
+            <ProInlineCta
+              label="Try Strix Enterprise"
+              desc="SSO, compliance-ready reports, VPC or self-hosted deployment."
+              slug="book_demo"
+              surface="overview"
+              icon={Building2}
+              href={DEMO_URL}
+            />
+          </div>
+        </div>
+      )}
+
       {sections.length > 0 ? (
         <div className="animate-card-in rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5 space-y-8">
           {sections.map((s) => (
@@ -789,14 +815,23 @@ function AgentsTab({ run, canSteer }: { run: LoadedRun; canSteer: boolean }) {
       {/* Re-run always routes to Strix Cloud. */}
       <div className="rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5">
         <p className="text-sm font-semibold text-white">Run this pentest with more depth</p>
-        <p className="mt-0.5 text-xs text-[#666]">Re-run this pentest on managed infra in the cloud.</p>
+        <p className="mt-0.5 text-xs text-[#666]">Run this pentest again in Strix Cloud.</p>
         <div className="mt-3 flex flex-wrap gap-2.5">
           <ProInlineCta
             label="Re-run in Strix Pro with more depth"
-            desc="Run this pentest on managed infra with more depth."
+            desc="More depth, validated findings, and autofix."
             slug="live_scan"
             surface="agents"
             icon={Rocket}
+            primary
+          />
+          <ProInlineCta
+            label="Try Strix Enterprise"
+            desc="SSO, compliance-ready reports, VPC or self-hosted deployment."
+            slug="book_demo"
+            surface="agents"
+            icon={Building2}
+            href={DEMO_URL}
           />
         </div>
       </div>

strix/interface/viewer/frontend/src/components/ProCta.tsx

@@ -48,23 +48,40 @@ export function ProInlineCta({
   slug,
   icon: Icon,
   surface,
+  href = SIGNUP_URL,
+  primary = false,
 }: {
   label: string;
   desc: string;
   slug: string;
   icon: React.ElementType;
   surface?: string;
+  /** Destination before attribution params. Defaults to cloud sign-up. */
+  href?: string;
+  /** Solid white button instead of the outlined default. */
+  primary?: boolean;
 }) {
   return (
     <Tooltip text={desc}>
       <a
-        href={ctaUrl(SIGNUP_URL, slug)}
+        href={ctaUrl(href, slug)}
         target="_blank"
         rel="noopener noreferrer"
         onClick={() => trackCta(slug, surface)}
-        className="group inline-flex items-center gap-2 rounded-lg border border-[#222] bg-[rgba(255,255,255,0.02)] px-3 py-2 text-sm text-[#aaa] transition-colors hover:border-[#444] hover:text-white"
+        className={
+          primary
+            ? "group inline-flex items-center gap-2 rounded-lg border border-white bg-white px-3 py-2 text-sm font-semibold text-black transition-colors hover:bg-[#e5e5e5]"
+            : "group inline-flex items-center gap-2 rounded-lg border border-[#222] bg-[rgba(255,255,255,0.02)] px-3 py-2 text-sm text-[#aaa] transition-colors hover:border-[#444] hover:text-white"
+        }
       >
-        <Icon className="h-4 w-4 text-[#888] transition-colors group-hover:text-white" aria-hidden="true" />
+        <Icon
+          className={
+            primary
+              ? "h-4 w-4 text-black"
+              : "h-4 w-4 text-[#888] transition-colors group-hover:text-white"
+          }
+          aria-hidden="true"
+        />
         <span>{label}</span>
       </a>
     </Tooltip>

strix/interface/viewer/frontend/src/components/RunDetails.tsx

@@ -101,23 +101,6 @@ export function RunDetails({
   const totalTokens = num(usage.total_tokens);
   const cost = num(usage.cost);
   const subscription = str(raw.auth_mode) === "subscription";
-  const subscriptionProvider =
-    str(raw.subscription_provider) ??
-    (models.some((m) => m.toLowerCase().startsWith("opencode")) ? "opencode" : "chatgpt");
-  // Runs recorded before subscription_plan existed still carry the model string,
-  // whose prefix names the plan.
-  const subscriptionPlan =
-    str(raw.subscription_plan) ??
-    (models.some((m) => m.toLowerCase().startsWith("opencode-go/")) ? "go" : "zen");
-  const subscriptionLabel =
-    subscriptionProvider === "opencode"
-      ? subscriptionPlan === "go"
-        ? "OpenCode Go"
-        : "OpenCode Zen"
-      : "ChatGPT subscription";
-  // Zen bills prepaid credits per request, so its runs are not free and there is
-  // no price table to estimate them from. Go is a flat monthly plan.
-  const metered = subscriptionProvider === "opencode" && subscriptionPlan === "zen";
 
   const sub = (n: number, word: string) => (
     <span className="text-[#666]"> ({formatNumber(n)} {word})</span>
@@ -197,7 +180,7 @@ export function RunDetails({
                 <Field label="Provider">
                   <span className="inline-flex items-center gap-1.5">
                     <span className="rounded-full border border-[#22c55e]/40 bg-[#22c55e]/10 px-2 py-0.5 text-[11px] text-[#22c55e]">
-                      {subscriptionLabel}
+                      ChatGPT subscription
                     </span>
                   </span>
                 </Field>
@@ -217,21 +200,7 @@ export function RunDetails({
                 </Field>
               )}
               {totalTokens != null && <Field label="Total tokens">{formatNumber(totalTokens)}</Field>}
-              {subscription && metered ? (
-                <Field label="Cost">
-                  {cost != null && cost > 0 ? (
-                    <>
-                      <span className="text-[#22c55e]">${cost.toFixed(2)}</span>
-                      <span className="text-[#666]"> (Zen credits)</span>
-                    </>
-                  ) : (
-                    <>
-                      <span className="text-[#22c55e]">credits</span>
-                      <span className="text-[#666]"> (not priced locally)</span>
-                    </>
-                  )}
-                </Field>
-              ) : subscription ? (
+              {subscription ? (
                 <Field label="Cost">
                   <span className="text-[#22c55e]">$0.00</span>
                   <span className="text-[#666]"> (subscription)</span>

strix/interface/viewer/frontend/src/components/UpgradeModal.tsx

@@ -10,7 +10,7 @@ import {
   WandSparkles,
   Plug,
 } from "lucide-react";
-import { SIGNUP_URL, PRICING_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, PRICING_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
 
