fix(mcp): keep the session on tool-call protocol errors and report quarantine truthfully

.pre-commit-config.yaml

@@ -1,6 +1,3 @@
-# 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
@@ -12,18 +9,21 @@ repos:
       - id: ruff-format
         name: ruff-format
 
-  # 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
+  # MyPy for static type checking
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.17.1
     hooks:
       - id: mypy
-        name: mypy
-        entry: uv run mypy
-        language: system
-        types_or: [python, pyi]
-        files: ^(strix|tests)/
-        require_serial: true
+        additional_dependencies: [
+          types-requests,
+          types-python-dateutil,
+          pydantic,
+          fastapi,
+          pytest,
+          hatchling,
+          "openai-agents[litellm]>=0.19.0,<0.20",
+        ]
+        args: [--install-types, --non-interactive]
 
   # Built-in hooks for basic file checks
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -62,6 +62,5 @@ ci:
   autoupdate_branch: ""
   autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
   autoupdate_schedule: weekly
-  # pre-commit.ci cannot run `language: system` hooks; mypy runs via `make check-all`.
-  skip: [mypy]
+  skip: []
   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="openrouter/z-ai/glm-5.3"        # any LiteLLM model id
+  export STRIX_LLM="openai/gpt-5.4"                 # any LiteLLM model id
   export LLM_API_KEY="<key>"
   strix -n -t ./ --scan-mode quick --max-budget 10  # headless scan; always use -n
   ```

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="openrouter/z-ai/glm-5.3"
+   export STRIX_LLM="openai/gpt-5.4"
    export LLM_API_KEY="your-api-key"
    ```
 

README.md

@@ -17,9 +17,6 @@
 <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>
@@ -37,7 +34,7 @@
 
 
 > [!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?utm_source=github&utm_medium=readme&utm_content=tip_ci).
+> **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).
 
 ---
 
@@ -85,7 +82,7 @@ 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="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 
 # Run your first security assessment
@@ -97,17 +94,9 @@ strix --target ./app-directory
 
 ---
 
-## Ways to Run Strix
+## ☁️ Strix Platform
 
-- **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.
+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.
 
 - **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
@@ -115,13 +104,7 @@ 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
 
-[**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)
+[**Start your first pentest →**](https://app.strix.ai)
 
 ---
 
@@ -133,9 +116,7 @@ Strix is agent-ready. Give Claude Code, Cursor, Codex, or any [SKILL.md-compatib
 npx skills add usestrix/strix
 ```
 
-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.
+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.
 
 ---
 
@@ -191,9 +172,18 @@ strix view my-run-name
 strix view --host 0.0.0.0 --port 8080 --no-open
 ```
 
-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.
+`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.
 
-See the [viewer documentation](https://docs.strix.ai/usage/viewer) for the options and for reaching the viewer from another machine.
+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.
 
 ---
 
@@ -219,9 +209,18 @@ 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, Postman export, or a live collection by id
+# OpenAPI / Swagger file (.json / .yaml)
 strix --target ./openapi.yaml --target https://api.your-app.com
-strix --target postman://<collection-uuid> --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>"
 ```
 
 
@@ -236,9 +235,19 @@ 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
-```
 
-See the [CLI reference](https://docs.strix.ai/usage/cli) for every option, including scan modes, diff scope, instruction files, and budgets.
+# 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
+```
 
 ### Headless Mode
 
@@ -278,55 +287,153 @@ jobs:
 ```
 
 > [!TIP]
-> 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.
+> 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.
 
 ### Configuration
 
 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 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 auth status                    # show the active sign-in, or logout to forget it
+strix --target ./app-directory
+
+strix auth status             # show the active sign-in
+strix auth logout             # forget the sign-in
 ```
 
 #### Use the managed platform: `strix cloud`
 
-Run scans on [app.strix.ai](https://app.strix.ai) from the terminal, without Docker or an LLM key:
+The `strix cloud` commands drive the managed platform ([app.strix.ai](https://app.strix.ai)) from the terminal. Sign in once with the device flow. The sign-in creates your account and workspace on first use and stores a personal API token in `~/.strix/platform-auth.json`:
 
 ```bash
-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
+strix cloud login                         # browser approval, then workspace + scope profile
+strix cloud login --workspace "My Team"   # select a workspace by name or ID
+strix cloud whoami                        # fast local account/workspace status
+strix cloud session                       # verify remote session + consent ceiling
+strix cloud logout                        # revoke remotely, then remove locally
 ```
 
-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.
+The default **Recommended** scope preset supports normal scan work, local source uploads,
+workspace switching, and user-approved credit top-ups. It excludes credential creation;
+request `tokens:write` explicitly (or choose Full) when needed. For strict least privilege, pass an explicit list such as
+`--scopes scans:read scans:write uploads:write billing:read`. Named automation
+profiles are also available with `--scope-profile minimal|recommended|full`.
 
-See the [cloud CLI documentation](https://docs.strix.ai/cloud/cli) for scopes, workspaces, billing, and source-upload options.
+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 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 credits                           # credit balance
+strix cloud billing topup --credits 20 --yes  # explicitly approve agent payment after HTTP 402
+```
+
+Workspaces and account setup also work from the terminal:
+
+```bash
+strix cloud workspaces list                   # numbered list; `workspace` is also accepted
+strix cloud workspaces create --name "My Team" # admin + organizations:write
+strix cloud workspaces use 2                  # switch by list number, exact name, or ID
+strix cloud session scopes                    # granted scopes + login ceiling
+strix cloud session scopes set minimal        # narrow without another browser sign-in
+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.
+
+The commands work for humans and agents: terminal output favors names, branches, lifecycle states, and numbered selectors, while redirected output (or `--json`) preserves complete machine-readable records and IDs. 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 distinguish API keys from named CLI device sessions. Binary downloads are the exception: intentionally redirect their raw bytes, 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. `--token` and `STRIX_API_TOKEN` are stateless per-command overrides and never replace the stored sign-in; pair a CLI-session override with `--workspace-id` or `STRIX_WORKSPACE_ID`.
+
+A browser sign-in creates one reusable credential per CLI installation. Logging in again on the
+same installation replaces its secret instead of accumulating keys. Workspace switches keep that
+credential and expiry, preserve the server-side scope preference, cap access by the target role,
+and can never exceed the login consent ceiling. Each process pins its starting workspace, so a
+concurrent switch fails safely instead of sending a stale command to another organization.
+`strix cloud logout` revokes the server session before deleting the local token; use
+`--local-only` only when you deliberately cannot reach the server.
+
+Write commands take request fields as flags, and 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
+```
+
+For an agent or CI local-source scan, run `--dry-run --show-files --json`, review the manifest,
+and capture `source.archive_sha256`. Rerun with the same `--source`, every `--exclude`, and any
+`--include-*` selection flags, replacing `--dry-run` with `--approve-sha256 HASH`; Strix
+rebuilds the archive and refuses to upload it if the digest changed. `--yes` instead approves
+only the snapshot built in that one invocation. It is suitable for a deliberate human or
+one-shot approval, not as a digest-bound two-step agent/CI handoff.
+
+The safe default honors `.gitignore` and `.strixignore` and excludes hidden paths, secret-like
+files, VCS metadata, dependencies/build output, symlinks, and nested archives. Opt in
+separately with `--include-hidden`, `--include-sensitive`, or `--include-archives`. The client
+caps a bundle at 20,000 files, 25 MiB per file, 250 MiB expanded, and 50 MiB compressed, and
+the service independently validates the archive. Source alone infers a code review; adding a
+domain infers a live test. You can always pass `--engagement-type` explicitly.
+
+Strix removes the temporary local archive after every invocation. It deletes a staged remote
+upload after a definitive scan rejection. If a network error, `5xx` response, malformed
+success response, or interruption makes the launch outcome ambiguous, it retains the upload and reports its `upload_id` with
+`launch_outcome_unknown: true`; if automatic deletion cannot be confirmed, it reports the ID
+with `cleanup_unknown: true`. Check `strix cloud scans list` before retrying. If no scan is
+linked to the retained upload, delete it with `strix cloud uploads delete UPLOAD_ID`.
+
+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. Plan blocks exit `4`; an
+insufficient credit wallet exits `5` without creating or charging a scan.
+
+Enable native tab completion once per shell session:
+
+```bash
+source <(strix completions zsh)       # use bash instead of zsh when appropriate
+strix completions fish | source
+```
 
 #### 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 local `stdio` servers or remote `http` 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:
 
 ```json
 [
+  {
+    "name": "local_fs",
+    "transport": "stdio",
+    "command": "npx",
+    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
+  },
   {
     "name": "github",
     "transport": "http",
@@ -337,19 +444,20 @@ Strix can connect to Model Context Protocol (MCP) servers you list and expose th
 ]
 ```
 
-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.
+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`.
 
 **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., `openrouter/z-ai/glm-5.3`, `openai/gpt-5.4`).
+  Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
 </ParamField>
 
 <ParamField path="LLM_API_KEY" type="string">
@@ -80,22 +80,6 @@ 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>
@@ -161,7 +145,7 @@ strix --target ./app --config /path/to/config.json
 ```json
 {
   "env": {
-    "STRIX_LLM": "openrouter/z-ai/glm-5.3",
+    "STRIX_LLM": "openai/gpt-5.4",
     "LLM_API_KEY": "sk-...",
     "STRIX_REASONING_EFFORT": "high"
   }
@@ -172,11 +156,10 @@ strix --target ./app --config /path/to/config.json
 
 ```bash
 # Required
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="sk-..."
 
-# Optional: Enable web search (Exa preferred, Perplexity supported)
-export EXA_API_KEY="..."
+# Optional: Enable web search
 export PERPLEXITY_API_KEY="pplx-..."
 
 # Optional: Custom timeouts

docs/cloud/cli.mdx

@@ -1,103 +0,0 @@
----
-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/contributing.mdx

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

docs/docs.json

@@ -25,8 +25,7 @@
             "pages": [
               "usage/cli",
               "usage/scan-modes",
-              "usage/instructions",
-              "usage/viewer"
+              "usage/instructions"
             ]
           },
           {
@@ -78,8 +77,7 @@
           {
             "group": "Strix Cloud",
             "pages": [
-              "cloud/overview",
-              "cloud/cli"
+              "cloud/overview"
             ]
           }
         ]

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="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 
 # Scan