 /**
  * Dialog shown when a platform feature is clicked in the sidebar: a short
@@ -141,6 +141,19 @@ export function UpgradeModal({
               <ExternalLink className="h-3 w-3" />
             </a>
           </div>
+
+          <p className="text-center text-xs text-[#666]">
+            SSO, compliance reports, or a private deployment?{" "}
+            <a
+              href={ctaUrl(DEMO_URL, "upgrade_book_demo")}
+              target="_blank"
+              rel="noopener noreferrer"
+              onClick={() => trackCta("upgrade_book_demo", source)}
+              className="whitespace-nowrap text-[#aaa] underline underline-offset-2 transition-colors hover:text-white"
+            >
+              Try Strix Enterprise
+            </a>
+          </p>
         </div>
       </div>
     </div>

strix/interface/viewer/frontend/src/components/live/tool-renderers/index.ts

@@ -116,7 +116,7 @@ const CATEGORY_TOOLS: Record<ToolCategory, readonly string[]> = {
   filesystem: ["apply_patch", "view_image", "str_replace_editor", "list_files", "search_files"],
   // Caido proxy tools (legacy: send_request)
   proxy: ["list_requests", "view_request", "repeat_request", "list_sitemap", "view_sitemap_entry", "scope_rules", "send_request"],
-  reporting: ["create_vulnerability_report", "list_reports", "get_report"],
+  reporting: ["create_vulnerability_report", "update_vulnerability_report", "list_reports", "get_report"],
   thinking: ["think"],
   agents: ["create_agent", "agent_finish", "send_message_to_agent", "wait_for_agents", "view_agent_graph", "stop_agent"],
   search: ["web_search"],

strix/interface/viewer/report_pdf.py

@@ -20,6 +20,7 @@ from datetime import datetime
 from io import BytesIO
 from typing import TYPE_CHECKING, Any
 
+from markdown_it import MarkdownIt
 from pypdf import PdfReader, PdfWriter
 from reportlab.lib import colors
 from reportlab.lib.enums import TA_CENTER
@@ -49,6 +50,8 @@ from strix.interface.viewer.transcript import (
 if TYPE_CHECKING:
     from pathlib import Path
 
+    from markdown_it.token import Token
+
 
 # Palette lifted from the cloud report theme (styles/base.ts, docx/theme.ts).
 _INK = colors.HexColor("#000000")
@@ -72,11 +75,21 @@ _SANS_BOLD = "Helvetica-Bold"
 _MONO = "Courier"
 
 _PAGE_W, _PAGE_H = A4
+_INLINE_MD = MarkdownIt("commonmark", {"html": False, "linkify": False}).disable(
+    ["autolink", "image", "link"]
+)
+_UNSAFE_TEXT_RE = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f\ud800-\udfff\ufffe\uffff]")
+
+
+def _normalize_text(value: Any) -> str:
+    """Normalize characters that ReportLab cannot safely serialize."""
+    text = str(value).replace("\r\n", "\n").replace("\r", "\n")
+    return _UNSAFE_TEXT_RE.sub("\ufffd", text)
 
 
 def _esc(value: Any) -> str:
     """Escape a value for reportlab's Paragraph markup."""
-    return html.escape(str(value)).replace("\n", "<br/>")
+    return html.escape(_normalize_text(value)).replace("\n", "<br/>")
 
 
 class _NumberedCanvas(pdfcanvas.Canvas):  # type: ignore[misc]  # reportlab base is untyped
@@ -253,7 +266,10 @@ def _duration(start: Any, end: Any) -> str:
     end_dt = _parse_time(end)
     if not start_dt or not end_dt:
         return "n/a"
-    seconds = int((end_dt - start_dt).total_seconds())
+    try:
+        seconds = int((end_dt - start_dt).total_seconds())
+    except (OverflowError, TypeError):
+        return "n/a"
     if seconds < 0:
         return "n/a"
     hours, remainder = divmod(seconds, 3600)
@@ -265,10 +281,18 @@ def _duration(start: Any, end: Any) -> str:
     return f"{secs}s"
 
 
-def _severity_badge(styles: dict[str, ParagraphStyle], severity: str) -> Table:
+def _normalize_severity(value: Any) -> str:
+    severity = str(value or "").lower().strip()
+    if severity == "informational":
+        return "info"
+    return severity if severity in {*_SEVERITY_COLORS, "info"} else "low"
+
+
+def _severity_badge(styles: dict[str, ParagraphStyle], severity: Any) -> Table:
     """A colored pill matching .severity-badge in the cloud report."""
+    severity = _normalize_severity(severity)
     color = _SEVERITY_COLORS.get(severity, _MUTED)
-    cell = Paragraph(severity.upper(), styles["badge"])
+    cell = Paragraph(_esc(severity.upper()), styles["badge"])
     table = Table([[cell]], colWidths=[len(severity) * 6.5 + 20])
     table.setStyle(
         TableStyle(
@@ -406,27 +430,36 @@ def _cover(
 
 
 def _inline_md(text: str) -> str:
-    """Convert inline markdown (bold, italic, `code`) to reportlab markup.
+    """Render a safe subset of inline Markdown as ReportLab markup."""
+    tokens = _INLINE_MD.parseInline(_normalize_text(text))[0].children or []
+    return "".join(_inline_token_markup(token) for token in tokens)
 
-    Code spans are stashed as placeholders before bold/italic run, so bold that
-    wraps a code span (``**`x`**``) works and code contents are never mangled.
-    """
-    codes: list[str] = []
 
-    def _stash(match: re.Match[str]) -> str:
-        codes.append(match.group(1))
-        return f"\x00{len(codes) - 1}\x00"
+def _inline_token_markup(token: Token) -> str:
+    fixed_markup = {
+        "strong_open": "<b>",
+        "strong_close": "</b>",
+        "em_open": "<i>",
+        "em_close": "</i>",
+        "hardbreak": "<br/>",
+        "softbreak": " ",
+    }.get(token.type)
+    if fixed_markup is not None:
+        return fixed_markup
+    if token.type == "code_inline":
+        return f'<font face="{_MONO}" color="#b31d28">{html.escape(token.content)}</font>'
+    # Unsupported token content remains escaped so parser extensions cannot
+    # expose ReportLab tags.
+    return html.escape(token.content)
 
-    seg = html.escape(re.sub(r"`([^`]+)`", _stash, text))
-    seg = re.sub(r"\*\*(.+?)\*\*", r"<b>\1</b>", seg)
-    seg = re.sub(r"__(.+?)__", r"<b>\1</b>", seg)
-    seg = re.sub(r"\*(.+?)\*", r"<i>\1</i>", seg)
 
-    def _restore(match: re.Match[str]) -> str:
-        inner = html.escape(codes[int(match.group(1))])
-        return f'<font face="{_MONO}" color="#b31d28">{inner}</font>'
-
-    return re.sub(r"\x00(\d+)\x00", _restore, seg)
+def _markdown_paragraph(text: str, style: ParagraphStyle) -> Paragraph:
+    """Build a Markdown paragraph, falling back to escaped source text."""
+    source = _normalize_text(text)
+    try:
+        return Paragraph(_inline_md(source), style)
+    except ValueError:
+        return Paragraph(_esc(source), style)
 
 
 def _strip_leading_heading(md: str) -> str:
@@ -447,12 +480,12 @@ def _markdown_flowables(  # noqa: PLR0915 - cohesive block parser, splitting hur
 
     def flush_para() -> None:
         if para:
-            flow.append(Paragraph(_inline_md(" ".join(para)), styles["body"]))
+            flow.append(_markdown_paragraph(" ".join(para), styles["body"]))
             para.clear()
 
     def flush_bullets() -> None:
         for marker, item in bullets:
-            flow.append(Paragraph(f"{marker}&nbsp;{_inline_md(item)}", styles["bullet"]))
+            flow.append(_markdown_paragraph(f"{marker}\u00a0{item}", styles["bullet"]))
         bullets.clear()
 
     lines = md.replace("\r\n", "\n").split("\n")
@@ -479,7 +512,7 @@ def _markdown_flowables(  # noqa: PLR0915 - cohesive block parser, splitting hur
         if heading:
             flush_para()
             flush_bullets()
-            flow.append(Paragraph(_inline_md(heading.group(2)), styles["md_heading"]))
+            flow.append(_markdown_paragraph(heading.group(2), styles["md_heading"]))
             i += 1
             continue
         ordered = re.match(r"^(\d+)\.\s+(.*)$", stripped)
@@ -532,7 +565,7 @@ def _finding_flowables(
     styles: dict[str, ParagraphStyle], index: int, vuln: dict[str, Any]
 ) -> list[Flowable]:
     title = vuln.get("title") or "Untitled finding"
-    severity = str(vuln.get("severity") or "").lower().strip() or "low"
+    severity = _normalize_severity(vuln.get("severity"))
 
     meta_bits = []
     if vuln.get("cvss") is not None:

strix/interface/viewer/static/index.html

@@ -6,8 +6,8 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <meta name="color-scheme" content="dark" />
     <title>Strix Results</title>
-    <script type="module" crossorigin src="./assets/index-DD3_cI9L.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-Ccea__Xc.css">
+    <script type="module" crossorigin src="./assets/index-B94ANU8d.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-DN__rVv3.css">
   </head>
   <body>
     <div id="root"></div>

strix/llm/context_budget.py

@@ -18,8 +18,6 @@ logger = logging.getLogger(__name__)
 _STRIPPABLE_PREFIXES = (
     "openai/",
     "chatgpt/",
-    "opencode-go/",
-    "opencode/",
     "litellm/",
     "any-llm/",
     "ollama/",
@@ -50,11 +48,7 @@ def _model_info(model: str) -> dict[str, int]:
     lookup_key = _lookup_key(model)
     # Provider-qualified ChatGPT lookups may start a synchronous device-login
     # poll. LiteLLM keys the metadata by the underlying model slug.
-    candidates = (
-        (lookup_key,)
-        if model.startswith(("chatgpt/", "opencode/", "opencode-go/"))
-        else (model, lookup_key)
-    )
+    candidates = (lookup_key,) if model.startswith("chatgpt/") else (model, lookup_key)
     for candidate in candidates:
         info = _safe_get_model_info(candidate)
         if info is not None:

strix/llm/warmup.py

@@ -1,20 +1,22 @@
 """Background pre-import of the heavy scan dependencies.
 
 The scan engine's import graph (the agents SDK, OpenAI client, LiteLLM, the
-Caido SDK, the Docker SDK) costs seconds to import cold, but none of it is
-needed until a scan actually starts. Importing it on a daemon thread at CLI
-entry overlaps that cost with the I/O-bound startup work that always precedes
-a scan (argument parsing, Docker checks, image pull, TUI setup), so by the
-time the scan begins the modules are already in ``sys.modules``. Any thread
-that needs one of them before the warm-up finishes just blocks on the normal
-import lock, so behaviour is unchanged either way.
+Caido SDK) costs seconds to import cold, but none of it is needed until a scan
+actually starts. Importing it on a daemon thread at CLI entry overlaps that
+cost with the I/O-bound startup work that always precedes a scan (argument
+parsing, Docker checks, image pull, TUI setup). The Docker SDK is not on the
+list: the Docker checks import it on the main thread during that same window.
+
+The main thread must call :func:`wait_for_import_warmup` before its first
+import from that graph. Two threads that enter the same package graph from
+different modules hold each other's import locks, and CPython breaks the cycle
+by failing one of the imports.
 """
 
 from __future__ import annotations
 
 import importlib
 import logging
-import sys
 import threading
 
 
@@ -24,45 +26,17 @@ WARMUP_MODULES = (
     "strix.core.runner",
     "litellm",
     "caido_sdk_client",
-    "docker",
 )
 
-_lock = threading.Lock()
 _thread: threading.Thread | None = None
 
 
-def _purge_orphaned_modules(before: frozenset[str]) -> None:
-    """Remove submodules stranded by an import attempt that just failed.
-
-    When a package import fails partway (for example CPython's import-lock
-    deadlock avoidance breaking a cross-thread cycle), the failed package is
-    removed from ``sys.modules`` but submodules it already finished stay
-    behind. A later import of one of those submodules then short-circuits on
-    the cached entry without re-importing its parent, and re-entering the
-    parent from inside a submodule crashes with "partially initialized
-    module". Dropping the orphans (cached submodules whose ancestor package is
-    gone) restores a clean slate, and touches nothing another thread imported
-    successfully.
-    """
-    added = set(sys.modules) - before
-    for name in added:
-        parent = name.rpartition(".")[0]
-        while parent:
-            if parent not in sys.modules:
-                sys.modules.pop(name, None)
-                logger.debug("Import warm-up purged orphaned module %r", name)
-                break
-            parent = parent.rpartition(".")[0]
-
-
 def _warm(modules: tuple[str, ...]) -> None:
     for name in modules:
-        before = frozenset(sys.modules)
         try:
             importlib.import_module(name)
         except Exception:  # noqa: BLE001 - a failed warm-up must never fail the run.
             logger.debug("Import warm-up for %r failed", name, exc_info=True)
-            _purge_orphaned_modules(before)
 
 
 def start_import_warmup(modules: tuple[str, ...] = WARMUP_MODULES) -> threading.Thread:
@@ -72,11 +46,15 @@ def start_import_warmup(modules: tuple[str, ...] = WARMUP_MODULES) -> threading.
     runtime that has no local Docker) warm a narrower set.
     """
     global _thread  # noqa: PLW0603
-    with _lock:
-        if _thread is not None:
-            return _thread
+    if _thread is None:
         _thread = threading.Thread(
             target=_warm, args=(modules,), name="strix-import-warmup", daemon=True
         )
         _thread.start()
-        return _thread
+    return _thread
+
+
+def wait_for_import_warmup() -> None:
+    """Block until the warm-up thread has finished, if one was started."""
+    if _thread is not None:
+        _thread.join()

strix/report/state.py

@@ -10,7 +10,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any, Optional, cast
 from uuid import uuid4
 
-from strix.config import opencode
+from strix.config import codex
 from strix.config.loader import load_settings
 from strix.core.paths import run_dir_for, runtime_state_dir
 from strix.report.coverage import write_coverage
@@ -44,6 +44,57 @@ def _strix_version() -> str | None:
         return None
 