docs/integrations/github-actions.mdx

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

docs/llm-providers/novita.mdx

@@ -17,9 +17,6 @@ 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/z-ai/glm-5.3"
+export STRIX_LLM="openrouter/openai/gpt-5.4"
 export LLM_API_KEY="sk-or-..."
 ```
 
@@ -18,12 +18,9 @@ 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

@@ -9,17 +9,14 @@ Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibi
 
 Set your model and API key:
 
-| 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`               |
+| 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` |
 
 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 ```
 
@@ -65,7 +62,6 @@ 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/quickstart.mdx

@@ -28,12 +28,12 @@ description: "Install Strix and run your first security scan"
 Set your LLM provider:
 
 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 ```
 
 <Tip>
-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`.
+For best results, use `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 with Exa or Perplexity   |
+| Web Search     | Real-time OSINT via Perplexity           |
 | Notes          | Document findings during the scan        |
 | Reporting      | Generate vulnerability reports with PoCs |

docs/usage/viewer.mdx

@@ -1,49 +0,0 @@
----
-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 = "1.6.2"
+version = "1.6.0"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"
@@ -250,7 +250,6 @@ 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
@@ -414,8 +413,6 @@ known_third_party = ["pydantic", "litellm"]
 # ============================================================================
 
 [tool.bandit]
-# 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"]
+exclude_dirs = ["docs", "build", "dist"]
 skips = ["B101", "B601", "B404", "B603", "B607"]  # Skip assert, shell injection, subprocess import and partial path checks
 severity = "medium"

scripts/install.sh

@@ -346,9 +346,6 @@ 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 ""

strix/agents/factory.py

@@ -69,7 +69,7 @@ from strix.tools.todo.tools import (
     mark_todo_pending,
     update_todo,
 )
-from strix.tools.web_search.tool import web_get_contents, web_search
+from strix.tools.web_search.tool import web_search
 
 
 if TYPE_CHECKING:
@@ -579,7 +579,6 @@ _BASE_TOOLS: tuple[Tool, ...] = (
     save_threat_model,
     amend_threat_model,
     web_search,
-    web_get_contents,
     create_vulnerability_report,
     create_dependency_report,
     update_vulnerability_report,

strix/config/codex.py

@@ -183,7 +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",  # nosec B105 - boolean flag, not a secret
+        "id_token_add_organizations": "true",
         "codex_cli_simplified_flow": "true",
         "originator": ORIGINATOR,
     }

strix/config/loader.py

@@ -10,13 +10,11 @@ from typing import TYPE_CHECKING, Any
 
 from pydantic import AliasChoices, BaseModel
 
-from strix.config.settings import LlmSettings, Settings
+from strix.config.settings import Settings
 from strix.utils.secret_files import write_secret_text
 
 
 if TYPE_CHECKING:
-    from collections.abc import Mapping
-
     from pydantic.fields import FieldInfo
 
 
@@ -27,11 +25,6 @@ _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.
@@ -61,31 +54,22 @@ def apply_config_override(path: Path) -> None:
 
 
 def persist_current() -> None:
-    """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.
-    """
+    """Write currently-set env vars to the active config file (0o600)."""
     s = load_settings()
     target = _override or _DEFAULT_PATH
     target.parent.mkdir(parents=True, exist_ok=True)
 
-    env_block = _drop_stale_llm_connection(_read_env_block(target))
-    for sub_name in type(s).model_fields:
+    env_block: dict[str, str] = {}
+    for sub_name in 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():
-            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]
+            for alias in _aliases_for(finfo):
+                value = os.environ.get(alias.upper())
+                if value:
+                    env_block[alias.upper()] = value
+                    break
 
     write_secret_text(target, json.dumps({"env": env_block}, indent=2))
 
@@ -109,9 +93,17 @@ 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.
     """
-    env_block_upper = _drop_stale_llm_connection(_read_env_block(path))
-    if not env_block_upper:
+    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 {}
+
+    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]] = {}
@@ -131,38 +123,3 @@ 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

@@ -562,8 +562,6 @@ 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",
@@ -572,7 +570,6 @@ 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",
@@ -580,8 +577,6 @@ 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",
@@ -603,7 +598,6 @@ FRONTIER_MODEL_FAMILIES = (
     (("deepseek",), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
     (("alibaba", "dashscope", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
     (("moonshot", "moonshotai", "kimi"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
-    (("zai", "z-ai", "zai-org", "zhipuai"), ("glm-5.3", "glm-5.2")),
 )
 
 

strix/config/settings.py

@@ -120,10 +120,6 @@ 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
 
@@ -132,25 +128,6 @@ 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

@@ -24,8 +24,6 @@ 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.
@@ -38,10 +36,6 @@ 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
@@ -181,7 +175,6 @@ 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())
@@ -191,8 +184,6 @@ 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:
@@ -284,29 +275,10 @@ 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.
-
-        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.
-        """
+        """Queue a user/peer message in the target's mailbox and wake it."""
         from_user = message.get("from") == "user"
         if from_user and self._budget_paused:
             await self.resume_from_budget_pause(exclude=target_agent_id)
@@ -314,13 +286,6 @@ 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

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

strix/core/runner.py

@@ -45,7 +45,6 @@ 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,
@@ -117,13 +116,6 @@ 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.
 
@@ -321,7 +313,6 @@ 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,
@@ -331,7 +322,6 @@ 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"]
 
@@ -438,7 +428,6 @@ 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
@@ -583,7 +572,6 @@ 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,
@@ -621,7 +609,6 @@ 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")
@@ -634,7 +621,6 @@ 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/cli_args.py

@@ -98,14 +98,6 @@ 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

@@ -14,7 +14,7 @@ import sys
 from rich.console import Console
 from rich.markup import escape
 
-from strix.interface.cloud import http
+import strix.interface.cloud.http as http  # noqa: PLR0402
 from strix.interface.cloud.render import json_mode
 from strix.interface.cloud.runner import resolve, run
 from strix.interface.cloud.session import run_session

strix/interface/cloud/http.py

@@ -34,30 +34,13 @@ 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.
+    """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:
+    def __init__(self, message: str, *, exit_code: int = EXIT_ERROR, payload: Any = None) -> None:
         super().__init__(message)
         self.exit_code = exit_code
         self.payload = payload
-        self.next_step = next_step
 
 
 class CloudTransportError(CloudError):
@@ -366,43 +349,13 @@ def check(response: requests.Response) -> Any:
             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 error_code == "scan_credit_limit_reached":
+        raise CloudError(message, exit_code=EXIT_PAYMENT, payload=data)
     if response.status_code in (401, 403):
         raise CloudError(message, exit_code=EXIT_AUTH, payload=data)
+    if response.status_code == 402:
+        hint = detail or (
+            "not enough credits. Run `strix cloud billing topup --credits N` to buy credits."
+        )
+        raise CloudError(hint, exit_code=EXIT_PAYMENT, 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/runner.py

@@ -1035,14 +1035,10 @@ def _emit_error(
             payload = {"error": str(exc)}
             if exc.payload is not None:
                 payload["detail"] = exc.payload
-        if exc.next_step:
-            payload["next_step"] = exc.next_step
         sys.stdout.write(json.dumps(payload, indent=2, default=str) + "\n")
         return
     target = Console(stderr=True) if to_stderr else console
     target.print(f"[red]Error:[/] {escape(sanitize_terminal_text(exc))}")
-    if exc.next_step:
-        target.print(f"[yellow]Next step:[/] {escape(sanitize_terminal_text(exc.next_step))}")
 
 
 def _emit_interrupted(console: Console, *, as_json: bool, to_stderr: bool) -> None:

strix/interface/cloud/source_upload.py

@@ -203,17 +203,6 @@ def prepare_source(
     """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,
@@ -235,34 +224,14 @@ def prepare_source(
     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)
+        raise http.CloudError(
+            "source archive is larger than the 50 MB upload limit; narrow --source or "
+            "add --exclude patterns."
+        )
     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,
     *,

strix/interface/cloud/spec.py

@@ -1066,8 +1066,7 @@ SPEC: dict[str, dict[str, Cmd]] = {
         "request": Cmd(
             "POST",
             "/uploads/request",
-            "Request an upload URL. To scan local source, prefer `strix cloud scans start "
-            "--source DIR`, which packs, uploads, and starts the scan in one step.",
+            "Request an upload URL.",
             body=(
                 P("file_name", required=True, help="File name."),
                 P("file_size", "int", required=True, help="File size in bytes."),

strix/interface/environment.py

@@ -8,29 +8,17 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import IntegrationSettings, codex, load_settings
+from strix.config import 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()
@@ -45,7 +33,6 @@ 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
@@ -59,7 +46,8 @@ def validate_environment() -> None:
     if not settings.llm.api_base:
         missing_optional_vars.append("LLM_API_BASE")
 
-    missing_optional_vars.extend(_missing_web_search_vars(settings.integrations))
+    if not settings.integrations.perplexity_api_key:
+        missing_optional_vars.append("PERPLEXITY_API_KEY")
 
     if missing_required_vars:
         error_text = Text()
@@ -82,7 +70,7 @@ 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., 'openrouter/z-ai/glm-5.3' or "
+                    " - Model name to use (e.g., 'openai/gpt-5.4' or "
                     "'anthropic/claude-opus-4-7')\n",
                     style="white",
                 )
@@ -101,14 +89,7 @@ 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 (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",
+                        " - API key for Perplexity AI web search (enables real-time research)\n",
                         style="white",
                     )
                 elif var == "STRIX_REASONING_EFFORT":
@@ -121,7 +102,7 @@ def validate_environment() -> None:
                     )
 
         error_text.append("\nExample setup:\n", style="white")
-        error_text.append("export STRIX_LLM='openrouter/z-ai/glm-5.3'\n", style="dim white")
+        error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")
 
         if missing_optional_vars:
             for var in missing_optional_vars:
@@ -135,8 +116,6 @@ 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",
@@ -155,7 +134,6 @@ 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)",
@@ -183,7 +161,6 @@ 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")
 
@@ -231,7 +208,6 @@ 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

@@ -41,8 +41,7 @@ from strix.interface.update_check import (
 from strix.interface.utils import (
     build_final_stats_text,
 )
-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 import posthog, scarf
 from strix.telemetry.logging import configure_dependency_logging
 
 
@@ -333,11 +332,6 @@ 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)
@@ -397,22 +391,22 @@ 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 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.
+    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.
     """
-    set_scan_phase("preflight")
+    validate_environment()
+    if not args.non_interactive:
+        return
     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)
@@ -459,6 +453,8 @@ def main() -> None:
 
         sys.exit(run_cloud(sys.argv[2:]))
 
+    from strix.llm.warmup import start_import_warmup
+
     start_import_warmup()
 
     args = parse_arguments()
@@ -471,12 +467,10 @@ def main() -> None:
 
     check_docker_installed()
     pull_docker_image()
-    validate_environment()
 
-    # Everything below imports the scan engine; do not race the warm-up thread.
-    wait_for_import_warmup()
-
-    if args.non_interactive:
+    # 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:
         _bootstrap_scan(args)
 
     from strix.report.state import get_global_report_state
@@ -487,21 +481,18 @@ 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 as exc:
+    except Exception:
         exit_reason = "error"
-        report_error("unhandled_exception", exc)
+        posthog.error("unhandled_exception")
+        scarf.error("unhandled_exception")
         raise
     finally:
         report_state = get_global_report_state()
@@ -520,7 +511,6 @@ 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/tui/backend/controller.py

@@ -36,8 +36,7 @@ if TYPE_CHECKING:
 _STOPPABLE_AGENT_STATUSES = frozenset({"running", "waiting", "budget_paused"})
 
 ChangeCallback = Callable[[], None]
-StartCallback = Callable[[], Awaitable[None]]
-VerifyCallback = Callable[[], Awaitable[None]]
+StartCallback = Callable[[bool], Awaitable[None]]
 QuitCallback = Callable[[], Awaitable[None]]
 
 
@@ -52,7 +51,6 @@ 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:
@@ -101,6 +99,7 @@ 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
@@ -113,7 +112,6 @@ 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
 
@@ -330,6 +328,12 @@ 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)
@@ -340,44 +344,27 @@ 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()
+        await self._begin_scan(verify)
         return {"started": True}
 
-    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:
+    async def _begin_scan(self, verify: bool) -> None:
         if self._on_start is None:
             raise RuntimeError("Scan start is unavailable")
         self._start_in_progress = True
         try:
-            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
+            await self._on_start(verify)
         finally:
             self._start_in_progress = False
         self.setup_mode = False
@@ -397,7 +384,7 @@ 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()
+        await self._begin_scan(self._pending_verify)
         return {"approved": approved}
 
     async def _send_message(self, payload: dict[str, Any]) -> dict[str, Any]:

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

@@ -45,20 +45,23 @@ 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}))
 	}
-	// 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 {
+	// 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 {
 		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 if setup.start
-	// wins 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 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.
 	return *m, tea.Sequence(commands...)
 }
 

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

@@ -94,6 +94,25 @@ 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 {
@@ -141,6 +160,10 @@ 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)
@@ -250,8 +273,9 @@ func TestSetupPromptWithTargetLaunches(t *testing.T) {
 			t.Fatalf("missing %s in %v", want, types)
 		}
 	}
-	if _, found := startPayloadFlag(t, envelopes, "mount_working_dir"); found {
-		t.Fatalf("a targeted prompt must not ask to mount the working directory: %v", 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)
 	}
 	// The target and instruction must reach the backend before setup.start
 	// closes the setup guard.

strix/interface/tui/runtime.py

@@ -37,7 +37,6 @@ 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
 
 
@@ -64,14 +63,11 @@ 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)
@@ -111,53 +107,7 @@ class GoTuiRuntime:
         )
         self.controller.notify_changed()
 
-    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:
+    async def start_from_setup(self, verify: bool = True) -> None:
         candidate = deepcopy(self.args)
         candidate.scan_mode = self.controller.scan_mode
         candidate.instruction = self.controller.instruction
@@ -174,7 +124,16 @@ class GoTuiRuntime:
             if isinstance(target, dict) and target.get("original")
         ]
         targets_changed = self.controller.targets != existing_targets
-        persist_current()
+        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
         # 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
@@ -184,11 +143,7 @@ class GoTuiRuntime:
             candidate.target = list(self.controller.targets)
             candidate.target_list = []
             build_targets_info(candidate)
-        try:
-            prepare_run(candidate)
-        except Exception as exc:
-            report_error("scan_preparation_failed", exc)
-            raise
+        prepare_run(candidate)
         telemetry_start(candidate)
 
         vars(self.args).update(vars(candidate))
@@ -202,21 +157,13 @@ 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"
@@ -255,9 +202,6 @@ 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"
@@ -432,7 +376,9 @@ class GoTuiRuntime:
                 )
             process, backend_socket = await launch_tui_process(command, env, cwd)
             await self.server.start(backend_socket)
-            prepare_task = self._start_preparation()
+            if not self.controller.setup_mode:
+                self.controller.begin_preparation()
+                prepare_task = asyncio.create_task(self.prepare_and_start())
             sync_task = asyncio.create_task(self.sync_state())
             return_code = await wait_process(process)
             check_return_code(return_code)

strix/interface/utils.py

@@ -19,7 +19,6 @@ 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
 
 
@@ -1603,8 +1602,7 @@ def check_docker_connection() -> Any:
 
     try:
         return docker.from_env()
-    except DockerException as exc:
-        report_error("docker_unavailable", exc)
+    except DockerException:
         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 = _state_label(summary)
+    state_label = "[#eab308]live[/]" if live else "[#22c55e]finished[/]"
     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
@@ -107,18 +107,6 @@ 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

@@ -8,7 +8,6 @@ import {
   Radar,
   Rocket,
   ArrowUpRight,
-  Building2,
   History,
 } from "lucide-react";
 import type { Vulnerability, VulnerabilitySeverity } from "@/types/issues";
@@ -36,7 +35,7 @@ import {
   type LoadedRun,
   type RunsPayload,
 } from "@/data/serverSource";
-import { SIGNUP_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, ctaUrl, trackCta } from "@/lib/cta";
 import { runTitle } from "@/lib/target-utils";
 import Sidebar from "@/components/Sidebar";
 import PastRunsView from "@/components/PastRunsView";
@@ -707,31 +706,6 @@ 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) => (
@@ -815,23 +789,14 @@ 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]">Run this pentest again in Strix Cloud.</p>
+        <p className="mt-0.5 text-xs text-[#666]">Re-run this pentest on managed infra in the cloud.</p>
         <div className="mt-3 flex flex-wrap gap-2.5">
           <ProInlineCta
             label="Re-run in Strix Pro with more depth"
-            desc="More depth, validated findings, and autofix."
+            desc="Run this pentest on managed infra with more depth."
             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

@@ -48,40 +48,23 @@ 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(href, slug)}
+        href={ctaUrl(SIGNUP_URL, slug)}
         target="_blank"
         rel="noopener noreferrer"
         onClick={() => trackCta(slug, surface)}
-        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"
-        }
+        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"
       >
-        <Icon
-          className={
-            primary
-              ? "h-4 w-4 text-black"
-              : "h-4 w-4 text-[#888] transition-colors group-hover:text-white"
-          }
-          aria-hidden="true"
-        />
+        <Icon className="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/UpgradeModal.tsx

@@ -10,7 +10,7 @@ import {
   WandSparkles,
   Plug,
 } from "lucide-react";
-import { SIGNUP_URL, PRICING_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, PRICING_URL, ctaUrl, trackCta } from "@/lib/cta";
 
 /**
  * Dialog shown when a platform feature is clicked in the sidebar: a short
@@ -141,19 +141,6 @@ 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/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-B94ANU8d.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-DN__rVv3.css">
+    <script type="module" crossorigin src="./assets/index-Bpn8GiSb.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-qwPOPAGC.css">
   </head>
   <body>
     <div id="root"></div>

strix/llm/warmup.py

@@ -1,22 +1,20 @@
 """Background pre-import of the heavy scan dependencies.
 
 The scan engine's import graph (the agents SDK, OpenAI client, LiteLLM, the
-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.
+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.
 """
 
 from __future__ import annotations
 
 import importlib
 import logging
+import sys
 import threading
 
 
@@ -26,17 +24,45 @@ 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:
@@ -46,15 +72,11 @@ def start_import_warmup(modules: tuple[str, ...] = WARMUP_MODULES) -> threading.
     runtime that has no local Docker) warm a narrower set.
     """
     global _thread  # noqa: PLW0603
-    if _thread is None:
+    with _lock:
+        if _thread is not None:
+            return _thread
         _thread = threading.Thread(
             target=_warm, args=(modules,), name="strix-import-warmup", daemon=True
         )
         _thread.start()
-    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()
+        return _thread

strix/report/state.py

@@ -167,7 +167,7 @@ def get_global_report_state() -> Optional["ReportState"]:
     return _global_report_state
 
 
-def set_global_report_state(report_state: Optional["ReportState"]) -> None:
+def set_global_report_state(report_state: "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.

strix/skills/__init__.py

@@ -1,5 +1,6 @@
 import logging
 import re
+import threading
 from collections import Counter
 from collections.abc import Iterator
 from pathlib import Path
@@ -7,6 +8,7 @@ from typing import TypeGuard
 
 import yaml
 
+from strix.telemetry import posthog, scarf
 from strix.utils.resource_paths import get_strix_resource_path
 
 
@@ -239,19 +241,16 @@ 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)
 
-def get_loaded_skill_names() -> list[str]:
-    """Distinct skills loaded so far in this process (custom skills collapse to ``"custom"``)."""
-    return sorted(_LOADED_SKILLS)
+    threading.Thread(target=_send, daemon=True).start()
 
 
 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, the failure category, the scan phase, and the exception class name (not messages or stack traces)\
+**Session Errors:** Duration and error types (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 were used during a scan (reported once, at scan end)\
+**Feature Usage:** Which built-in skills are loaded\
 **Aggregate Metrics:** Vulnerability counts by severity and weakness category (CWE)
 
 ### What We **Never** Collect

strix/telemetry/__init__.py

@@ -1,19 +1,7 @@
 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, cast
+from typing import Any
 from uuid import uuid4
 
 
@@ -54,43 +54,3 @@ 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

@@ -4,14 +4,10 @@ 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,
 )
 
@@ -39,12 +35,7 @@ def _send(event: str, properties: dict[str, Any]) -> bool:
             "api_key": _POSTHOG_PUBLIC_API_KEY,
             "event": event,
             "distinct_id": SESSION_ID,
-            "properties": {
-                **properties,
-                "$lib": "strix-cli",
-                "$lib_version": get_version(),
-                "$process_person_profile": False,
-            },
+            "properties": properties,
         }
         with requests.post(f"{_POSTHOG_HOST}/capture/", json=payload, timeout=SEND_TIMEOUT):
             pass
@@ -91,6 +82,16 @@ 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
@@ -129,7 +130,6 @@ 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(),
         },
     )
 
@@ -180,12 +180,6 @@ def viewer_agent_steered() -> None:
     _send("viewer_agent_steered", {**base_props()})
 
 
-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))
+def error(error_type: str) -> None:
+    props = {**base_props(), "error_type": error_type}
     _send("error", props)

strix/telemetry/scarf.py

@@ -7,13 +7,10 @@ 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,
 )
@@ -93,6 +90,17 @@ 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
@@ -132,18 +140,14 @@ 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, exc: BaseException | None = None) -> None:
+def error(error_type: str) -> 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

@@ -15,7 +15,6 @@ 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
 
 
@@ -29,40 +28,6 @@ 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,
@@ -73,7 +38,6 @@ 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.
 
@@ -99,12 +63,6 @@ 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)
@@ -191,11 +149,8 @@ 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. In interactive runs a message wakes the target regardless of
+    flow. Messages to any registered agent wake it, 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.
@@ -240,23 +195,10 @@ 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": error,
-                "target_agent_id": target_agent_id,
-                "target_status": status,
-                "delivery_status": "not_delivered",
+                "error": f"Target agent '{target_agent_id}' not found or message delivery failed",
             },
             ensure_ascii=False,
             default=str,
@@ -422,31 +364,6 @@ 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)
@@ -693,9 +610,6 @@ 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:
@@ -709,7 +623,6 @@ 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,
@@ -719,7 +632,6 @@ async def agent_finish(
                 "content": report,
                 "type": "completion",
                 "priority": "high",
-                "filed_report_ids": filed_report_ids,
             },
         )
         parent_notified = True
@@ -730,11 +642,10 @@ async def agent_finish(
         await notify_parent_on_terminal(coordinator, me, "completed")
 
     logger.info(
-        "agent_finish: %s success=%s findings=%d filed_reports=%d parent_notified=%s",
+        "agent_finish: %s success=%s findings=%d parent_notified=%s",
         me,
         success,
         len(findings or []),
-        len(filed_report_ids),
         parent_notified,
     )
 
@@ -745,7 +656,6 @@ 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/web_search/tool.py

@@ -1,12 +1,11 @@
-"""Security-focused web research tools (Exa or Perplexity)."""
+"""``web_search`` — Perplexity-backed security-focused web search."""
 
 from __future__ import annotations
 
 import asyncio
 import json
 import logging
-from typing import TYPE_CHECKING, Any, cast
-from urllib.parse import urlsplit, urlunsplit
+from typing import Any
 
 import requests
 from agents import RunContextWrapper, function_tool
@@ -14,10 +13,6 @@ from agents import RunContextWrapper, function_tool
 from strix.config import load_settings
 
 
-if TYPE_CHECKING:
-    from collections.abc import Callable
-
-
 logger = logging.getLogger(__name__)
 
 
@@ -46,7 +41,22 @@ Structure your response to be comprehensive yet concise, emphasizing the most cr
 security implications and details."""
 
 
-def _perplexity_content(api_key: str, query: str) -> str:
+def _do_search(query: str) -> dict[str, Any]:  # noqa: PLR0911 - each error class needs its own sanitized return
+    if not query or not query.strip():
+        return {"success": False, "error": "Query cannot be empty"}
+
+    api_key = load_settings().integrations.perplexity_api_key
+    if not api_key:
+        logger.warning("web_search invoked without PERPLEXITY_API_KEY configured")
+        return {
+            "success": False,
+            "error": (
+                "Web search is not configured for this scan "
+                "(operator needs to set PERPLEXITY_API_KEY). Proceed without it"
+            ),
+        }
+    logger.info("web_search query (len=%d): %s", len(query), query[:120])
+
     url = "https://api.perplexity.ai/chat/completions"
     headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
     payload = {
@@ -56,269 +66,61 @@ def _perplexity_content(api_key: str, query: str) -> str:
             {"role": "user", "content": query},
         ],
     }
-    with requests.post(url, headers=headers, json=payload, timeout=300) as response:
-        response.raise_for_status()
-        return str(response.json()["choices"][0]["message"]["content"])
 
-
-_EXA_PAGE_MAX_CHARS = 20000
-_EXA_MAX_CONTENT_URLS = 10
-_EXA_SUMMARY_PROMPT = (
-    "Summarize this page for a penetration tester. Keep concrete technical detail: "
-    "affected products and exact versions, CVE and CWE identifiers, CVSS scores, "
-    "exploitation preconditions, payloads or commands, and mitigations. "
-    "Leave out marketing copy and navigation text."
-)
-
-
-def _exa_result_block(result: dict[str, Any]) -> str | None:
-    result_url = str(result.get("url") or result.get("id") or "")
-    if not result_url:
-        return None
-    title = str(result.get("title") or result_url)
-    parts = [f"### {title}\n{result_url}"]
-    summary = str(result.get("summary") or "").strip()
-    if summary:
-        parts.append(summary)
-    return "\n".join(parts)
-
-
-def _exa_page_block(result: dict[str, Any]) -> str | None:
-    result_url = str(result.get("url") or result.get("id") or "")
-    text = str(result.get("text") or "").strip()
-    if not result_url or not text:
-        return None
-    if len(text) > _EXA_PAGE_MAX_CHARS:
-        text = f"{text[:_EXA_PAGE_MAX_CHARS]}\n[truncated at {_EXA_PAGE_MAX_CHARS} characters]"
-    title = str(result.get("title") or result_url)
-    return f"### {title}\n{result_url}\n\n{text}"
-
-
-def _exa_blocks(
-    results: list[Any],
-    render: Callable[[dict[str, Any]], str | None],
-) -> list[str]:
-    blocks: list[str] = []
-    for result in results:
-        if not isinstance(result, dict):
-            continue
-        block = render(cast("dict[str, Any]", result))
-        if block:
-            blocks.append(block)
-    return blocks
-
-
-def _exa_post(api_key: str, endpoint: str, payload: dict[str, Any]) -> dict[str, Any]:
-    headers = {"x-api-key": api_key, "Content-Type": "application/json"}
-    with requests.post(endpoint, headers=headers, json=payload, timeout=300) as response:
-        response.raise_for_status()
-        body: dict[str, Any] = response.json()
-    return body
-
-
-def _exa_content(api_key: str, query: str, search_type: str, num_results: int) -> str:
-    body = _exa_post(
-        api_key,
-        "https://api.exa.ai/search",
-        {
-            "query": f"{_SYSTEM_PROMPT}\n\n{query}",
-            "type": search_type,
-            "numResults": num_results,
-            "contents": {"summary": {"query": _EXA_SUMMARY_PROMPT}},
-        },
-    )
-    blocks = _exa_blocks(body.get("results") or [], _exa_result_block)
-    if not blocks:
-        raise ValueError("Exa response has no results")
-    return "\n\n".join(blocks)
-
-
-def _normalize_url(url: str) -> str:
-    """Canonical form for matching: case-fold scheme and host only, drop a trailing slash."""
-    parts = urlsplit(url.strip())
-    return urlunsplit(
-        (parts.scheme.lower(), parts.netloc.lower(), parts.path.rstrip("/"), parts.query, "")
-    )
-
-
-def _exa_page_text(api_key: str, urls: list[str]) -> tuple[str, set[str]]:
-    """Fetch page text and report which of the requested URLs Exa returned."""
-    body = _exa_post(api_key, "https://api.exa.ai/contents", {"urls": urls, "text": True})
-    blocks: list[str] = []
-    fetched: set[str] = set()
-    results: list[Any] = body.get("results") or []
-    for result in results:
-        if not isinstance(result, dict):
-            continue
-        page = cast("dict[str, Any]", result)
-        block = _exa_page_block(page)
-        if not block:
-            continue
-        blocks.append(block)
-        fetched.add(_normalize_url(str(page.get("url") or page.get("id") or "")))
-    if not blocks:
-        raise ValueError("Exa returned no page contents")
-    return "\n\n".join(blocks), fetched
-
-
-def _resolve_provider(  # noqa: PLR0911 - each provider/missing-key case needs its own return
-    integrations: Any,
-) -> tuple[str, str] | dict[str, Any]:
-    """Pick the search provider and its key, or return a sanitized error dict."""
-    provider = integrations.web_search_provider
-    perplexity_key = integrations.perplexity_api_key
-    exa_key = integrations.exa_api_key
-
-    if provider == "perplexity":
-        if not perplexity_key:
-            return _not_configured_error("PERPLEXITY_API_KEY")
-        return ("perplexity", perplexity_key)
-    if provider == "exa":
-        if not exa_key:
-            return _not_configured_error("EXA_API_KEY")
-        return ("exa", exa_key)
-
-    if exa_key:
-        return ("exa", exa_key)
-    if perplexity_key:
-        return ("perplexity", perplexity_key)
-    return _not_configured_error("EXA_API_KEY or PERPLEXITY_API_KEY")
-
-
-def _not_configured_error(missing: str) -> dict[str, Any]:
-    logger.warning("web_search invoked without %s configured", missing)
-    return {
-        "success": False,
-        "error": (
-            "Web search is not configured for this scan "
-            f"(operator needs to set {missing}). Proceed without it"
-        ),
-    }
-
-
-def _guarded_call[T](  # noqa: PLR0911 - each error class needs its own sanitized return
-    tool: str,
-    rejected_hint: str,
-    fetch: Callable[[], T],
-) -> T | dict[str, Any]:
-    """Run a provider call and translate any failure into a sanitized error dict."""
     try:
-        return fetch()
+        with requests.post(url, headers=headers, json=payload, timeout=300) as response:
+            response.raise_for_status()
+            content = response.json()["choices"][0]["message"]["content"]
     except requests.exceptions.Timeout:
-        logger.warning("%s timed out", tool)
-        return {"success": False, "error": f"{tool} timed out. Try again or narrow the request"}
+        logger.warning("web_search timed out")
+        return {
+            "success": False,
+            "error": "Web search timed out. Try again or shorten the query",
+        }
     except requests.exceptions.HTTPError as exc:
         status = exc.response.status_code if exc.response is not None else None
-        logger.exception("%s HTTP error status=%s", tool, status)
+        logger.exception("web_search HTTP error status=%s", status)
         if status is not None and 400 <= status < 500:
-            return {"success": False, "error": rejected_hint}
-        return {"success": False, "error": f"{tool} service is unavailable. Try again later"}
+            return {
+                "success": False,
+                "error": (
+                    "Web search rejected the query. Refine it "
+                    "(more specific, shorter, no unusual characters) and retry"
+                ),
+            }
+        return {
+            "success": False,
+            "error": "Web search service is unavailable. Try again later",
+        }
     except requests.exceptions.RequestException:
-        logger.exception("%s network error", tool)
-        return {"success": False, "error": f"{tool} network error. Try again later"}