 
+# Content a revision may replace. The identity of the finding (id, timestamp,
+# finding_class) and its original author stay put. dependency_metadata is
+# replaced whole, so a caller carries the package identity over itself.
+UPDATABLE_REPORT_FIELDS = frozenset(
+    {
+        "title",
+        "dependency_metadata",
+        "severity",
+        "description",
+        "impact",
+        "target",
+        "technical_analysis",
+        "poc_description",
+        "poc_script_code",
+        "remediation_steps",
+        "evidence",
+        "assumptions",
+        "counterevidence",
+        "confidence",
+        "confidence_rationale",
+        "severity_change_conditions",
+        "fix_effort",
+        "cvss",
+        "cvss_breakdown",
+        "endpoint",
+        "method",
+        "cve",
+        "cwe",
+        "code_locations",
+        "http_exchange_ids",
+        "fix_verification",
+        "fix_pr_body",
+    }
+)
+
+_LOWERCASE_REPORT_FIELDS = frozenset({"severity", "confidence", "fix_effort"})
+
+# Fields that only describe another field. A revision may raise the rating or
+# replace the locations without restating the reasoning behind the old one, and
+# that leftover reasoning then contradicts the finding it annotates
+# ("confidence: high" beside a rationale calling the evidence unconfirmed). When
+# the field they describe changes and the update carries no replacement, they
+# are dropped rather than kept.
+_DEPENDENT_REPORT_FIELDS: dict[str, tuple[str, ...]] = {
+    "confidence": ("confidence_rationale",),
+    "severity": ("severity_change_conditions",),
+    "cvss": ("cvss_breakdown",),
+    "code_locations": ("fix_verification",),
+}
+
+
 def _clean_title(title: str) -> str:
     """Return a single-line finding title.
 
@@ -117,7 +168,7 @@ def get_global_report_state() -> Optional["ReportState"]:
     return _global_report_state
 
 
-def set_global_report_state(report_state: "ReportState") -> None:
+def set_global_report_state(report_state: Optional["ReportState"]) -> None:
     global _global_report_state  # noqa: PLW0603
     _global_report_state = report_state
     # New run: drop any streamed-cost entries a prior run left unconsumed.
@@ -152,13 +203,8 @@ class ReportState:
 
         self._llm_usage = LLMUsageLedger()
         self._telemetry_llm_usage_baseline: dict[str, Any] = {}
-        auth_mode = opencode.auth_mode(load_settings().llm.model)
-        oc = opencode.subscription_model(load_settings().llm.model)
-        # A flat subscription has no per-run charge to report. Zen bills prepaid
-        # credits per request, so its cost is real and stays tracked.
-        self._llm_usage.zero_cost = auth_mode == "subscription" and not (
-            oc is not None and oc.metered
-        )
+        auth_mode = codex.auth_mode(load_settings().llm.model)
+        self._llm_usage.zero_cost = auth_mode == "subscription"
         self.run_record: dict[str, Any] = {
             "run_id": self.run_id,
             "run_name": self.run_name,
@@ -166,8 +212,6 @@ class ReportState:
             "end_time": None,
             "status": "running",
             "auth_mode": auth_mode,
-            "subscription_provider": opencode.subscription_provider(load_settings().llm.model),
-            "subscription_plan": opencode.subscription_plan(load_settings().llm.model),
             "targets_info": [],
             "llm_usage": self._build_llm_usage_record(),
         }
@@ -176,6 +220,7 @@ class ReportState:
 
         self.caido_url: str | None = None
         self.vulnerability_found_callback: Callable[[dict[str, Any]], None] | None = None
+        self.vulnerability_updated_callback: Callable[[dict[str, Any]], None] | None = None
 
         self._sarif_repo_ctx: dict[str, Any] | None = None
         self._sarif_repo_ctx_ready: bool = False
@@ -243,6 +288,12 @@ class ReportState:
                 )
             self.vulnerability_reports = [r for r in data if isinstance(r, dict)]
             for r in self.vulnerability_reports:
+                # A finding written before the class was persisted still carries the
+                # metadata of its class, so name the class it always had.
+                if not r.get("finding_class"):
+                    r["finding_class"] = (
+                        "dependency_cve" if r.get("dependency_metadata") else "dynamic"
+                    )
                 title = r.get("title")
                 stale_md = False
                 if isinstance(title, str):
@@ -283,6 +334,7 @@ class ReportState:
         cve: str | None = None,
         cwe: str | None = None,
         code_locations: list[dict[str, Any]] | None = None,
+        http_exchange_ids: list[str] | None = None,
         fix_verification: str | None = None,
         fix_pr_body: str | None = None,
         finding_class: str | None = None,
@@ -341,6 +393,8 @@ class ReportState:
             report["cwe"] = cwe.strip()
         if code_locations:
             report["code_locations"] = code_locations
+        if http_exchange_ids:
+            report["http_exchange_ids"] = http_exchange_ids
         if fix_verification:
             report["fix_verification"] = fix_verification.strip()
         if fix_pr_body:
@@ -353,17 +407,115 @@ class ReportState:
         if agent_name:
             report["agent_name"] = agent_name
 
+        if self.vulnerability_found_callback:
+            self.vulnerability_found_callback(report)
+
         self.vulnerability_reports.append(report)
         logger.info(f"Added vulnerability report: {report_id} - {title}")
         posthog.finding(severity, cwe=cwe, is_cve=bool(cve))
         scarf.finding(severity, cwe=cwe, is_cve=bool(cve))
 
-        if self.vulnerability_found_callback:
-            self.vulnerability_found_callback(report)
-
         self.save_run_data()
         return report_id
 
+    def update_vulnerability_report(
+        self,
+        report_id: str,
+        fields: dict[str, Any],
+        *,
+        update_reason: str | None = None,
+        updated_by_agent_id: str | None = None,
+        updated_by_agent_name: str | None = None,
+    ) -> dict[str, Any] | None:
+        """Apply a revision to an existing report, keeping its id.
+
+        A field that only describes a field this update replaces is dropped when
+        the update carries no replacement for it, so the revised report cannot
+        state a new rating beside the superseded reasoning for the old one.
+
+        Returns the revised report, or ``None`` when the id is unknown or when
+        nothing in ``fields`` changes it.
+        """
+        report = next((r for r in self.vulnerability_reports if r.get("id") == report_id), None)
+        if report is None:
+            logger.warning("cannot update unknown vulnerability report %s", report_id)
+            return None
+
+        changed: dict[str, Any] = {}
+        for key, raw_value in fields.items():
+            if key not in UPDATABLE_REPORT_FIELDS or raw_value is None:
+                continue
+            value = raw_value
+            if isinstance(value, str):
+                value = _clean_title(value) if key == "title" else value.strip()
+                if key in _LOWERCASE_REPORT_FIELDS:
+                    value = value.lower()
+                if not value:
+                    continue
+            if report.get(key) == value:
+                continue
+            changed[key] = value
+
+        superseded = {
+            dependent
+            for primary, dependents in _DEPENDENT_REPORT_FIELDS.items()
+            if primary in changed
+            for dependent in dependents
+            if dependent not in changed and report.get(dependent) not in (None, "", [], {})
+        }
+
+        if not changed and not superseded:
+            logger.info("update for %s carried no new content; keeping it as is", report_id)
+            return None
+
+        entry: dict[str, Any] = {
+            "timestamp": datetime.now(UTC).strftime("%Y-%m-%d %H:%M:%S UTC"),
+            "fields": sorted(changed),
+        }
+        if superseded:
+            entry["dropped_fields"] = sorted(superseded)
+        if update_reason and update_reason.strip():
+            entry["reason"] = update_reason.strip()[:500]
+        if updated_by_agent_id:
+            entry["agent_id"] = updated_by_agent_id
+        if updated_by_agent_name:
+            entry["agent_name"] = updated_by_agent_name
+        for key in ("severity", "cvss", "confidence"):
+            if key in changed and report.get(key) is not None:
+                entry[f"previous_{key}"] = report[key]
+
+        raw_history = report.get("update_history")
+        history: list[dict[str, Any]] = (
+            [e for e in raw_history if isinstance(e, dict)] if isinstance(raw_history, list) else []
+        )
+        history.append(entry)
+
+        revised = {**report, **changed}
+        for dependent in superseded:
+            revised.pop(dependent, None)
+        revised["update_history"] = history
+        revised["updated_at"] = entry["timestamp"]
+
+        # Persistence must accept the revision before local state changes. A
+        # failed callback leaves the old evidence intact and the update retryable.
+        if self.vulnerability_updated_callback:
+            self.vulnerability_updated_callback(revised)
+        report.clear()
+        report.update(revised)
+
+        # The markdown on disk still shows the superseded evidence, so let the
+        # writer re-render it.
+        self._saved_vuln_ids.discard(report_id)
+
+        logger.info(
+            "Updated vulnerability report %s (%s)",
+            report_id,
+            ", ".join(entry["fields"]) or "no field replaced",
+        )
+
+        self.save_run_data()
+        return report
+
     def get_existing_vulnerabilities(self) -> list[dict[str, Any]]:
         return list(self.vulnerability_reports)
 

strix/report/writer.py

@@ -356,4 +356,41 @@ def render_vulnerability_md(report: dict[str, Any]) -> str:  # noqa: PLR0912, PL
         lines.append(str(report["assumptions"]))
         lines.append("")
 
+    lines.extend(render_update_history(report.get("update_history")))
+
     return "\n".join(lines)
+
+
+def render_update_history(history: Any) -> list[str]:
+    """Render the audit trail of every revision a report has received."""
+    if not isinstance(history, list):
+        return []
+    entries: list[dict[str, Any]] = [
+        cast("dict[str, Any]", e) for e in history if isinstance(e, dict)
+    ]
+    if not entries:
+        return []
+
+    lines = ["## Update History\n"]
+    for entry in entries:
+        author = str(entry.get("agent_name") or entry.get("agent_id") or "an agent")
+        raw_fields = entry.get("fields")
+        fields: list[Any] = raw_fields if isinstance(raw_fields, list) else []
+        changed = ", ".join(str(field) for field in fields)
+        timestamp = str(entry.get("timestamp") or "unknown")
+        lines.append(f"**{timestamp}** — {author} updated: {changed}")
+        raw_dropped = entry.get("dropped_fields")
+        if isinstance(raw_dropped, list) and raw_dropped:
+            dropped = ", ".join(str(field) for field in raw_dropped)
+            lines.append(f"  Dropped as superseded: {dropped}")
+        for key, label in (
+            ("previous_severity", "severity"),
+            ("previous_cvss", "CVSS"),
+            ("previous_confidence", "confidence"),
+        ):
+            if entry.get(key) is not None:
+                lines.append(f"  Previous {label}: {entry[key]}")
+        if entry.get("reason"):
+            lines.append(f"  Reason: {entry['reason']}")
+        lines.append("")
+    return lines

strix/runtime/session_manager.py

@@ -5,7 +5,9 @@ from __future__ import annotations
 import asyncio
 import logging
 import os
+import shutil
 import sys
+import tempfile
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
@@ -13,7 +15,6 @@ from agents.sandbox.entries import BaseEntry, File, LocalDir
 from agents.sandbox.manifest import Environment, Manifest
 
 from strix.config import load_settings
-from strix.core.paths import run_dir_for, runtime_state_dir
 from strix.runtime.backends import backend_supports_bind_mounts, get_backend
 from strix.runtime.caido_bootstrap import bootstrap_caido
 from strix.runtime.caido_handle import CaidoBootstrapHandle
@@ -168,6 +169,17 @@ def build_extra_file_entries(
     return entries
 
 
+def extra_file_staging_dir(scan_id: str) -> Path:
+    """A fresh host staging directory for a scan's extra-file bind mounts.
+
+    The docker daemon resolves bind sources in its own filesystem. With a
+    remote daemon (e.g. a dind sidecar) the run directory is not shared, so
+    staging lives under the temp dir like every other bind-mount source.
+    """
+    safe = "".join(c if c.isalnum() or c in "-_." else "-" for c in scan_id)
+    return Path(tempfile.mkdtemp(prefix=f"strix-extra-files-{safe}-"))
+
+
 def build_extra_file_bind_mounts(
     extra_files: list[dict[str, Any]],
     staging_dir: Path,
@@ -280,11 +292,12 @@ async def create_or_reuse(
     backend_name = load_settings().runtime.backend
     backend = get_backend(backend_name)
 
+    staging_dir: Path | None = None
     if backend_supports_bind_mounts(backend_name):
         bind_mounts = build_bind_mounts(local_sources)
         entries: dict[str | Path, BaseEntry] = {}
         if extra_files:
-            staging_dir = runtime_state_dir(run_dir_for(scan_id)) / "extra_files"
+            staging_dir = extra_file_staging_dir(scan_id)
             bind_mounts.extend(
                 build_extra_file_bind_mounts(extra_files, staging_dir, local_sources)
             )
@@ -322,44 +335,56 @@ async def create_or_reuse(
         image,
     )
     report("Starting sandbox container")
-    client, session = await backend(
-        image=image,
-        manifest=manifest,
-        exposed_ports=(_CONTAINER_CAIDO_PORT,),
-        bind_mounts=bind_mounts,
-    )
-
-    report("Setting up the proxy")
-    caido_endpoint = await session.resolve_exposed_port(_CONTAINER_CAIDO_PORT)
-    scheme = "https" if caido_endpoint.tls else "http"
-    host_caido_url = f"{scheme}://{caido_endpoint.host}:{caido_endpoint.port}"
-    logger.debug("Caido host endpoint resolved: %s", host_caido_url)
-
-    # The Caido login + project setup polls the guest for a couple of seconds
-    # and nothing needs the client before the first proxy tool call, so it
-    # runs concurrently with the rest of scan start; consumers resolve the
-    # handle at first use (see CaidoBootstrapHandle).
-    caido_client = CaidoBootstrapHandle(
-        asyncio.create_task(
-            bootstrap_caido(
-                session,
-                host_url=host_caido_url,
-                container_url=container_caido_url,
-            ),
-            name=f"caido-bootstrap-{scan_id}",
+    try:
+        client, session = await backend(
+            image=image,
+            manifest=manifest,
+            exposed_ports=(_CONTAINER_CAIDO_PORT,),
+            bind_mounts=bind_mounts,
         )
-    )
 