+        logger.exception("web_search network error")
+        return {
+            "success": False,
+            "error": "Web search network error. Try again later",
+        }
     except (KeyError, IndexError, ValueError):
-        logger.exception("%s response shape unexpected", tool)
-        return {"success": False, "error": f"{tool} returned an unexpected response. Try again"}
+        logger.exception("web_search response shape unexpected")
+        return {
+            "success": False,
+            "error": "Web search returned an unexpected response. Try again",
+        }
     except Exception:
-        logger.exception("%s failed", tool)
-        return {"success": False, "error": f"{tool} failed unexpectedly"}
-
-
-def _do_search(query: str) -> dict[str, Any]:
-    if not query or not query.strip():
-        return {"success": False, "error": "Query cannot be empty"}
-
-    integrations = load_settings().integrations
-    resolved = _resolve_provider(integrations)
-    if isinstance(resolved, dict):
-        return resolved
-    provider, api_key = resolved
-    logger.info("web_search provider=%s query (len=%d): %s", provider, len(query), query[:120])
-
-    def fetch() -> str:
-        if provider == "exa":
-            return _exa_content(
-                api_key,
-                query,
-                integrations.exa_search_type,
-                integrations.exa_num_results,
-            )
-        return _perplexity_content(api_key, query)
-
-    outcome = _guarded_call(
-        "Web search",
-        (
-            "Web search rejected the query. Refine it "
-            "(more specific, shorter, no unusual characters) and retry"
-        ),
-        fetch,
-    )
-    if isinstance(outcome, dict):
-        return outcome
-    return {
-        "success": True,
-        "query": query,
-        "provider": provider,
-        "content": outcome,
-    }
-
-
-def _do_get_contents(urls: list[str]) -> dict[str, Any]:
-    cleaned = [url.strip() for url in urls if url and url.strip()]
-    if not cleaned:
-        return {"success": False, "error": "Provide at least one URL"}
-    if len(cleaned) > _EXA_MAX_CONTENT_URLS:
+        logger.exception("web_search failed")
         return {
             "success": False,
-            "error": f"Too many URLs. Pass at most {_EXA_MAX_CONTENT_URLS} per call",
+            "error": "Web search failed unexpectedly",
         }
-
-    integrations = load_settings().integrations
-    api_key = integrations.exa_api_key
-    if not api_key:
-        return _not_configured_error("EXA_API_KEY")
-    if integrations.web_search_provider == "perplexity":
-        logger.warning("web_get_contents invoked while the provider is pinned to Perplexity")
+    else:
         return {
-            "success": False,
-            "error": (
-                "Page fetching needs the Exa provider "
-                "(operator pinned STRIX_WEB_SEARCH_PROVIDER to perplexity). "
-                "Use web_search instead"
-            ),
+            "success": True,
+            "query": query,
+            "content": content,
         }
 
-    logger.info("web_get_contents urls=%d", len(cleaned))
-    outcome = _guarded_call(
-        "Page fetch",
-        "Page fetch was rejected. Check the URLs are complete, public, and correctly formed",
-        lambda: _exa_page_text(api_key, cleaned),
-    )
-    if isinstance(outcome, dict):
-        return outcome
-    content, fetched = outcome
-    missing = [url for url in cleaned if _normalize_url(url) not in fetched]
-    result: dict[str, Any] = {
-        "success": True,
-        "urls": [url for url in cleaned if url not in missing],
-        "provider": "exa",
-        "content": content,
-    }
-    if missing:
-        logger.warning(
-            "web_get_contents returned %d of %d pages", len(cleaned) - len(missing), len(cleaned)
-        )
-        result["failed_urls"] = missing
-        result["warning"] = (
-            f"Exa returned no content for {len(missing)} of {len(cleaned)} requested URLs. "
-            "Those pages are missing from the content below"
-        )
-    return result
-
 
 @function_tool(timeout=330)
 async def web_search(ctx: RunContextWrapper, query: str) -> str:
-    """Real-time web search (Exa or Perplexity) — your primary research tool.
+    """Real-time web search via Perplexity — your primary research tool.
 
     Use it liberally for anything that's not in your training data:
 
@@ -348,12 +150,6 @@ async def web_search(ctx: RunContextWrapper, query: str) -> str:
     exploits, Kali-compatible tooling, and concrete code/command
     examples.
 
-    With the Exa provider you get a ranked list of results, each with a
-    title, URL, and a short security-focused summary. Read the result
-    you need, then call ``web_get_contents`` with its URL to pull the
-    full page text when a summary is not enough. With Perplexity you get
-    a single synthesized cited answer.
-
     **Good example queries** (each is a full sentence, names a
     version/product, and asks one concrete thing):
 
@@ -381,33 +177,3 @@ async def web_search(ctx: RunContextWrapper, query: str) -> str:
     """
     result = await asyncio.to_thread(_do_search, query)
     return json.dumps(result, ensure_ascii=False, default=str)
-
-
-@function_tool(timeout=330)
-async def web_get_contents(ctx: RunContextWrapper, urls: list[str]) -> str:
-    """Fetch the full, cleaned text of specific web pages (Exa only).
-
-    Use this as the drill-down step after ``web_search``: when a result's
-    summary is not enough, pass that result's URL here to read the whole
-    page. Good for reading a full advisory, a CVE writeup,
-    an exploit proof-of-concept, or vendor documentation end to end.
-
-    Prefer ``web_search`` first to find the right pages, then fetch only
-    the few URLs worth reading in full — each page can be large, so avoid
-    fetching many pages you do not need.
-
-    This tool needs the Exa provider (``EXA_API_KEY``). When the operator
-    pins the provider to Perplexity, it returns an error and you should
-    use ``web_search`` instead.
-
-    Some pages block extraction. When a page returns no content, the
-    result lists it under ``failed_urls`` and the ``content`` field holds
-    only the pages that came back. Check ``failed_urls`` before you
-    conclude that a page had nothing useful.
-
-    Args:
-        urls: The page URLs to fetch, at most 10 per call. Use complete,
-            public URLs (for example the ones returned by ``web_search``).
-    """
-    result = await asyncio.to_thread(_do_get_contents, urls)
-    return json.dumps(result, ensure_ascii=False, default=str)

tests/conftest.py

@@ -24,30 +24,3 @@ def _isolate_mcp_config(
     monkeypatch.setenv("STRIX_MCP_CONFIG", str(missing))
     monkeypatch.delenv("STRIX_MCP_ONLY", raising=False)
     monkeypatch.delenv("STRIX_MCP_EXCLUDE", raising=False)
-
-
-@pytest.fixture(autouse=True)
-def _plain_terminal(monkeypatch: pytest.MonkeyPatch) -> None:
-    """Make Rich output identical on every developer's machine.
-
-    Many CLI tests force ``isatty()`` to ``True`` to exercise the human-readable
-    code path and then assert on the plain text. Rich picks its color system
-    from ``TERM``, ``COLORTERM``, and ``FORCE_COLOR``, so on a real terminal
-    those assertions would meet ANSI escape codes instead of the words they
-    look for. A dumb terminal renders the same text without any styling.
-    """
-    monkeypatch.setenv("TERM", "dumb")
-    for name in ("COLORTERM", "FORCE_COLOR", "NO_COLOR", "TTY_COMPATIBLE"):
-        monkeypatch.delenv(name, raising=False)
-
-
-@pytest.fixture(autouse=True)
-def _isolate_wallet_config(monkeypatch: pytest.MonkeyPatch) -> None:
-    """Keep a developer's real mppx wallet out of the top-up tests.
-
-    ``strix cloud billing topup`` chooses the Stripe Link flow or the
-    preconfigured mppx wallet from these variables, so leaving them set would
-    silently switch which branch a test runs.
-    """
-    for name in ("MPPX_ACCOUNT", "MPPX_STRIPE_SECRET_KEY", "MPPX_STRIPE_PAYMENT_METHOD"):
-        monkeypatch.delenv(name, raising=False)

tests/test_agent_graph_coordination.py

@@ -1,258 +0,0 @@
-"""Tests for parent/child coordination once a non-interactive child has finished.
-
-A non-interactive agent's loop returns after its terminal state, so nothing will
-ever read a message sent to it afterwards. Messaging it must say so instead of
-reporting delivery, waiting on it must return at once, and its completion report
-must carry the ids of the reports it actually filed so the parent does not have
-to go asking.
-"""
-
-from __future__ import annotations
-
-import json
-from typing import TYPE_CHECKING, Any, cast
-
-import pytest
-from agents.tool_context import ToolContext
-
-from strix.core.agents import AgentCoordinator
-from strix.report.state import ReportState, set_global_report_state
-from strix.tools.agents_graph.tools import agent_finish, send_message_to_agent, wait_for_agents
-
-
-if TYPE_CHECKING:
-    from collections.abc import Iterator
-    from pathlib import Path
-
-
-@pytest.fixture
-def report_state(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Iterator[ReportState]:
-    monkeypatch.chdir(tmp_path)
-    state = ReportState(run_name="test-run")
-    set_global_report_state(state)
-    yield state
-    set_global_report_state(None)
-
-
-async def _graph(*, interactive: bool) -> AgentCoordinator:
-    coordinator = AgentCoordinator()
-    await coordinator.register("root", "strix", parent_id=None)
-    await coordinator.register("child", "Validator", parent_id="root")
-    await coordinator.attach_runtime("root", resumable=interactive)
-    await coordinator.attach_runtime("child", resumable=interactive)
-    return coordinator
-
-
-async def _call(
-    tool: Any, coordinator: AgentCoordinator, agent_id: str, args: dict[str, Any], **extra: Any
-) -> dict[str, Any]:
-    ctx = ToolContext(
-        context={"coordinator": coordinator, "agent_id": agent_id, **extra},
-        tool_name=tool.name,
-        tool_call_id="call-1",
-        tool_arguments="{}",
-    )
-    raw: str = await tool.on_invoke_tool(ctx, json.dumps(args))
-    return cast("dict[str, Any]", json.loads(raw))
-
-
-# --- send_message_to_agent -------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_message_to_finished_non_interactive_child_is_not_delivered() -> None:
-    coordinator = await _graph(interactive=False)
-    await coordinator.set_status("child", "completed")
-
-    result = await _call(
-        send_message_to_agent,
-        coordinator,
-        "root",
-        {"target_agent_id": "child", "message": "did you file it?", "message_type": "query"},
-    )
-
-    assert result["success"] is False
-    assert result["delivery_status"] == "not_delivered"
-    assert result["target_status"] == "completed"
-    assert "list_reports" in result["error"]
-    assert coordinator.pending_counts.get("child", 0) == 0
-    assert coordinator.runtimes["child"].mailbox == []
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("status", ["stopped", "failed", "crashed"])
-async def test_every_terminal_non_interactive_status_is_unreachable(status: str) -> None:
-    coordinator = await _graph(interactive=False)
-    await coordinator.set_status("child", status)
-
-    assert await coordinator.send("child", {"from": "root", "content": "hi"}) is False
-    assert await coordinator.reachability("child") == (False, status)
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("status", ["running", "waiting"])
-async def test_message_to_live_child_is_delivered(status: str) -> None:
-    coordinator = await _graph(interactive=False)
-    await coordinator.set_status("child", status)
-
-    result = await _call(
-        send_message_to_agent,
-        coordinator,
-        "root",
-        {"target_agent_id": "child", "message": "wrap up"},
-    )
-
-    assert result["success"] is True
-    assert result["delivery_status"] == "delivered"
-    assert coordinator.pending_counts["child"] == 1
-
-
-@pytest.mark.asyncio
-async def test_message_to_finished_interactive_child_still_wakes_it() -> None:
-    # An interactive loop parks after finishing and resumes on a message.
-    coordinator = await _graph(interactive=True)
-    await coordinator.set_status("child", "completed")
-
-    result = await _call(
-        send_message_to_agent,
-        coordinator,
-        "root",
-        {"target_agent_id": "child", "message": "one more thing"},
-    )
-
-    assert result["success"] is True
-    assert coordinator.pending_counts["child"] == 1
-
-
-@pytest.mark.asyncio
-async def test_unknown_target_is_reported_as_not_found() -> None:
-    coordinator = await _graph(interactive=False)
-
-    result = await _call(
-        send_message_to_agent,
-        coordinator,
-        "root",
-        {"target_agent_id": "ghost", "message": "hello"},
-    )
-
-    assert result["success"] is False
-    assert result["target_status"] is None
-    assert "not found" in result["error"]
-
-
-# --- wait_for_agents -------------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_wait_returns_at_once_when_no_child_can_answer() -> None:
-    coordinator = await _graph(interactive=False)
-    await coordinator.set_status("child", "completed")
-    # The completion report was already consumed in an earlier turn.
-
-    result = await _call(
-        wait_for_agents,
-        coordinator,
-        "root",
-        {"reason": "waiting for validator", "timeout_seconds": 240},
-    )
-
-    assert result["wait_outcome"] == "no_active_agents"
-    assert result["agents"] == [{"agent_id": "child", "name": "Validator", "status": "completed"}]
-    assert coordinator.statuses["root"] == "running"
-
-
-@pytest.mark.asyncio
-async def test_wait_delivers_a_pending_report_before_checking_liveness() -> None:
-    coordinator = await _graph(interactive=False)
-    await coordinator.send("root", {"from": "child", "type": "completion", "content": "done"})
-    await coordinator.set_status("child", "completed")
-
-    result = await _call(wait_for_agents, coordinator, "root", {"timeout_seconds": 5})
-
-    assert result["wait_outcome"] == "message_arrived"
-    assert result["pending_messages"] == 1
-
-
-@pytest.mark.asyncio
-async def test_wait_still_parks_while_a_child_is_running() -> None:
-    coordinator = await _graph(interactive=False)
-
-    result = await _call(wait_for_agents, coordinator, "root", {"timeout_seconds": 1})
-
-    assert result["wait_outcome"] == "timeout"
-
-
-@pytest.mark.asyncio
-async def test_interactive_wait_parks_even_without_active_children() -> None:
-    # In an interactive run a finished child can be woken later, so parking is
-    # legitimate; the run loop's own auto-resume bounds the wait.
-    coordinator = await _graph(interactive=True)
-    await coordinator.set_status("child", "completed")
-
-    result = await _call(
-        wait_for_agents, coordinator, "root", {"timeout_seconds": 5}, interactive=True
-    )
-
-    assert result["wait_outcome"] == "waiting"
-
-
-# --- agent_finish ----------------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_agent_finish_lists_the_reports_the_child_filed(report_state: ReportState) -> None:
-    coordinator = await _graph(interactive=False)
-    mine = report_state.add_vulnerability_report(
-        title="IDOR on /api/audits", severity="high", agent_id="child", agent_name="Validator"
-    )
-    report_state.add_vulnerability_report(title="Root's own", severity="low", agent_id="root")
-
-    result = await _call(
-        agent_finish,
-        coordinator,
-        "child",
-        {"result_summary": "confirmed", "findings": ["IDOR confirmed"]},
-        parent_id="root",
-    )
-
-    assert result["filed_report_ids"] == [mine]
-    delivered = coordinator.runtimes["root"].mailbox
-    assert len(delivered) == 1
-    assert delivered[0]["filed_report_ids"] == [mine]
-    body = delivered[0]["content"]
-    assert f"- {mine} [HIGH] IDOR on /api/audits" in body
-    assert "Root's own" not in body
-
-
-@pytest.mark.asyncio
-async def test_agent_finish_states_explicitly_when_nothing_was_filed(
-    report_state: ReportState,
-) -> None:
-    coordinator = await _graph(interactive=False)
-    report_state.add_vulnerability_report(title="Someone else's", severity="low", agent_id="root")
-
-    result = await _call(
-        agent_finish,
-        coordinator,
-        "child",
-        {"result_summary": "nothing exploitable", "findings": ["ruled out X"]},
-        parent_id="root",
-    )
-
-    assert result["filed_report_ids"] == []
-    body = coordinator.runtimes["root"].mailbox[0]["content"]
-    assert "Vulnerability reports filed by this agent" in body
-    assert body.index("filed by this agent") < body.index("- (none)")
-
-
-@pytest.mark.asyncio
-async def test_agent_finish_without_report_state_still_completes() -> None:
-    set_global_report_state(None)
-    coordinator = await _graph(interactive=False)
-
-    result = await _call(
-        agent_finish, coordinator, "child", {"result_summary": "done"}, parent_id="root"
-    )
-
-    assert result["success"] is True
-    assert result["filed_report_ids"] == []

tests/test_cloud_cli.py

@@ -6,7 +6,6 @@ import io
 import json
 import shutil
 import subprocess
-import sys
 import urllib.request
 import webbrowser
 from pathlib import Path
@@ -17,7 +16,7 @@ import requests
 from rich.console import Console
 
 from strix.interface import cloud, platform_cli
-from strix.interface.cloud import http, render, runner, workspaces
+from strix.interface.cloud import billing, http, payment_proxy, render, runner, workspaces
 from strix.interface.cloud.spec import GROUP_HELP, SPEC
 
 
@@ -148,7 +147,7 @@ def test_read_groups_have_safe_defaults(group: str, verb: str) -> None:
     resolved = runner.resolve(group, [])
     assert resolved is not None
     command, remaining = resolved
-    assert command is SPEC[group][verb]
+    assert command is runner.SPEC[group][verb]
     assert remaining == []
 
 
@@ -534,69 +533,6 @@ def test_insufficient_credits_exits_with_payment_code(monkeypatch: pytest.Monkey
     assert cloud.run_cloud(["scans", "start", "--domain-ids", "d1"]) == http.EXIT_PAYMENT
 
 
-def test_insufficient_credits_always_prints_topup_instruction(
-    monkeypatch: pytest.MonkeyPatch, capsys: Any
-) -> None:
-    monkeypatch.setattr(
-        http,
-        "request",
-        lambda *_a, **_k: FakeResponse(
-            status_code=402,
-            payload={"detail": "Out of credits.", "code": "scan_credit_limit_reached"},
-        ),
-    )
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
-    argv = ["scans", "start", "--domain-ids", "d1", "--app-url", "https://app.strix.ai"]
-    assert cloud.run_cloud(argv) == http.EXIT_PAYMENT
-    output = " ".join(capsys.readouterr().out.split())
-    assert "Error: Out of credits." in output
-    assert "Next step:" in output
-    assert "strix cloud billing topup --credits <count>" in output
-    assert "https://app.strix.ai/settings/billing" in output
-    assert "strix cloud billing credits" in output
-
-
-def test_insufficient_credits_shows_platform_hint_once(
-    monkeypatch: pytest.MonkeyPatch, capsys: Any
-) -> None:
-    hint = "Buy credits at https://app.strix.ai/settings/billing. Then retry this request."
-    payload = {
-        "detail": f"Out of credits. {hint}",
-        "code": "scan_credit_limit_reached",
-        "hint": hint,
-        "topup_url": "https://app.strix.ai/settings/billing",
-    }
-    monkeypatch.setattr(
-        http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=payload)
-    )
-    assert cloud.run_cloud(["scans", "start", "--domain-ids", "d1", "--json"]) == http.EXIT_PAYMENT
-    result = json.loads(capsys.readouterr().out)
-    assert result["error"] == "Out of credits."
-    assert result["next_step"] == hint
-    assert result["topup_url"] == "https://app.strix.ai/settings/billing"
-
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
-    assert cloud.run_cloud(["scans", "start", "--domain-ids", "d1"]) == http.EXIT_PAYMENT
-    output = " ".join(capsys.readouterr().out.split())
-    assert output.count(hint) == 1
-    assert "Error: Out of credits." in output
-    assert f"Next step: {hint}" in output
-
-
-def test_payment_required_without_body_names_the_topup_command(
-    monkeypatch: pytest.MonkeyPatch, capsys: Any
-) -> None:
-    monkeypatch.setattr(
-        http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload={})
-    )
-    argv = ["scans", "start", "--domain-ids", "d1", "--json", "--app-url", "https://app.strix.ai"]
-    assert cloud.run_cloud(argv) == http.EXIT_PAYMENT
-    result = json.loads(capsys.readouterr().out)
-    assert result["error"] == "Not enough credits to run this command."
-    assert "strix cloud billing topup --credits <count>" in result["next_step"]
-    assert "https://app.strix.ai/settings/billing" in result["next_step"]
-
-
 def test_data_rejects_non_object() -> None:
     assert cloud.run_cloud(["scans", "start", "--data", "[1,2]"]) == http.EXIT_USAGE
     assert cloud.run_cloud(["scans", "start", "--data", "not json"]) == http.EXIT_USAGE
@@ -625,7 +561,7 @@ def test_stored_token_is_never_sent_to_a_different_platform_origin(
         lambda: {"api_token": "stored-secret", "app_url": "https://app.strix.ai"},
     )
     monkeypatch.setattr(
-        requests,
+        http.requests,
         "request",
         lambda *_args, **_kwargs: pytest.fail("a mismatched origin must not receive the token"),
     )
@@ -640,7 +576,7 @@ def test_stored_token_requires_an_issuer_binding(monkeypatch: pytest.MonkeyPatch
     monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
     monkeypatch.setattr(http, "read_record", lambda: {"api_token": "legacy-secret"})
     monkeypatch.setattr(
-        requests,
+        http.requests,
         "request",
         lambda *_args, **_kwargs: pytest.fail("an unbound token must not be sent"),
     )
@@ -666,7 +602,7 @@ def test_stored_token_is_sent_only_to_its_bound_platform(
         seen.update(url=url, headers=kwargs["headers"])
         return FakeResponse(payload={"balance": 1})
 
-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
     response = http.request("GET", "/billing/credits")
 
     assert response.status_code == 200
@@ -690,7 +626,7 @@ def test_explicit_token_can_target_an_explicit_platform(
         seen.update(url=url, headers=kwargs["headers"])
         return FakeResponse(payload={"balance": 1})
 
-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
     override_value = "explicit-preview-" + str(1)
     response = http.request("GET", "/billing/credits", token=override_value)
 
@@ -770,9 +706,9 @@ def test_topup_noninteractive_requires_explicit_payment_approval(
     monkeypatch.setattr(
         http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
     )
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: False)
+    monkeypatch.setattr(runner.sys.stdin, "isatty", lambda: False)
     monkeypatch.setattr(
-        subprocess,
+        billing.subprocess,
         "run",
         lambda *_a, **_k: pytest.fail("wallet must not run without --yes"),
     )
@@ -796,10 +732,10 @@ def test_topup_machine_output_never_prompts_even_with_terminal_stdin(
     monkeypatch.setattr(
         http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
     )
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: stdout_tty)
+    monkeypatch.setattr(runner.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: stdout_tty)
     monkeypatch.setattr(
-        Console,
+        runner.Console,
         "input",
         lambda *_a, **_k: pytest.fail("machine-readable top-up must not prompt"),
     )
@@ -903,7 +839,7 @@ def test_topup_keeps_token_out_of_wallet_process_and_forwards_payment(
         upstream.update(method=method, url=url, **kwargs)
         return FakeResponse(payload=receipt, content=json.dumps(receipt).encode())
 
-    monkeypatch.setattr(requests, "request", fake_upstream_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_upstream_request)
 
     def fake_run(command: list[str], **kwargs: Any) -> Any:
         commands.append(command)
@@ -969,7 +905,6 @@ def test_topup_wallet_failure_is_one_redacted_json_object(
         http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
         subprocess,
@@ -1011,7 +946,6 @@ def test_topup_wallet_interruption_reports_unknown_payment_outcome(
         ),
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
         subprocess, "run", lambda *_a, **_k: (_ for _ in ()).throw(KeyboardInterrupt)
@@ -1037,7 +971,6 @@ def test_topup_non_json_wallet_success_requires_balance_verification(
         ),
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
         subprocess,
@@ -1064,7 +997,6 @@ def test_topup_rejects_parseable_wallet_error_as_a_success(
         ),
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
         subprocess,
@@ -1104,7 +1036,6 @@ def test_topup_does_not_trust_an_unobserved_wallet_receipt(
         ),
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
         subprocess,
@@ -1125,7 +1056,7 @@ def test_topup_does_not_trust_an_unobserved_wallet_receipt(
 def test_topup_human_mode_requires_a_bridge_confirmed_receipt(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -1135,10 +1066,9 @@ def test_topup_human_mode_requires_a_bridge_confirmed_receipt(
         ),
     )
     monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
     monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
     monkeypatch.setattr(
-        requests,
+        payment_proxy.requests,
         "request",
         lambda *_a, **_k: FakeResponse(status_code=200, content=b"<html>not a receipt</html>"),
     )
@@ -1667,7 +1597,7 @@ def test_handoff_links_reject_non_http_schemes(
     monkeypatch: pytest.MonkeyPatch,
     capsys: Any,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -1952,7 +1882,7 @@ def test_workspace_use_preserves_definitive_conflict(
 def test_group_help_lists_all_verbs_instead_of_default_verb_help(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     assert cloud.run_cloud(["workspaces", "-h"]) == 0
     output = capsys.readouterr().out
     assert "workspaces verbs" in output
@@ -1976,7 +1906,7 @@ def test_workspace_alias_routes_to_workspaces(monkeypatch: pytest.MonkeyPatch) -
 def test_workspace_human_list_is_numbered_and_hides_ids(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -2024,7 +1954,7 @@ def test_integrations_human_list_exposes_installation_id_and_json_stays_full(
         ],
         "bitbucket_oauth_enabled": True,
     }
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     assert cloud.run_cloud(["integrations", "list"]) == 0
@@ -2042,7 +1972,7 @@ def test_integrations_human_list_exposes_installation_id_and_json_stays_full(
 def test_pr_review_human_list_prioritizes_actionable_fields(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -2117,7 +2047,7 @@ def test_pr_review_human_list_shows_pull_request_state(
     capsys: Any,
     pr_state: str,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -2180,7 +2110,7 @@ def test_scan_human_list_identifies_internal_and_uploaded_targets(
     record: dict[str, Any],
     expected_targets: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -2344,7 +2274,7 @@ def test_human_lists_prioritize_actionable_fields(
     visible: tuple[str, ...],
     hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     assert cloud.run_cloud(command) == 0
@@ -2358,7 +2288,7 @@ def test_human_lists_prioritize_actionable_fields(
 def test_token_human_list_shows_lifecycle_status(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -2715,7 +2645,7 @@ def test_nonstandard_human_list_envelopes_are_actionable(
     visible: tuple[str, ...],
     hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     assert cloud.run_cloud(command) == 0
@@ -2765,7 +2695,7 @@ def test_chat_credentials_human_view_separates_attached_and_available_sources(
             }
         ],
     }
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     command = ["chat", "credentials", "chat-id", "--scan-ids", "source-scan-id"]
@@ -2991,7 +2921,7 @@ def test_named_human_list_views_match_api_fields(
     visible: tuple[str, ...],
     hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     assert cloud.run_cloud(command) == 0
@@ -3005,7 +2935,7 @@ def test_named_human_list_views_match_api_fields(
 def test_supply_chain_org_summary_human_view_shows_totals_and_repository_risk(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -3166,7 +3096,7 @@ def test_wrapped_detail_human_views_are_unwrapped_and_actionable(
     visible: tuple[str, ...],
     hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))
 
     assert cloud.run_cloud(command) == 0
@@ -3180,7 +3110,7 @@ def test_wrapped_detail_human_views_are_unwrapped_and_actionable(
 def test_trace_human_view_summarizes_events_and_preserves_selector(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     seen_query: dict[str, Any] = {}
 
     def fake_trace_request(_method: str, _path: str, **kwargs: Any) -> FakeResponse:
@@ -3276,7 +3206,7 @@ def test_trace_human_view_summarizes_events_and_preserves_selector(
 def test_paginated_human_list_shows_total_and_continuation_command(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -3378,7 +3308,7 @@ def test_page_pagination_explains_an_out_of_range_page() -> None:
 def test_human_detail_preserves_long_prose_beyond_table_cell_limit(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     description = (
         " ".join(["authorization context"] * 12) + " final-description-marker\nsecond-line-marker"
     )
@@ -3456,7 +3386,7 @@ def test_large_vulnerability_detail_prioritizes_evidence_and_remediation() -> No
 def test_test_user_human_view_joins_latest_verification(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -3553,7 +3483,7 @@ def test_wide_knowledge_table_keeps_title_readable_with_long_identifiers() -> No
 def test_human_get_prioritizes_details_and_hides_internal_identity_fields(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",

tests/test_cloud_cli_runtime.py

@@ -6,16 +6,13 @@ import argparse
 import io
 import json
 import sys
-import time
 from typing import TYPE_CHECKING, Any
 
 import pytest
-import requests
 from rich.console import Console
 
 from strix.interface import cloud, platform_cli
 from strix.interface.cloud import http, render, runner, source_scan
-from strix.interface.cloud.source_upload import prepare_source
 from strix.interface.main import main as interface_main
 
 
@@ -172,7 +169,7 @@ def test_connector_enrollment_command_is_complete_multiline_and_terminal_safe(
         "  -e LABEL=before\x1b]52;c;copied\x07after \\\n"
         "  ghcr.io/usestrix/connector:latest"
     )
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -296,8 +293,8 @@ def test_source_prompt_shows_paths_and_literal_confirmation(
         return "n"
 
     monkeypatch.setattr(console, "input", answer)
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdout, "isatty", lambda: True)
     args = argparse.Namespace(
         source=str(tmp_path),
         dry_run=False,
@@ -327,7 +324,7 @@ def test_source_prompt_interruption_removes_temporary_archive(
     (tmp_path / "app.py").write_text("print('ok')\n", encoding="utf-8")
     console = Console(file=io.StringIO(), width=100)
     archive_paths: list[Path] = []
-    original_prepare = prepare_source
+    original_prepare = source_scan.prepare_source
 
     def capture_bundle(*args: Any, **kwargs: Any) -> Any:
         bundle = original_prepare(*args, **kwargs)
@@ -339,8 +336,8 @@ def test_source_prompt_interruption_removes_temporary_archive(
 
     monkeypatch.setattr(source_scan, "prepare_source", capture_bundle)
     monkeypatch.setattr(console, "input", interrupt)
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdout, "isatty", lambda: True)
     args = argparse.Namespace(
         source=str(tmp_path),
         dry_run=False,
@@ -397,7 +394,7 @@ def test_device_login_rejects_non_http_verification_url(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
         "post",
         lambda *_a, **_k: FakeResponse(
             {
@@ -430,7 +427,7 @@ def test_boolean_query_values_are_lowercase_for_url_search_params(
         seen["params"] = kwargs.get("params")
         return FakeResponse({"items": []})
 
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(http.requests, "request", fake_request)
     http.request("GET", "/test", query={"enabled": True, "disabled": False})
     assert seen["params"] == {"enabled": "true", "disabled": "false"}
 
@@ -484,7 +481,7 @@ def test_binary_response_refuses_to_write_to_a_terminal(
     monkeypatch: pytest.MonkeyPatch,
     capsys: Any,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",
@@ -516,7 +513,7 @@ def test_binary_response_can_be_intentionally_redirected(
             return None
 
     redirected = RedirectedStdout()
-    monkeypatch.setattr(sys, "stdout", redirected)
+    monkeypatch.setattr(runner.sys, "stdout", redirected)
     monkeypatch.setattr(
         http,
         "request",
@@ -537,7 +534,7 @@ def test_redirected_binary_errors_never_append_diagnostics_to_stdout(
         def iter_content(self, *, chunk_size: int) -> Any:
             assert chunk_size == 1024 * 1024
             yield b"%PDF-partial"
-            raise requests.ConnectionError("connection lost")
+            raise http.requests.ConnectionError("connection lost")
 
     response = (
         FakeResponse({"detail": "report rejected"}, status_code=500)
@@ -648,7 +645,7 @@ def test_binary_download_streams_and_preserves_existing_file_on_failure(
         def iter_content(self, *, chunk_size: int) -> Any:
             assert chunk_size == 1024 * 1024
             yield b"partial"
-            raise requests.ConnectionError("connection lost")
+            raise http.requests.ConnectionError("connection lost")
 
         def close(self) -> None:
             self.closed = True
@@ -773,7 +770,7 @@ def test_session_help_is_specific_and_human_whoami_shows_scopes(
             "scopes": ["scans:read", "organizations:read"],
         }
     )
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(platform_cli.sys.stdout, "isatty", lambda: True)
     assert cloud.run_cloud(["whoami", "--help"]) == 0
     who_help = capsys.readouterr().out
     assert "strix cloud whoami" in who_help
@@ -787,7 +784,7 @@ def test_non_tty_whoami_and_logout_emit_json(
 ) -> None:
     monkeypatch.delenv("STRIX_API_TOKEN", raising=False)
     monkeypatch.setattr(platform_cli, "AUTH_PATH", tmp_path / "auth.json")
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: False)
+    monkeypatch.setattr(platform_cli.sys.stdout, "isatty", lambda: False)
     platform_cli.save_record(
         {
             "api_token": "secret",
@@ -802,7 +799,7 @@ def test_non_tty_whoami_and_logout_emit_json(
     assert json.loads(capsys.readouterr().out)["email"] == "agent@example.test"
 
     monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
         "delete",
         lambda *_args, **_kwargs: type("Response", (), {"status_code": 200})(),
     )
@@ -834,7 +831,7 @@ def test_scope_picker_labels_match_the_server_presets() -> None:
 def test_noninteractive_login_never_prompts_for_workspace(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: False)
+    monkeypatch.setattr(platform_cli.sys.stdin, "isatty", lambda: False)
     console = Console(file=io.StringIO())
     console.input = lambda *_args, **_kwargs: pytest.fail("must not prompt")  # type: ignore[method-assign]
 
@@ -899,10 +896,10 @@ def test_device_flow_slow_down_never_exceeds_the_poll_interval_cap(
         sleeps.append(seconds)
         now += seconds
 
-    monkeypatch.setattr(requests, "post", post)
+    monkeypatch.setattr(platform_cli.requests, "post", post)
     monkeypatch.setattr(platform_cli, "_app_url", lambda: "https://example.test")
-    monkeypatch.setattr(time, "monotonic", monotonic)
-    monkeypatch.setattr(time, "sleep", sleep)
+    monkeypatch.setattr(platform_cli.time, "monotonic", monotonic)
+    monkeypatch.setattr(platform_cli.time, "sleep", sleep)
 
     with pytest.raises(platform_cli.PlatformAuthError, match="expired"):
         platform_cli._run_device_flow(
@@ -936,9 +933,9 @@ def test_device_flow_accepts_external_authkit_url_and_binds_token_origin(
             ),
         ]
     )
-    monkeypatch.setattr(requests, "post", lambda *_a, **_k: next(responses))
+    monkeypatch.setattr(platform_cli.requests, "post", lambda *_a, **_k: next(responses))
     monkeypatch.setattr(platform_cli, "_app_url", lambda: "https://preview.strix.ai")
-    monkeypatch.setattr(time, "sleep", lambda _seconds: None)
+    monkeypatch.setattr(platform_cli.time, "sleep", lambda _seconds: None)
 
     record = platform_cli._run_device_flow(
         Console(file=io.StringIO()),
@@ -987,7 +984,7 @@ def test_root_help_accepts_json_before_help_and_leaf_help_stays_specific(