-    bundle = {
-        "client": client,
-        "session": session,
-        "caido_client": caido_client,
-    }
-    _SESSION_CACHE[scan_id] = bundle
+        report("Setting up the proxy")
+        caido_endpoint = await session.resolve_exposed_port(_CONTAINER_CAIDO_PORT)
+        scheme = "https" if caido_endpoint.tls else "http"
+        host_caido_url = f"{scheme}://{caido_endpoint.host}:{caido_endpoint.port}"
+        logger.debug("Caido host endpoint resolved: %s", host_caido_url)
+
+        # The Caido login + project setup polls the guest for a couple of seconds
+        # and nothing needs the client before the first proxy tool call, so it
+        # runs concurrently with the rest of scan start; consumers resolve the
+        # handle at first use (see CaidoBootstrapHandle).
+        caido_client = CaidoBootstrapHandle(
+            asyncio.create_task(
+                bootstrap_caido(
+                    session,
+                    host_url=host_caido_url,
+                    container_url=container_caido_url,
+                ),
+                name=f"caido-bootstrap-{scan_id}",
+            )
+        )
+
+        bundle = {
+            "client": client,
+            "session": session,
+            "caido_client": caido_client,
+            "extra_file_staging_dir": staging_dir,
+        }
+        _SESSION_CACHE[scan_id] = bundle
+    except BaseException:
+        # Until the bundle is cached, cleanup(scan_id) cannot find the
+        # staging dir, so it is removed here.
+        _remove_staging_dir(staging_dir)
+        raise
     logger.info("Sandbox session for scan %s ready and cached", scan_id)
     return bundle
 
 
+def _remove_staging_dir(staging_dir: Path | None) -> None:
+    if staging_dir is not None:
+        shutil.rmtree(staging_dir, ignore_errors=True)
+
+
 async def cleanup(scan_id: str) -> None:
     """Tear down ``scan_id``'s container and drop its cache entry.
 
@@ -373,6 +398,8 @@ async def cleanup(scan_id: str) -> None:
         logger.debug("cleanup(%s): no cached session", scan_id)
         return
 
+    _remove_staging_dir(bundle.get("extra_file_staging_dir"))
+
     caido_client = bundle.get("caido_client")
     if caido_client is not None:
         try:

strix/skills/__init__.py

@@ -1,6 +1,5 @@
 import logging
 import re
-import threading
 from collections import Counter
 from collections.abc import Iterator
 from pathlib import Path
@@ -8,7 +7,6 @@ from typing import TypeGuard
 
 import yaml
 
-from strix.telemetry import posthog, scarf
 from strix.utils.resource_paths import get_strix_resource_path
 
 
@@ -241,16 +239,19 @@ def validate_requested_skills(skill_list: list[str], max_skills: int = 5) -> str
     return None
 
 
+_LOADED_SKILLS: set[str] = set()
+
+
 def _track_skill_loaded(skill_name: str, file_path: Path) -> None:
     builtin = get_strix_resource_path("skills")
     if not file_path.is_relative_to(builtin):
         skill_name = "custom"
+    _LOADED_SKILLS.add(skill_name)
 
-    def _send() -> None:
-        posthog.skill_loaded(skill_name)
-        scarf.skill_loaded(skill_name)
 
-    threading.Thread(target=_send, daemon=True).start()
+def get_loaded_skill_names() -> list[str]:
+    """Distinct skills loaded so far in this process (custom skills collapse to ``"custom"``)."""
+    return sorted(_LOADED_SKILLS)
 
 
 def _candidate_skill_files(skill_name: str) -> list[Path]:

strix/telemetry/README.md

@@ -12,11 +12,11 @@ Privacy is our priority. All collected data is anonymized by default. Each sessi
 
 We collect only very **basic** usage data including:
 
-**Session Errors:** Duration and error types (not messages or stack traces)\
+**Session Errors:** Duration, the failure category, the scan phase, and the exception class name (not messages or stack traces)\
 **System Context:** OS type, architecture, Strix version\
 **Scan Context:** Scan mode (quick/standard/deep), scan type (whitebox/blackbox)\
 **Model Usage:** Which LLM model is being used and whether it runs via an API key or a model subscription (not prompts or responses)\
-**Feature Usage:** Which built-in skills are loaded\
+**Feature Usage:** Which built-in skills were used during a scan (reported once, at scan end)\
 **Aggregate Metrics:** Vulnerability counts by severity and weakness category (CWE)
 
 ### What We **Never** Collect

strix/telemetry/__init__.py

@@ -1,7 +1,19 @@
 from . import posthog, scarf
+from ._common import set_scan_phase
+
+
+def report_error(error_type: str, exc: BaseException | None = None) -> None:
+    """Beacon a failure category, plus the exception class when one is given.
+
+    Only class names travel: never the message, arguments, or traceback.
+    """
+    posthog.error(error_type, exc)
+    scarf.error(error_type, exc)
 
 
 __all__ = [
     "posthog",
+    "report_error",
     "scarf",
+    "set_scan_phase",
 ]

strix/telemetry/_common.py

@@ -5,7 +5,7 @@ import platform
 import sys
 from importlib.metadata import PackageNotFoundError, version
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
 from uuid import uuid4
 
 
@@ -54,3 +54,43 @@ def base_props() -> dict[str, Any]:
         "python": f"{sys.version_info.major}.{sys.version_info.minor}",
         "strix_version": get_version(),
     }
+
+
+# Coarse stage of the current run, attached to ``error`` beacons so a failure
+# can be placed without a message or trace. Process-local, like the rest of the
+# CLI telemetry: one process runs one scan.
+_scan_phase = "startup"
+
+
+def set_scan_phase(phase: str) -> None:
+    global _scan_phase  # noqa: PLW0603
+    _scan_phase = phase
+
+
+def get_scan_phase() -> str:
+    return _scan_phase
+
+
+def _exception_name(exc: BaseException) -> str:
+    cls = type(exc)
+    package = cls.__module__.split(".")[0]
+    return cls.__name__ if package == "builtins" else f"{package}.{cls.__name__}"
+
+
+def _unwrap_group(exc: BaseException) -> BaseException:
+    if not isinstance(exc, BaseExceptionGroup):
+        return exc
+    group = cast("BaseExceptionGroup[BaseException]", exc)
+    return group.exceptions[0] if group.exceptions else group
+
+
+def exception_props(exc: BaseException) -> dict[str, str]:
+    """Class names only. Messages, arguments, and tracebacks never leave the machine."""
+    exc = _unwrap_group(exc)
+    props = {"exception_type": _exception_name(exc)}
+    cause = exc.__cause__
+    if cause is None and not exc.__suppress_context__:
+        cause = exc.__context__
+    if cause is not None:
+        props["exception_cause"] = _exception_name(cause)
+    return props

strix/telemetry/posthog.py

@@ -4,10 +4,14 @@ from typing import TYPE_CHECKING, Any
 import requests
 
 from strix.config import load_settings
+from strix.skills import get_loaded_skill_names
 from strix.telemetry._common import (
     SEND_TIMEOUT,
     SESSION_ID,
     base_props,
+    exception_props,
+    get_scan_phase,
+    get_version,
     is_first_run,
 )
 