 def test_non_tty_dispatcher_always_emits_structured_json(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: False)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: False)
 
     assert cloud.run_cloud([]) == 0
     assert json.loads(capsys.readouterr().out)["command"] == "strix cloud"
@@ -1023,7 +1020,7 @@ def test_source_upload_rejects_untrusted_destinations_before_reading_file(
     source.write_bytes(b"approved source")
     monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
     monkeypatch.setattr(
-        requests,
+        http.requests,
         "put",
         lambda *_args, **_kwargs: pytest.fail("an untrusted URL must not receive source bytes"),
     )
@@ -1062,7 +1059,7 @@ def test_source_upload_allows_only_managed_or_same_origin_storage(
         return response
 
     monkeypatch.setattr(http, "_app_url_override", app_url)
-    monkeypatch.setattr(requests, "put", put)
+    monkeypatch.setattr(http.requests, "put", put)
     http.upload_file(signed_url, "upload-token", source)
 
     assert request_options["allow_redirects"] is False
@@ -1083,7 +1080,7 @@ def test_source_upload_refuses_redirects_without_following_them(
         return response
 
     monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
-    monkeypatch.setattr(requests, "put", put)
+    monkeypatch.setattr(http.requests, "put", put)
 
     with pytest.raises(http.CloudError, match="unexpected redirect"):
         http.upload_file(
@@ -1098,7 +1095,7 @@ def test_source_upload_refuses_redirects_without_following_them(
 def test_one_time_api_token_has_save_now_warning(
     monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
     monkeypatch.setattr(
         http,
         "request",

tests/test_cloud_idempotency.py

@@ -3,11 +3,9 @@
 from __future__ import annotations
 
 import json
-import time
 from typing import Any
 
 import pytest
-import requests
 
 from strix.interface import cloud
 from strix.interface.cloud import http, runner
@@ -32,7 +30,7 @@ class FakeResponse:
 @pytest.fixture(autouse=True)
 def _token(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setenv("STRIX_API_TOKEN", "idempotency-test-token")
-    monkeypatch.setattr(time, "sleep", lambda _seconds: None)
+    monkeypatch.setattr(runner.time, "sleep", lambda _seconds: None)
 
 
 def test_scan_start_generates_and_sends_one_stable_key(
@@ -199,7 +197,7 @@ def test_http_client_places_key_in_the_header(monkeypatch: pytest.MonkeyPatch) -
         seen.update(kwargs)
         return FakeResponse({"ok": True})
 
-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
     http.request("POST", "/scans", body={}, idempotency_key="header-key")
     assert seen["headers"]["Idempotency-Key"] == "header-key"
     assert seen["headers"]["Authorization"] == "Bearer idempotency-test-token"

tests/test_cloud_payment_proxy.py

@@ -7,7 +7,6 @@ import urllib.request
 from typing import TYPE_CHECKING, Any
 
 import pytest
-import requests
 
 from strix.interface.cloud import payment_proxy
 
@@ -40,8 +39,7 @@ def _post(url: str, body: bytes, headers: dict[str, str] | None = None) -> bytes
         method="POST",
     )
     with urllib.request.urlopen(request, timeout=2) as response:  # noqa: S310
-        body_bytes: bytes = response.read()
-    return body_bytes
+        return response.read()
 
 
 def test_bridge_bounds_decompressed_upstream_response(monkeypatch: pytest.MonkeyPatch) -> None:
@@ -52,7 +50,7 @@ def test_bridge_bounds_decompressed_upstream_response(monkeypatch: pytest.Monkey
         return response
 
     monkeypatch.setattr(payment_proxy, "_MAX_UPSTREAM_RESPONSE_BYTES", 4)
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)
 
     with payment_proxy.wallet_payment_bridge(
         upstream_url="https://app.example.test/api/v1/billing/topup",
@@ -82,7 +80,7 @@ def test_bridge_forwards_only_the_approved_request_and_protected_headers(
         captured.append(kwargs)
         return _StreamingResponse([b'{"ok":true}'])
 
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)
     with payment_proxy.wallet_payment_bridge(
         upstream_url="https://app.example.test/api/v1/billing/topup",
         api_token="strix-secret",  # noqa: S106
@@ -126,7 +124,7 @@ def test_bridge_limits_valid_wallet_attempts(monkeypatch: pytest.MonkeyPatch) ->
         calls += 1
         return _StreamingResponse([b"{}"])
 
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)
     with payment_proxy.wallet_payment_bridge(
         upstream_url="https://app.example.test/api/v1/billing/topup",
         api_token="strix-secret",  # noqa: S106

tests/test_cloud_session.py

@@ -6,7 +6,6 @@ import json
 from typing import TYPE_CHECKING, Any
 
 import pytest
-import requests
 from rich.console import Console
 
 from strix.interface import cloud, platform_cli, platform_identity
@@ -56,7 +55,7 @@ def test_http_workspace_pin_is_captured_once(
         sent.append(dict(kwargs["headers"]))
         return Response({})
 
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(http.requests, "request", fake_request)
     http.configure()
     platform_cli.save_record(
         {
@@ -117,7 +116,7 @@ def test_logout_keeps_local_token_when_remote_outcome_is_not_definitive(
         }
     )
     monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
         "delete",
         lambda *_args, **_kwargs: Response({"detail": "unavailable"}, 503),
     )

tests/test_cloud_source_upload.py

@@ -655,44 +655,3 @@ def test_incomplete_upload_credentials_delete_the_reserved_upload(
     monkeypatch.setattr(http, "request", fake_request)
     assert cloud.run_cloud(["scans", "start", "--source", str(tmp_path), "--yes", "--json"]) == 1
     assert ("DELETE", "/uploads/upload-incomplete") in paths
-
-
-def test_archive_source_is_rejected_with_directory_guidance(tmp_path: Path) -> None:
-    archive = tmp_path / "backend.zip"
-    with zipfile.ZipFile(archive, "w") as bundle:
-        bundle.writestr("app.py", "print('safe')\n")
-
-    with pytest.raises(http.CloudError, match="not an archive") as raised:
-        source_upload.prepare_source(
-            str(archive),
-            include_hidden=False,
-            include_sensitive=False,
-            include_archives=False,
-            exclude=[],
-        )
-    assert raised.value.next_step is not None
-    assert "--source" in raised.value.next_step
-    assert "--dry-run --show-files" in raised.value.next_step
-
-
-def test_oversize_archive_names_largest_files_and_exclude_guidance(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    (tmp_path / "app.py").write_text("print('safe')\n", encoding="utf-8")
-    (tmp_path / "big.bin").write_bytes(os.urandom(4096))
-    monkeypatch.setattr(source_upload, "MAX_ARCHIVE_BYTES", 1024)
-
-    with pytest.raises(http.CloudError, match=r"larger than the 0\.0 MiB upload limit") as raised:
-        source_upload.prepare_source(
-            str(tmp_path),
-            include_hidden=False,
-            include_sensitive=False,
-            include_archives=False,
-            exclude=[],
-        )
-    message = str(raised.value)
-    assert message.index("big.bin") < message.index("app.py")
-    assert raised.value.next_step is not None
-    assert "--exclude" in raised.value.next_step
-    assert "--dry-run --show-files" in raised.value.next_step
-    assert not list(tmp_path.glob("strix-source-*.zip"))

tests/test_config_loader.py

@@ -30,8 +30,6 @@ _LLM_ENV_KEYS = [
     "STRIX_FORCE_REQUIRED_TOOL_CHOICE",
     "LLM_TIMEOUT",
     "PERPLEXITY_API_KEY",
-    "EXA_API_KEY",
-    "STRIX_WEB_SEARCH_PROVIDER",
     # RuntimeSettings
     "STRIX_IMAGE",
     "STRIX_RUNTIME_BACKEND",
@@ -82,17 +80,6 @@ def test_read_json_overrides_maps_to_nested_settings(tmp_path: Path) -> None:
     }
 
 
-def test_read_json_overrides_maps_exa_and_provider(tmp_path: Path) -> None:
-    path = tmp_path / "cli-config.json"
-    path.write_text(
-        json.dumps({"env": {"EXA_API_KEY": "exa-key", "STRIX_WEB_SEARCH_PROVIDER": "exa"}}),
-        encoding="utf-8",
-    )
-    assert loader._read_json_overrides(path) == {
-        "integrations": {"exa_api_key": "exa-key", "web_search_provider": "exa"},
-    }
-
-
 def test_read_json_overrides_skips_keys_already_in_environ(
     tmp_path: Path, monkeypatch: pytest.MonkeyPatch
 ) -> None:
@@ -221,191 +208,6 @@ def test_persist_current_writes_env_block(tmp_path: Path, monkeypatch: pytest.Mo
     }
 
 
-def test_persist_current_keeps_file_values_when_env_is_unset(tmp_path: Path) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    assert loader.load_settings().llm.model == "file-model"
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {
-        "env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}
-    }
-
-
-def test_persist_current_env_overrides_file_value(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "PERPLEXITY_API_KEY": "file-pplx"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("PERPLEXITY_API_KEY", "env-pplx")
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {
-        "env": {"STRIX_LLM": "file-model", "PERPLEXITY_API_KEY": "env-pplx"}
-    }
-
-
-def test_linked_llm_model_change_drops_stored_key_and_base(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps(
-            {
-                "env": {
-                    "STRIX_LLM": "file-model",
-                    "LLM_API_KEY": "file-key",
-                    "LLM_API_BASE": "http://file-base",
-                    "PERPLEXITY_API_KEY": "pplx",
-                }
-            }
-        ),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("STRIX_LLM", "env-model")
-
-    llm = loader.load_settings().llm
-    assert llm.model == "env-model"
-    assert llm.api_key is None
-    assert llm.api_base is None
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {
-        "env": {"STRIX_LLM": "env-model", "PERPLEXITY_API_KEY": "pplx"}
-    }
-
-
-def test_linked_llm_key_change_drops_stored_model(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("LLM_API_KEY", "new-key")
-
-    assert loader.load_settings().llm.model is None
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {"env": {"LLM_API_KEY": "new-key"}}
-
-
-def test_linked_llm_secondary_alias_in_env_is_not_a_change(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("LLM_API_KEY", "file-key")
-    monkeypatch.setenv("OPENAI_API_KEY", "unrelated-global-key")
-
-    llm = loader.load_settings().llm
-    assert llm.model == "file-model"
-    assert llm.api_key == "file-key"
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {
-        "env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}
-    }
-
-
-def test_linked_llm_unchanged_env_keeps_stored_key(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("STRIX_LLM", "file-model")
-
-    assert loader.load_settings().llm.api_key == "file-key"
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {
-        "env": {"STRIX_LLM": "file-model", "LLM_API_KEY": "file-key"}
-    }
-
-
-def test_persist_current_env_alias_replaces_other_alias_in_file(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(json.dumps({"env": {"OPENAI_API_KEY": "old-key"}}), encoding="utf-8")
-    loader.apply_config_override(target)
-    monkeypatch.setenv("LLM_API_KEY", "new-key")
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {"env": {"LLM_API_KEY": "new-key"}}
-
-
-def test_persist_current_empty_env_clears_file_value(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(
-        json.dumps({"env": {"STRIX_LLM": "file-model", "PERPLEXITY_API_KEY": "pplx"}}),
-        encoding="utf-8",
-    )
-    loader.apply_config_override(target)
-    monkeypatch.setenv("PERPLEXITY_API_KEY", "")
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {"env": {"STRIX_LLM": "file-model"}}
-
-
-def test_persist_current_empty_primary_alias_does_not_save_sibling(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text(json.dumps({"env": {"PERPLEXITY_API_KEY": "pplx"}}), encoding="utf-8")
-    loader.apply_config_override(target)
-    monkeypatch.setenv("LLM_API_KEY", "")
-    monkeypatch.setenv("OPENAI_API_KEY", "sibling-key")
-
-    assert loader.load_settings().llm.api_key == ""
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {"env": {"PERPLEXITY_API_KEY": "pplx"}}
-
-
-def test_persist_current_replaces_corrupt_file(
-    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
-) -> None:
-    target = tmp_path / "cli-config.json"
-    target.write_text("{not json", encoding="utf-8")
-    loader.apply_config_override(target)
-    monkeypatch.setenv("STRIX_LLM", "env-model")
-
-    loader.persist_current()
-
-    assert json.loads(target.read_text(encoding="utf-8")) == {"env": {"STRIX_LLM": "env-model"}}
-
-
 def test_persist_current_sets_0600_mode(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setenv("STRIX_LLM", "persisted-model")
     target = tmp_path / "cli-config.json"

tests/test_dedupe_model.py

@@ -114,14 +114,7 @@ def test_config_file_loads_dedupe_model(
     tmp_path: Path,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
-    for key in (
-        "STRIX_LLM",
-        "LLM_API_KEY",
-        "OPENAI_API_KEY",
-        "LLM_API_BASE",
-        "STRIX_DEDUPE_MODEL",
-        "STRIX_DEDUPE_REASONING_EFFORT",
-    ):
+    for key in ("STRIX_LLM", "STRIX_DEDUPE_MODEL", "STRIX_DEDUPE_REASONING_EFFORT"):
         monkeypatch.delenv(key, raising=False)
     path = tmp_path / "config.json"
     path.write_text(

tests/test_docker_client_delete.py

@@ -12,7 +12,6 @@ would let it escape and surface a traceback on every teardown.
 from __future__ import annotations
 
 from types import SimpleNamespace
-from typing import TYPE_CHECKING, cast
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
@@ -23,10 +22,6 @@ from requests.exceptions import ConnectionError as RequestsConnectionError
 from strix.runtime.docker_client import StrixDockerSandboxClient
 
 
-if TYPE_CHECKING:
-    from agents.sandbox.session.sandbox_session import SandboxSession
-
-
 def _client_with_kill_error(exc: Exception) -> StrixDockerSandboxClient:
     """A StrixDockerSandboxClient whose containers.get(...).kill() raises ``exc``."""
     client = StrixDockerSandboxClient.__new__(StrixDockerSandboxClient)
@@ -36,10 +31,9 @@ def _client_with_kill_error(exc: Exception) -> StrixDockerSandboxClient:
     return client
 
 
-def _session(container_id: str | None = "abc123") -> SandboxSession:
+def _session() -> object:
     # delete() reads session._inner.state.container_id
-    fake = SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id=container_id)))
-    return cast("SandboxSession", fake)
+    return SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id="abc123")))
 
 
 @pytest.mark.parametrize(
@@ -51,7 +45,7 @@ def _session(container_id: str | None = "abc123") -> SandboxSession:
     ],
 )
 @pytest.mark.asyncio
-async def test_delete_swallows_best_effort_kill_errors(exc: Exception) -> None:
+async def test_delete_swallows_best_effort_kill_errors(exc):
     """A torn-down socket (ConnectionError) or a gone/unhappy container
     (NotFound/APIError) during the kill must not propagate; delete() still
     delegates to the SDK's delete()."""
@@ -68,7 +62,7 @@ async def test_delete_swallows_best_effort_kill_errors(exc: Exception) -> None:
 
 
 @pytest.mark.asyncio
-async def test_delete_does_not_swallow_unrelated_errors() -> None:
+async def test_delete_does_not_swallow_unrelated_errors():
     """A programming error (e.g. ValueError) is not part of best-effort kill and
     must still propagate."""
     client = _client_with_kill_error(ValueError("boom"))
@@ -77,11 +71,11 @@ async def test_delete_does_not_swallow_unrelated_errors() -> None:
 
 
 @pytest.mark.asyncio
-async def test_delete_noop_without_container_id() -> None:
+async def test_delete_noop_without_container_id():
     """No container_id -> no kill attempt, just delegate."""
     client = StrixDockerSandboxClient.__new__(StrixDockerSandboxClient)
     client.docker_client = MagicMock()
-    session = _session(container_id=None)
+    session = SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id=None)))
 
     with patch.object(
         DockerSandboxClient, "delete", new=AsyncMock(return_value=session)

tests/test_go_tui_runtime.py

@@ -343,19 +343,15 @@ async def test_setup_preflights_model_before_starting(
         assert candidate.scope_mode == "diff"
         assert candidate.diff_base == "origin/main"
 
-    monkeypatch.setattr(go_tui, "persist_current", lambda: calls.append("persist"))
     monkeypatch.setattr(go_tui, "build_targets_info", build)
     monkeypatch.setattr(go_tui, "prepare_run", prepare)
     monkeypatch.setattr(go_tui, "telemetry_start", lambda _args: calls.append("telemetry"))
     monkeypatch.setattr(runtime, "init_run_state", lambda: calls.append("state"))
     monkeypatch.setattr(runtime, "start_scan", lambda: calls.append("scan"))
 
-    # The controller runs these two in turn for every setup launch.
-    await runtime.ensure_model_verified()
     await runtime.start_from_setup()
 
-    # The same steps, in the same order, as a direct launch's prepare_and_start.
-    assert calls == ["preflight", "persist", "targets", "prepare", "telemetry", "state", "scan"]
+    assert calls == ["preflight", "targets", "prepare", "telemetry", "state", "scan"]
     assert runtime.args.scan_mode == "quick"
     assert runtime.args.instruction == ""
     assert runtime.args.max_budget_usd == 8.5
@@ -364,138 +360,35 @@ async def test_setup_preflights_model_before_starting(
     assert runtime.args.diff_base == "origin/main"
 
 
-def _setup_model(
-    monkeypatch: pytest.MonkeyPatch, model: str | None = "openrouter/test-model"
+@pytest.mark.asyncio
+async def test_optimistic_setup_skips_model_preflight(
+    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
+    runtime = GoTuiRuntime(args())
+    runtime.controller.targets = [str(Path.cwd())]
+    calls: list[str] = []
+
+    async def preflight(_model: str) -> None:
+        calls.append("preflight")
+
     monkeypatch.setattr(
         go_tui,
         "load_settings",
-        lambda: SimpleNamespace(llm=SimpleNamespace(model=model)),
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
     )
-
-
-def _setup_messages(runtime: GoTuiRuntime) -> list[tuple[str, str]]:
-    return [(message["level"], message["text"]) for message in runtime.controller.messages]
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_reports_success_in_the_setup_log(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    calls: list[str] = []
-
-    async def preflight(model: str) -> None:
-        calls.append(model)
-
-    _setup_model(monkeypatch)
     monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
+    monkeypatch.setattr(go_tui, "build_targets_info", lambda _args, **_kw: calls.append("targets"))
+    monkeypatch.setattr(go_tui, "prepare_run", lambda _args: calls.append("prepare"))
+    monkeypatch.setattr(go_tui, "telemetry_start", lambda _args: calls.append("telemetry"))
+    monkeypatch.setattr(runtime, "init_run_state", lambda: calls.append("state"))
+    monkeypatch.setattr(runtime, "start_scan", lambda: calls.append("scan"))
 
-    await runtime.check_setup_model()
+    await runtime.start_from_setup(verify=False)
 
-    assert calls == ["openrouter/test-model"]
-    assert runtime.model_verified is True
-    assert _setup_messages(runtime) == [
-        ("info", "Verifying model connection..."),
-        ("info", "Model connection verified"),
-    ]
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_reports_failure_without_leaving_setup(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-
-    async def preflight(_model: str) -> None:
-        raise TimeoutError("connection timed out")
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-
-    await runtime.check_setup_model()
-
-    assert runtime.model_verified is False
-    assert runtime.controller.setup_mode is True
-    assert runtime.controller.scan_state == "setup"
-    assert _setup_messages(runtime)[-1] == (
-        "error",
-        "Model connection failed: connection timed out",
-    )
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_waits_for_a_configured_model(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-
-    _setup_model(monkeypatch, model=None)
-    monkeypatch.setattr(
-        go_tui,
-        "preflight_model_connection",
-        lambda _model: pytest.fail("nothing to check without a model"),
-    )
-
-    await runtime.check_setup_model()
-
-    assert runtime.model_verified is False
-    assert runtime.controller.messages == []
-
-
-@pytest.mark.asyncio
-async def test_ensure_model_verified_reuses_the_startup_check(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    release = asyncio.Event()
-    calls: list[str] = []
-
-    async def preflight(_model: str) -> None:
-        calls.append("preflight")
-        await release.wait()
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-    runtime._setup_preflight = asyncio.create_task(runtime.check_setup_model())
-    await asyncio.sleep(0)
-
-    # A launch that arrives mid-check waits for it rather than racing a second
-    # round trip.
-    ensure = asyncio.create_task(runtime.ensure_model_verified())
-    await asyncio.sleep(0)
-    assert not ensure.done()
-    release.set()
-    await ensure
-
-    assert calls == ["preflight"]
-    assert runtime.model_verified is True
-
-
-@pytest.mark.asyncio
-async def test_ensure_model_verified_retries_after_a_failed_startup_check(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    outcomes = iter([TimeoutError("connection timed out"), None])
-    calls: list[str] = []
-
-    async def preflight(_model: str) -> None:
-        calls.append("preflight")
-        outcome = next(outcomes)
-        if outcome is not None:
-            raise outcome
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-
-    await runtime.check_setup_model()
-    assert runtime.model_verified is False
-
-    await runtime.ensure_model_verified()
-
-    assert calls == ["preflight", "preflight"]
-    assert runtime.model_verified is True
+    # No preflight: the scan launches straight through and any model error
+    # surfaces once the agent runs.
+    assert "preflight" not in calls
+    assert calls == ["targets", "prepare", "telemetry", "state", "scan"]
 
 
 @pytest.mark.asyncio
@@ -507,8 +400,15 @@ async def test_confirmed_target_less_launch_mounts_workspace_without_targets(
     runtime.controller.workspace_mount = str(Path.home())
     prepared: list[argparse.Namespace] = []
 
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "persist_current", lambda: None)
+    async def preflight(_model: str) -> None:
+        return None
+
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
+    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
     monkeypatch.setattr(
         go_tui,
         "build_targets_info",
@@ -519,7 +419,7 @@ async def test_confirmed_target_less_launch_mounts_workspace_without_targets(
     monkeypatch.setattr(runtime, "init_run_state", lambda: None)
     monkeypatch.setattr(runtime, "start_scan", lambda: None)
 
-    await runtime.start_from_setup()
+    await runtime.start_from_setup(verify=False)
 
     assert prepared[0].workspace_mount == str(Path.home())
     assert prepared[0].targets_info == []
@@ -542,8 +442,15 @@ async def test_setup_preserves_prepared_cli_targets(
     runtime = GoTuiRuntime(runtime_args)
     calls: list[str] = []
 
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "persist_current", lambda: calls.append("persist"))
+    async def preflight(_model: str) -> None:
+        calls.append("preflight")
+
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
+    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
     monkeypatch.setattr(
         go_tui,
         "build_targets_info",
@@ -558,7 +465,7 @@ async def test_setup_preserves_prepared_cli_targets(
 
     assert runtime.controller.targets == ["https://example.com"]
     assert runtime.args.targets_info[0]["type"] == "web"
-    assert calls == ["persist", "prepare", "telemetry", "state", "scan"]
+    assert calls == ["preflight", "prepare", "telemetry", "state", "scan"]
 
 
 @pytest.mark.asyncio
@@ -891,17 +798,19 @@ async def test_setup_preflight_failure_does_not_start_scan(
         nonlocal started
         started = True
 
-    _setup_model(monkeypatch)
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
     monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-    monkeypatch.setattr(go_tui, "persist_current", mark_started)
     monkeypatch.setattr(go_tui, "build_targets_info", mark_started)
     monkeypatch.setattr(runtime, "init_run_state", mark_started)
     monkeypatch.setattr(runtime, "start_scan", mark_started)
 
     with pytest.raises(RuntimeError, match="Model connection failed: 401 Unauthorized"):
-        await runtime.ensure_model_verified()
+        await runtime.start_from_setup()
 
-    assert runtime.model_verified is False
     assert started is False
     assert runtime.scan_task is None
 

tests/test_import_warmup.py

@@ -1,10 +1,12 @@
-"""The import warm-up thread must never race the main thread into the engine.
+"""The import warm-up thread must never leave the import system poisoned.
 
-Two threads that enter the same package graph from different modules hold
-each other's import locks (warm-up: ``strix.core.runner`` -> ``agents``;
-main: ``agents.models.interface``). CPython breaks such a cycle by failing one
-of the imports, so the main thread waits for the warm-up before its first
-engine import.
+Field failure: the warm-up thread's ``strix.core.runner`` import and the main
+thread's ``strix.report`` import both walked the agents SDK graph, and the two
+held each other's import locks (report -> dedupe -> agents while runner ->
+hooks -> report.state). CPython's deadlock avoidance breaks such a cycle by
+failing one import, which strands finished submodules in ``sys.modules`` with
+their parent package gone — and the next import of one of those submodules
+crashes with "partially initialized module".
 """
 
 from __future__ import annotations
@@ -12,16 +14,10 @@ from __future__ import annotations
 import subprocess
 import sys
 import textwrap
-import threading
-from typing import TYPE_CHECKING
 
 from strix.llm import warmup
 
 
-if TYPE_CHECKING:
-    import pytest
-
-
 def _run(code: str) -> subprocess.CompletedProcess[str]:
     return subprocess.run(  # noqa: S603
         [sys.executable, "-c", textwrap.dedent(code)],
@@ -60,49 +56,44 @@ def test_check_duplicate_resolves_lazily() -> None:
     assert result.returncode == 0, result.stderr
 
 
-def test_wait_for_import_warmup_lets_main_thread_import_the_agents_graph() -> None:
+def test_failed_warm_import_purges_orphaned_submodules() -> None:
     result = _run(
         """
         import sys
 
-        from strix.llm.warmup import start_import_warmup, wait_for_import_warmup
+        from strix.llm.warmup import _warm
 
-        # Same shape as the CLI: warm-up starts, then the main thread needs a
-        # module from the middle of the agents graph.
-        start_import_warmup()
-        wait_for_import_warmup()
+        # A package whose import fails after a submodule already completed:
+        # CPython removes the package but leaves the submodule stranded.
+        import pathlib
+        import tempfile
 
-        from agents.models.interface import ModelTracing  # noqa: F401
+        root = pathlib.Path(tempfile.mkdtemp())
+        pkg = root / "stranded_pkg"
+        pkg.mkdir()
+        (pkg / "ok.py").write_text("VALUE = 1")
+        (pkg / "__init__.py").write_text("from . import ok\\nraise RuntimeError('boom')")
+        sys.path.insert(0, str(root))
 
-        assert "agents" in sys.modules
-        assert "agents.models" in sys.modules
-        assert "strix.core.runner" in sys.modules
+        _warm(("stranded_pkg",))
+
+        assert "stranded_pkg" not in sys.modules
+        assert "stranded_pkg.ok" not in sys.modules, "orphan survived the purge"
+
+        # And the subtree imports cleanly afterwards up to the real error.
+        try:
+            import stranded_pkg  # noqa: F401
+        except RuntimeError:
+            pass
+        else:
+            raise AssertionError("expected the package's own error")
         """
     )
     assert result.returncode == 0, result.stderr
 
 
-def test_wait_for_import_warmup_blocks_until_the_thread_finishes(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    release = threading.Event()
-    monkeypatch.setattr(warmup, "_warm", lambda _modules: release.wait())
-    monkeypatch.setattr(warmup, "_thread", None)
-    warmup.start_import_warmup(())
-
-    waiter = threading.Thread(target=warmup.wait_for_import_warmup)
-    waiter.start()
-    waiter.join(0.2)
-    assert waiter.is_alive(), "returned before the warm-up finished"
-
-    release.set()
-    waiter.join(5)
-    assert not waiter.is_alive()
-
-
-def test_failed_warm_import_does_not_raise() -> None:
-    warmup._warm(("strix_no_such_module_for_warmup_test",))
-
-
-def test_wait_for_import_warmup_is_a_no_op_without_a_thread() -> None:
-    warmup.wait_for_import_warmup()
+def test_purge_does_not_touch_preexisting_or_healthy_modules() -> None:
+    before = frozenset(sys.modules) - {"strix.llm.warmup"}
+    warmup._purge_orphaned_modules(before)
+    assert "strix.llm.warmup" in sys.modules  # parent chain intact -> kept
+    assert "strix" in sys.modules

tests/test_models.py

@@ -72,13 +72,6 @@ def test_recommended_models_are_matched_case_insensitively() -> None:
         "moonshot/kimi-k2.6",
         "kimi-k2.7-code",
         "moonshot/kimi-k3",
-        "anthropic/claude-fable-5-1",
-        "vertex_ai/claude-fable-5-1@default",
-        "gemini/gemini-3.7-flash",
-        "glm-5.3",
-        "zai/glm-5.3-flash",
-        "openrouter/z-ai/glm-5.3",
-        "novita/zai-org/glm-5.2",
     ],
 )
 def test_frontier_model_families_are_accepted(model_name: str) -> None:
@@ -99,9 +92,6 @@ def test_frontier_model_families_are_accepted(model_name: str) -> None:
         "openrouter/x-ai/grok-4",
         "mistral/mistral-medium-3-5",
         "mistral/magistral-medium-latest",
-        "zai/glm-4.7",
-        "openrouter/z-ai/glm-5",
-        "custom-provider/glm-5.3-local",
     ],
 )
 def test_non_frontier_models_are_rejected(model_name: str) -> None:

tests/test_optional_deps.py

@@ -11,8 +11,7 @@ PYPROJECT = Path(__file__).resolve().parent.parent / "pyproject.toml"
 
 def _optional_dependencies() -> dict[str, list[str]]:
     data = tomllib.loads(PYPROJECT.read_text(encoding="utf-8"))
-    extras: dict[str, list[str]] = data["project"]["optional-dependencies"]
-    return extras
+    return data["project"]["optional-dependencies"]
 
 
 def test_vertex_extra_pins_google_auth() -> None:

tests/test_runner_mcp.py

@@ -185,4 +185,6 @@ async def test_roster_is_persisted_even_without_a_status_sink(
     )
 
     assert persisted, "roster must persist even when no status sink is attached"
-    assert persisted[-1] == [{"name": "local_fs", "provider": None, "tool_count": 3, "dead": False}]
+    assert persisted[-1] == [
+        {"name": "local_fs", "provider": None, "tool_count": 3, "dead": False}
+    ]

tests/test_sarif_stride.py

@@ -34,8 +34,7 @@ def _finding(**overrides: Any) -> dict[str, Any]:
 
 
 def _rule_tags(doc: dict[str, Any]) -> list[str]:
-    tags: list[str] = doc["runs"][0]["tool"]["driver"]["rules"][0]["properties"]["tags"]
-    return tags
+    return doc["runs"][0]["tool"]["driver"]["rules"][0]["properties"]["tags"]
 
 
 def test_stride_tags_on_rule_for_known_cwe() -> None:

tests/test_session_fd.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import asyncio
-import os
 from pathlib import Path
 from typing import Any, cast
 
@@ -10,40 +9,13 @@ import pytest
 from strix.core.sessions import open_agent_session
 
 
-def _fd_dir() -> Path | None:
+def _count_open_fds() -> int | None:
     for path in (Path("/proc/self/fd"), Path("/dev/fd")):
         if path.is_dir():
-            return path
+            return len(list(path.iterdir()))
     return None
 
 
-def _count_open_fds() -> int | None:
-    fd_dir = _fd_dir()
-    return None if fd_dir is None else len(list(fd_dir.iterdir()))
-
-
-def _count_open_fds_to(files: list[Path]) -> int | None:
-    """Count the descriptors this process holds on exactly ``files``.
-
-    Matching on inode rather than on the process-wide total keeps the check
-    immune to sockets and pipes that unrelated background threads open while
-    the test runs.
-    """
-    fd_dir = _fd_dir()
-    if fd_dir is None:
-        return None
-    wanted = {(stat.st_dev, stat.st_ino) for stat in (path.stat() for path in files)}
-    held = 0
-    for entry in fd_dir.iterdir():
-        try:
-            stat = os.fstat(int(entry.name))
-        except (OSError, ValueError):
-            continue
-        if (stat.st_dev, stat.st_ino) in wanted:
-            held += 1
-    return held
-
-
 @pytest.mark.asyncio
 async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None:
     """Descriptor use must track live operations, not the number of sessions.
@@ -53,20 +25,21 @@ async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None
     scan, and fan-out multiplies those handles until the process runs out of file
     descriptors (#1018). A session that is not mid-operation should hold none.
     """
-    if _fd_dir() is None:
+    baseline = _count_open_fds()
+    if baseline is None:
         pytest.skip("no /proc/self/fd or /dev/fd on this platform")
 
-    db_paths = [tmp_path / f"s{i}.db" for i in range(60)]
-    sessions = [open_agent_session(f"a{i}", path) for i, path in enumerate(db_paths)]
+    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(60)]
     try:
         for _ in range(4):
             await asyncio.gather(
                 *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
             )
             await asyncio.gather(*(s.get_items() for s in sessions))
-        parked = _count_open_fds_to(db_paths)
-        # 60 parked sessions, yet none of them holds its database open.
-        assert parked == 0, f"parked sessions hold {parked} database descriptors"
+        parked = _count_open_fds()
+        assert parked is not None
+        # 60 parked sessions, yet descriptors are back at the baseline.
+        assert parked - baseline <= 5, f"parked fds grew by {parked - baseline}"
     finally:
         for s in sessions:
             s.close()

tests/test_telemetry_errors.py

@@ -1,125 +0,0 @@
-"""Error beacons carry a category, phase, and exception class — never a message."""
-
-from __future__ import annotations
-
-from typing import Any
-
-import pytest
-import requests
-
-from strix.report.state import ReportState
-from strix.telemetry import posthog, report_error, scarf, set_scan_phase
-from strix.telemetry._common import exception_props
-
-
-PRIVATE_MESSAGE = "private message that must stay on the machine"
-
-
-def _capture(sent: list[dict[str, Any]], event: str, props: dict[str, Any]) -> bool:
-    sent.append({"event": event, **props})
-    return True
-
-
-def test_exception_props_uses_bare_name_for_builtins() -> None:
-    assert exception_props(ValueError(PRIVATE_MESSAGE)) == {"exception_type": "ValueError"}
-
-
-def test_exception_props_prefixes_third_party_top_level_package() -> None:
-    props = exception_props(requests.exceptions.ConnectTimeout(PRIVATE_MESSAGE))
-    assert props == {"exception_type": "requests.ConnectTimeout"}
-
-
-def _chained(cause: BaseException | None, *, explicit: bool) -> RuntimeError:
-    exc = RuntimeError("wrapped")
-    if explicit:
-        exc.__cause__ = cause
-        exc.__suppress_context__ = True
-    else:
-        exc.__context__ = cause
-    return exc
-
-
-def test_exception_props_reports_explicit_cause() -> None:
-    props = exception_props(_chained(ConnectionError(PRIVATE_MESSAGE), explicit=True))
-    assert props == {"exception_type": "RuntimeError", "exception_cause": "ConnectionError"}
-
-
-def test_exception_props_reports_implicit_context() -> None:
-    props = exception_props(_chained(KeyError("k"), explicit=False))
-    assert props["exception_cause"] == "KeyError"
-
-
-def test_exception_props_ignores_suppressed_context() -> None:
-    exc = _chained(None, explicit=True)
-    exc.__context__ = KeyError("k")
-    assert exception_props(exc) == {"exception_type": "RuntimeError"}
-
-
-def test_exception_props_unwraps_exception_group() -> None:
-    group = ExceptionGroup("tasks", [TimeoutError("t"), ValueError("v")])
-    assert exception_props(group) == {"exception_type": "TimeoutError"}
-
-
-@pytest.mark.parametrize("telemetry", [posthog, scarf])
-def test_error_event_carries_phase_and_class_but_no_message(
-    telemetry: Any,
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    sent: list[dict[str, Any]] = []
-    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
-    set_scan_phase("sandbox_init")
-
-    telemetry.error("scan_failed", RuntimeError(PRIVATE_MESSAGE))
-
-    assert len(sent) == 1
-    event = sent[0]
-    assert event["event"] == "error"
-    assert event["error_type"] == "scan_failed"
-    assert event["phase"] == "sandbox_init"