@@ -35,7 +39,12 @@ def _send(event: str, properties: dict[str, Any]) -> bool:
             "api_key": _POSTHOG_PUBLIC_API_KEY,
             "event": event,
             "distinct_id": SESSION_ID,
-            "properties": properties,
+            "properties": {
+                **properties,
+                "$lib": "strix-cli",
+                "$lib_version": get_version(),
+                "$process_person_profile": False,
+            },
         }
         with requests.post(f"{_POSTHOG_HOST}/capture/", json=payload, timeout=SEND_TIMEOUT):
             pass
@@ -82,16 +91,6 @@ def finding(severity: str, cwe: str | None = None, is_cve: bool = False) -> None
     )
 
 
-def skill_loaded(skill_name: str) -> None:
-    _send(
-        "skill_loaded",
-        {
-            **base_props(),
-            "skill": skill_name,
-        },
-    )
-
-
 def end(report_state: "ReportState", exit_reason: str = "completed") -> None:
     if report_state.posthog_scan_ended_sent:
         return
@@ -130,6 +129,7 @@ def end(report_state: "ReportState", exit_reason: str = "completed") -> None:
             "vulnerabilities_total": len(report_state.vulnerability_reports),
             **{f"vulnerabilities_{k}": v for k, v in vulnerabilities_counts.items()},
             **llm_props,
+            "skills": get_loaded_skill_names(),
         },
     )
 
@@ -180,6 +180,12 @@ def viewer_agent_steered() -> None:
     _send("viewer_agent_steered", {**base_props()})
 
 
-def error(error_type: str) -> None:
-    props = {**base_props(), "error_type": error_type}
+def error(error_type: str, exc: BaseException | None = None) -> None:
+    props: dict[str, Any] = {
+        **base_props(),
+        "error_type": error_type,
+        "phase": get_scan_phase(),
+    }
+    if exc is not None:
+        props.update(exception_props(exc))
     _send("error", props)

strix/telemetry/scarf.py

@@ -7,10 +7,13 @@ from typing import TYPE_CHECKING, Any
 import requests
 
 from strix.config import load_settings
+from strix.skills import get_loaded_skill_names
 from strix.telemetry._common import (
     SEND_TIMEOUT,
     SESSION_ID,
     base_props,
+    exception_props,
+    get_scan_phase,
     get_version,
     is_first_run,
 )
@@ -90,17 +93,6 @@ def finding(severity: str, cwe: str | None = None, is_cve: bool = False) -> None
     )
 
 
-def skill_loaded(skill_name: str) -> None:
-    _send(
-        "skill_loaded",
-        {
-            **base_props(),
-            "session": SESSION_ID,
-            "skill": skill_name,
-        },
-    )
-
-
 def end(report_state: ReportState, exit_reason: str = "completed") -> None:
     if report_state.scarf_scan_ended_sent:
         return
@@ -140,14 +132,18 @@ def end(report_state: ReportState, exit_reason: str = "completed") -> None:
             "vulnerabilities_total": len(report_state.vulnerability_reports),
             **{f"vulnerabilities_{k}": v for k, v in vulnerabilities_counts.items()},
             **llm_props,
+            "skills": ",".join(get_loaded_skill_names()),
         },
     )
 
 
-def error(error_type: str) -> None:
+def error(error_type: str, exc: BaseException | None = None) -> None:
     props: dict[str, Any] = {
         **base_props(),
         "session": SESSION_ID,
         "error_type": error_type,
+        "phase": get_scan_phase(),
     }
+    if exc is not None:
+        props.update(exception_props(exc))
     _send("error", props)

strix/tools/agents_graph/tools.py

@@ -15,6 +15,7 @@ from agents import RunContextWrapper, function_tool
 from strix.core.agents import Status, coordinator_from_context
 from strix.core.execution import notify_parent_on_terminal
 from strix.core.hooks import LLM_TURN_KEY
+from strix.report.state import get_global_report_state
 from strix.skills import validate_requested_skills
 
 
@@ -28,6 +29,40 @@ def _ctx(ctx: RunContextWrapper) -> dict[str, Any]:
     return ctx.context if isinstance(ctx.context, dict) else {}
 
 
+def _filed_reports_by(agent_id: str) -> list[dict[str, Any]]:
+    """Vulnerability reports the agent actually filed, from report state.
+
+    The narrative ``findings`` an agent hands to ``agent_finish`` is prose; a
+    parent that wants to act on a child's work needs the report ids. Read them
+    from the report state rather than trusting the child's description.
+    """
+    state = get_global_report_state()
+    if state is None:
+        return []
+    filed: list[dict[str, Any]] = []
+    seen: set[str] = set()
+    for report in state.get_existing_vulnerabilities():
+        if report.get("agent_id") != agent_id:
+            continue
+        report_id = str(report.get("id") or "")
+        if not report_id or report_id in seen:
+            continue
+        seen.add(report_id)
+        filed.append(report)
+    return filed
+
+
+def _render_filed_report(report: dict[str, Any]) -> str:
+    line = f"- {report.get('id')}"
+    severity = report.get("severity")
+    if severity:
+        line += f" [{str(severity).upper()}]"
+    title = report.get("title")
+    if title:
+        line += f" {title}"
+    return line
+
+
 def _render_completion_report(
     *,
     agent_name: str,
@@ -38,6 +73,7 @@ def _render_completion_report(
     findings: list[str],
     recommendations: list[str],
     open_items: list[str],
+    filed_reports: list[dict[str, Any]] | None = None,
 ) -> str:
     """Render a child's completion report as plain structured text.
 
@@ -63,6 +99,12 @@ def _render_completion_report(
         lines.append("Findings:")
         lines.extend(f"- {f}" for f in findings)
     lines.append("")
+    lines.append("Vulnerability reports filed by this agent (authoritative; use these ids):")
+    if filed_reports:
+        lines.extend(_render_filed_report(r) for r in filed_reports)
+    else:
+        lines.append("- (none)")
+    lines.append("")
     lines.append("Open items (unresolved, need follow-up):")
     if open_items:
         lines.extend(f"- {o}" for o in open_items)
@@ -149,8 +191,11 @@ async def send_message_to_agent(
     **Don't** use for routine "hello/status" pings, for context the
     target already has (children inherit parent history), or when
     parent/child completion via ``agent_finish`` already covers the
-    flow. Messages to any registered agent wake it, regardless of
+    flow. In interactive runs a message wakes the target regardless of
     status, so a follow-up can restart a completed/stopped/failed agent.
+    In non-interactive runs a finished agent is gone for good: the call
+    fails with the target's status, and you should read its filed
+    reports (``list_reports``) or spawn a new agent instead of waiting.
 
     Args:
         target_agent_id: Recipient's 8-char id.
@@ -195,10 +240,23 @@ async def send_message_to_agent(
         },
     )
     if not delivered:
+        _, status = await coordinator.reachability(target_agent_id)
+        if status is None:
+            error = f"Target agent '{target_agent_id}' not found"
+        else:
+            error = (
+                f"Target agent '{target_agent_id}' is '{status}' and cannot be woken in "
+                "this run; it will never read this message. Its filed reports are in "
+                "list_reports / get_report. Do not wait_for_agents on it - spawn a new "
+                "agent if more work is needed."
+            )
         return json.dumps(
             {
                 "success": False,
-                "error": f"Target agent '{target_agent_id}' not found or message delivery failed",
+                "error": error,
+                "target_agent_id": target_agent_id,
+                "target_status": status,
+                "delivery_status": "not_delivered",
             },
             ensure_ascii=False,
             default=str,
@@ -364,6 +422,31 @@ async def wait_for_agents(  # noqa: PLR0911
             default=str,
         )
 
+    # Non-interactive agents cannot be woken once terminal, so with nobody
+    # running or waiting there is no message left to wait for.
+    if not await coordinator.active_agents_except(me):
+        _, statuses, names, _ = await coordinator.graph_snapshot()
+        return json.dumps(
+            {
+                "success": True,
+                "wait_outcome": "no_active_agents",
+                "reason": reason,
+                "agents": [
+                    {"agent_id": aid, "name": names.get(aid, aid), "status": status}
+                    for aid, status in statuses.items()
+                    if aid != me
+                ],
+                "note": (
+                    "No other agent is running or waiting, so no message can arrive. "
+                    "Finished agents' results are in list_reports / get_report and their "
+                    "completion reports are already in your history. Continue your own "
+                    "work, spawn a new agent, or finish."
+                ),
+            },
+            ensure_ascii=False,
+            default=str,
+        )
+
     await coordinator.park_waiting(me, wait_kind="agents")
     try:
         await asyncio.wait_for(coordinator.wait_for_message(me), timeout_seconds)
@@ -610,6 +693,9 @@ async def agent_finish(
             default=str,
         )
 
+    filed_reports = _filed_reports_by(me)
+    filed_report_ids = [str(r.get("id")) for r in filed_reports]
+
     parent_notified = False
     if report_to_parent and await coordinator.claim_parent_notice(me):
         async with coordinator._lock:
@@ -623,6 +709,7 @@ async def agent_finish(
             findings=list(findings or []),
             recommendations=list(final_recommendations or []),
             open_items=list(open_items or []),
+            filed_reports=filed_reports,
         )
         await coordinator.send(
             parent_id,
@@ -632,6 +719,7 @@ async def agent_finish(
                 "content": report,
                 "type": "completion",
                 "priority": "high",
+                "filed_report_ids": filed_report_ids,
             },
         )
         parent_notified = True
@@ -642,10 +730,11 @@ async def agent_finish(
         await notify_parent_on_terminal(coordinator, me, "completed")
 
     logger.info(
-        "agent_finish: %s success=%s findings=%d parent_notified=%s",
+        "agent_finish: %s success=%s findings=%d filed_reports=%d parent_notified=%s",
         me,
         success,
         len(findings or []),
+        len(filed_report_ids),
         parent_notified,
     )
 
@@ -656,6 +745,7 @@ async def agent_finish(
             "parent_notified": parent_notified,
             "agent_id": me,
             "summary": result_summary,
+            "filed_report_ids": filed_report_ids,
             "findings_count": len(findings or []),
             "open_items_count": len(open_items or []),
             "has_recommendations": bool(final_recommendations),

strix/tools/mcp/__init__.py

@@ -13,6 +13,7 @@ from strix.tools.mcp.config import (
     McpAuth,
     McpConnectionConfig,
 )
+from strix.tools.mcp.failures import FailureInfo, HttpStatusRecorder, classify
 from strix.tools.mcp.loader import load_user_mcp_configs
 from strix.tools.mcp.naming import namespaced_tool_name
 from strix.tools.mcp.registry import (
@@ -38,6 +39,8 @@ __all__ = [
     "MCP_REGISTRY_CONTEXT_KEY",
     "BearerAuth",
     "ConnectedMcpServer",
+    "FailureInfo",
+    "HttpStatusRecorder",
     "McpAuth",
     "McpCallInfo",
     "McpConnectionConfig",
@@ -50,6 +53,7 @@ __all__ = [
     "SupervisedMcpSession",
     "attach_mcp_requests",
     "call_mcp",
+    "classify",
     "connect_mcp_servers",
     "describe_mcp",
     "list_mcps",

strix/tools/mcp/agent_tools.py

@@ -50,13 +50,6 @@ def _unknown_connection(connection: str, registry: McpRegistry) -> str:
     return f"Unknown MCP connection {connection!r}. Available connections: {available}."
 
 
-def _unavailable_connection(connection: str) -> str:
-    return (
-        f"MCP connection {connection!r} is unavailable: its live session failed and "
-        "could not be reconnected, so it is unavailable for the rest of this run."
-    )
-
-
 def _format_tool(tool: MCPTool) -> str:
     schema = json.dumps(tool.inputSchema or {"type": "object"}, indent=2, ensure_ascii=False)
     description = (tool.description or "").strip() or "(no description)"
@@ -114,8 +107,8 @@ async def describe_mcp(ctx: RunContextWrapper, connection: str) -> str:
         return _unknown_connection(connection, registry)
     try:
         tools = await entry.session.list_tools()
-    except McpConnectionUnavailableError:
-        return _unavailable_connection(connection)
+    except McpConnectionUnavailableError as exc:
+        return str(exc)
     if not tools:
         return f"MCP connection {connection!r} offers no tools."
     header = f"MCP connection {connection!r} offers {len(tools)} tool(s):"
@@ -170,8 +163,8 @@ async def call_mcp(
         return invalid_arguments
     try:
         available = await entry.session.list_tools()
-    except McpConnectionUnavailableError:
-        return _errored_tool_output(_unavailable_connection(connection))
+    except McpConnectionUnavailableError as exc:
+        return _errored_tool_output(str(exc))
     valid_names = {mcp_tool.name for mcp_tool in available}
     if tool not in valid_names:
         offered = ", ".join(sorted(valid_names)) or "(none)"