-    assert event["exception_type"] == "RuntimeError"
-    assert PRIVATE_MESSAGE not in repr(event)
-
-
-@pytest.mark.parametrize("telemetry", [posthog, scarf])
-def test_error_event_without_exception_omits_exception_fields(
-    telemetry: Any,
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    sent: list[dict[str, Any]] = []
-    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
-    set_scan_phase("startup")
-
-    telemetry.error("docker_not_installed")
-
-    assert sent[0]["error_type"] == "docker_not_installed"
-    assert sent[0]["phase"] == "startup"
-    assert "exception_type" not in sent[0]
-    assert "exception_cause" not in sent[0]
-
-
-def test_report_error_fans_out_to_both_backends(monkeypatch: pytest.MonkeyPatch) -> None:
-    sent: list[dict[str, Any]] = []
-    monkeypatch.setattr(posthog, "_send", lambda event, props: _capture(sent, event, props))
-    monkeypatch.setattr(scarf, "_send", lambda event, props: _capture(sent, event, props))
-
-    report_error("model_connection_failed", TimeoutError(PRIVATE_MESSAGE))
-
-    assert len(sent) == 2
-    assert {e["error_type"] for e in sent} == {"model_connection_failed"}
-    assert {e["exception_type"] for e in sent} == {"TimeoutError"}
-
-
-@pytest.mark.parametrize("telemetry", [posthog, scarf])
-def test_scan_ended_prefers_recorded_exit_reason(
-    telemetry: Any,
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    state = ReportState()
-    state.scan_ended_exit_reason = "budget_exceeded"
-    sent: list[dict[str, Any]] = []
-    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
-
-    telemetry.end(state, exit_reason="user_exit")
-
-    assert sent[0]["event"] == "scan_ended"
-    assert sent[0]["exit_reason"] == "budget_exceeded"

tests/test_tui_backend_controller.py

@@ -155,7 +155,7 @@ def test_setup_restores_prepared_cli_targets() -> None:
 async def test_start_validates_model_before_callback() -> None:
     started = False
 
-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
         nonlocal started
         started = True
 
@@ -170,7 +170,7 @@ async def test_start_validates_model_before_callback() -> None:
 async def test_start_launches_with_a_configured_model() -> None:
     started = False
 
-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
         nonlocal started
         started = True
 
@@ -189,7 +189,7 @@ async def test_start_launches_with_a_configured_model() -> None:
 async def test_start_without_target_requires_mount_consent() -> None:
     started = False
 
-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
         nonlocal started
         started = True
 
@@ -200,7 +200,7 @@ async def test_start_without_target_requires_mount_consent() -> None:
 
     # Mounting the working directory is never silent.
     with pytest.raises(ValueError, match="No target set"):
-        await controller.handle("setup.start", {})
+        await controller.handle("setup.start", {"verify": False})
     assert started is False
     assert controller.targets == []
     assert controller.workspace_mount is None
@@ -211,7 +211,7 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
     """Nothing is prepared until the live-view confirmation is answered."""
     started = False
 
-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
         nonlocal started
         started = True
 
@@ -220,7 +220,7 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
     loader._cached = None
     controller = TuiController(args(), on_start=start)
 
-    result = await controller.handle("setup.start", {"mount_working_dir": True})
+    result = await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
 
     assert result == {"started": True}
     # The live view is up so the prompt can be shown there, but the scan has not
@@ -236,23 +236,26 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
 @pytest.mark.asyncio
 async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:
     started = False
+    seen_verify: bool | None = None
 
-    async def start() -> None:
-        nonlocal started
+    async def start(verify: bool = True) -> None:
+        nonlocal started, seen_verify
         started = True
+        seen_verify = verify
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
     loader._cached = None
     controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
 
     result = await controller.handle("setup.confirm_mount", {"approved": True})
 
     assert result == {"approved": True}
     assert started is True
-    # Mounted as a workspace: the scan genuinely has no target, so the
-    # instruction is the only source of truth.
+    # Launched optimistically, and mounted as a workspace: the scan genuinely
+    # has no target, so the instruction is the only source of truth.
+    assert seen_verify is False
     assert controller.workspace_mount == str(Path.cwd())
     assert controller.targets == []
     assert controller.scan_state == "running"
@@ -261,23 +264,22 @@ async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:
 
 @pytest.mark.asyncio
 async def test_declining_the_mount_runs_without_one() -> None:
-    started = 0
+    started: list[bool] = []
 
-    async def start() -> None:
-        nonlocal started
-        started += 1
+    async def start(verify: bool = True) -> None:
+        started.append(verify)
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
     loader._cached = None
     controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
 
     result = await controller.handle("setup.confirm_mount", {"approved": False})
 
     assert result == {"approved": False}
     # Declining skips the directory; it does not abandon the scan.
-    assert started == 1
+    assert started == [False]
     assert controller.workspace_mount is None
     assert controller.pending_workspace_mount is None
     assert controller.setup_mode is False
@@ -287,22 +289,21 @@ async def test_declining_the_mount_runs_without_one() -> None:
 
 @pytest.mark.asyncio
 async def test_approving_the_mount_runs_with_it() -> None:
-    started = 0
+    started: list[bool] = []
 
-    async def start() -> None:
-        nonlocal started
-        started += 1
+    async def start(verify: bool = True) -> None:
+        started.append(verify)
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
     loader._cached = None
     controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
 
     result = await controller.handle("setup.confirm_mount", {"approved": True})
 
     assert result == {"approved": True}
-    assert started == 1
+    assert started == [False]
     assert controller.workspace_mount == str(Path.cwd())
     assert controller.scan_state == "running"
 
@@ -351,91 +352,23 @@ async def test_user_message_updates_live_agent_projection_immediately() -> None:
 
 
 @pytest.mark.asyncio
-async def test_start_verifies_the_model_before_a_targeted_launch() -> None:
-    order: list[str] = []
+async def test_start_forwards_verify_flag_by_default() -> None:
+    seen_verify: bool | None = None
 
-    async def verify() -> None:
-        order.append("verify")
-
-    async def start() -> None:
-        order.append("start")
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-    await controller.handle("setup.add_target", {"target": "https://example.com"})
-
-    await controller.handle("setup.start", {})
-
-    assert order == ["verify", "start"]
-
-
-@pytest.mark.asyncio
-async def test_start_verifies_the_model_before_a_bare_prompt_leaves_setup() -> None:
-    """A bare prompt gets the same model check as a named target, while the
-    setup log is still on screen to show the outcome."""
-    verified = 0
-
-    async def verify() -> None:
-        nonlocal verified
-        verified += 1
-
-    async def start() -> None:
-        return None
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-
-    await controller.handle("setup.start", {"mount_working_dir": True})
-
-    assert verified == 1
-    assert controller.setup_mode is False
-    assert controller.pending_workspace_mount == str(Path.cwd())
-
-
-@pytest.mark.asyncio
-async def test_failed_model_check_keeps_the_start_screen() -> None:
-    async def verify() -> None:
-        raise RuntimeError("Model connection failed: timed out")
-
-    async def start() -> None:
-        pytest.fail("the scan must not start when the model check fails")
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-
-    with pytest.raises(RuntimeError, match="Model connection failed"):
-        await controller.handle("setup.start", {"mount_working_dir": True})
-
-    # Still on the start screen, so the error lands in the setup log and the
-    # user can retry; no run was prepared behind a stuck live view.
-    assert controller.setup_mode is True
-    assert controller.scan_started is False
-    assert controller.scan_state == "setup"
-    assert controller.pending_workspace_mount is None
-
-
-@pytest.mark.asyncio
-async def test_confirmed_mount_launch_failure_is_reported_in_the_live_view() -> None:
-    async def start() -> None:
-        raise ValueError("Scan preparation failed")
+    async def start(verify: bool = True) -> None:
+        nonlocal seen_verify
+        seen_verify = verify
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
     loader._cached = None
     controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.add_target", {"target": "https://example.com"})
 
-    with pytest.raises(ValueError, match="Scan preparation failed"):
-        await controller.handle("setup.confirm_mount", {"approved": True})
+    # A named target keeps the upfront model check.
+    await controller.handle("setup.start", {})
 
-    assert controller.scan_state == "failed"
-    assert controller.error == "Scan preparation failed"
+    assert seen_verify is True
 
 
 @pytest.mark.asyncio
@@ -443,7 +376,7 @@ async def test_start_rejects_concurrent_and_repeated_submissions() -> None:
     entered = asyncio.Event()
     release = asyncio.Event()
 
-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
         entered.set()
         await release.wait()
 

tests/test_viewer.py

@@ -11,7 +11,7 @@ from typing import TYPE_CHECKING
 from urllib.parse import urlsplit
 
 from strix.core.paths import latest_run_dir, runs_base_dir
-from strix.interface.viewer.cli import _state_label, run_view
+from strix.interface.viewer.cli import run_view
 from strix.interface.viewer.server import serve
 from strix.interface.viewer.transcript import (
     build_run_state,
@@ -115,14 +115,6 @@ def test_read_run_summary_surfaces_mcp_connection_status(tmp_path: Path) -> None
     assert read_run_summary(run_dir)["mcp_connection_status"] == roster
 
 
-def test_viewer_cli_labels_terminal_statuses() -> None:
-    assert _state_label({"status": "completed", "finished": True}) == "[#22c55e]finished[/]"
-    assert _state_label({"status": "stopped", "finished": True}) == "[#eab308]stopped[/]"
-    assert _state_label({"status": "interrupted", "finished": True}) == "[#eab308]interrupted[/]"
-    assert _state_label({"status": "failed", "finished": True}) == "[#ef4444]failed[/]"
-    assert _state_label({"status": "running", "finished": False}) == "[#eab308]live[/]"
-
-
 def test_read_missing_artifacts_return_defaults(tmp_path: Path) -> None:
     run_dir = _make_run(tmp_path, "empty", status="running", end_time=None)
     assert read_vulnerabilities(run_dir) == []

tests/test_wait_dedupe.py

@@ -41,8 +41,6 @@ def _fast_wait(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
 async def _context() -> dict[str, Any]:
     coordinator = AgentCoordinator()
     await coordinator.register("root", "strix", parent_id=None)
-    # A live child keeps the wait genuine: with nobody to hear from it returns at once.
-    await coordinator.register("child", "recon", parent_id="root")
     return {"agent_id": "root", "coordinator": coordinator}
 
 

tests/test_web_search.py

@@ -1,416 +0,0 @@
-"""Tests for web_search/web_get_contents provider selection and the Exa backend."""
-
-from __future__ import annotations
-
-from typing import TYPE_CHECKING, Any
-
-import pytest
-import requests
-
-from strix.config.settings import IntegrationSettings
-from strix.interface.environment import _missing_web_search_vars
-from strix.tools.web_search import tool
-
-
-if TYPE_CHECKING:
-    from typing import Self
-
-
-class _FakeResponse:
-    def __init__(self, body: dict[str, Any]) -> None:
-        self._body = body
-        self.headers: dict[str, str] = {}
-
-    def __enter__(self) -> Self:
-        return self
-
-    def __exit__(self, *_exc: object) -> None:
-        return None
-
-    def raise_for_status(self) -> None:
-        return None
-
-    def json(self) -> dict[str, Any]:
-        return self._body
-
-
-def test_auto_prefers_exa_when_both_keys_set() -> None:
-    integrations = IntegrationSettings(PERPLEXITY_API_KEY="pk", EXA_API_KEY="ek")
-    assert tool._resolve_provider(integrations) == ("exa", "ek")
-
-
-def test_auto_falls_back_to_perplexity_when_only_perplexity_is_set() -> None:
-    integrations = IntegrationSettings(PERPLEXITY_API_KEY="pk")
-    assert tool._resolve_provider(integrations) == ("perplexity", "pk")
-
-
-def test_explicit_exa_ignores_a_configured_perplexity_key() -> None:
-    integrations = IntegrationSettings(
-        PERPLEXITY_API_KEY="pk",
-        EXA_API_KEY="ek",
-        STRIX_WEB_SEARCH_PROVIDER="exa",
-    )
-    assert tool._resolve_provider(integrations) == ("exa", "ek")
-
-
-def test_explicit_perplexity_ignores_a_configured_exa_key() -> None:
-    integrations = IntegrationSettings(
-        PERPLEXITY_API_KEY="pk",
-        EXA_API_KEY="ek",
-        STRIX_WEB_SEARCH_PROVIDER="perplexity",
-    )
-    assert tool._resolve_provider(integrations) == ("perplexity", "pk")
-
-
-def test_explicit_exa_without_a_key_names_only_exa() -> None:
-    integrations = IntegrationSettings(
-        PERPLEXITY_API_KEY="pk",
-        STRIX_WEB_SEARCH_PROVIDER="exa",
-    )
-    resolved = tool._resolve_provider(integrations)
-    assert isinstance(resolved, dict)
-    assert resolved["success"] is False
-    assert "EXA_API_KEY" in resolved["error"]
-    assert "PERPLEXITY_API_KEY" not in resolved["error"]
-
-
-def test_no_keys_names_both_providers() -> None:
-    resolved = tool._resolve_provider(IntegrationSettings())
-    assert isinstance(resolved, dict)
-    assert "EXA_API_KEY or PERPLEXITY_API_KEY" in resolved["error"]
-
-
-def test_exa_content_requests_summaries_and_renders_results(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    captured: dict[str, Any] = {}
-
-    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
-        captured["url"] = url
-        captured["headers"] = kwargs["headers"]
-        captured["json"] = kwargs["json"]
-        return _FakeResponse(
-            {
-                "results": [
-                    {
-                        "url": "https://nvd.example/cve",
-                        "title": "NVD entry",
-                        "summary": "  CVE-2024-0001 is a heap overflow.  ",
-                    },
-                    {"id": "https://blog.example/post"},
-                    "not-a-dict",
-                    {"title": "no url"},
-                ],
-            }
-        )
-
-    monkeypatch.setattr(requests, "post", fake_post)
-
-    content = tool._exa_content("ek", "OpenSSH 7.4 RCE?", "auto", 5)
-
-    assert captured["url"] == "https://api.exa.ai/search"
-    assert captured["headers"]["x-api-key"] == "ek"
-    assert "OpenSSH 7.4 RCE?" in captured["json"]["query"]
-    assert captured["json"]["type"] == "auto"
-    assert captured["json"]["numResults"] == 5
-    assert captured["json"]["contents"] == {"summary": {"query": tool._EXA_SUMMARY_PROMPT}}
-    assert content == (
-        "### NVD entry\nhttps://nvd.example/cve\nCVE-2024-0001 is a heap overflow.\n\n"
-        "### https://blog.example/post\nhttps://blog.example/post"
-    )
-
-
-def test_exa_content_renders_a_result_without_contents(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setattr(
-        requests,
-        "post",
-        lambda *_a, **_kw: _FakeResponse(
-            {"results": [{"url": "https://ex.example", "title": "Ex"}]}
-        ),
-    )
-    assert tool._exa_content("ek", "q", "auto", 5) == "### Ex\nhttps://ex.example"
-
-
-@pytest.mark.parametrize("body", [{}, {"results": None}, {"results": []}, {"results": ["x"]}])
-def test_exa_content_rejects_empty_results(
-    monkeypatch: pytest.MonkeyPatch, body: dict[str, Any]
-) -> None:
-    monkeypatch.setattr(requests, "post", lambda *_a, **_kw: _FakeResponse(body))
-    with pytest.raises(ValueError, match="no results"):
-        tool._exa_content("ek", "q", "auto", 5)
-
-
-def test_do_search_reports_empty_exa_results_as_unexpected(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(requests, "post", lambda *_a, **_kw: _FakeResponse({}))
-
-    result = tool._do_search("q")
-
-    assert result["success"] is False
-    assert "unexpected response" in result["error"]
-
-
-@pytest.mark.parametrize(
-    ("env", "expected"),
-    [
-        ({}, ["EXA_API_KEY", "PERPLEXITY_API_KEY"]),
-        ({"EXA_API_KEY": "ek"}, []),
-        ({"PERPLEXITY_API_KEY": "pk"}, []),
-        ({"STRIX_WEB_SEARCH_PROVIDER": "exa", "PERPLEXITY_API_KEY": "pk"}, ["EXA_API_KEY"]),
-        ({"STRIX_WEB_SEARCH_PROVIDER": "exa", "EXA_API_KEY": "ek"}, []),
-        ({"STRIX_WEB_SEARCH_PROVIDER": "perplexity", "EXA_API_KEY": "ek"}, ["PERPLEXITY_API_KEY"]),
-        ({"STRIX_WEB_SEARCH_PROVIDER": "perplexity", "PERPLEXITY_API_KEY": "pk"}, []),
-    ],
-)
-def test_environment_validation_follows_provider_rules(
-    env: dict[str, str], expected: list[str]
-) -> None:
-    integrations = IntegrationSettings.model_validate(env)
-    assert _missing_web_search_vars(integrations) == expected
-
-
-def test_exa_search_type_and_num_results_are_configurable(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    captured: dict[str, Any] = {}
-
-    class _Settings:
-        integrations = IntegrationSettings(
-            EXA_API_KEY="ek",
-            STRIX_EXA_SEARCH_TYPE="deep-reasoning",
-            STRIX_EXA_NUM_RESULTS=3,
-        )
-
-    def fake_post(_url: str, **kwargs: Any) -> _FakeResponse:
-        captured["json"] = kwargs["json"]
-        return _FakeResponse({"results": [{"url": "https://ex.example", "title": "Ex"}]})
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(requests, "post", fake_post)
-
-    assert tool._do_search("q")["success"] is True
-    assert captured["json"]["type"] == "deep-reasoning"
-    assert captured["json"]["numResults"] == 3
-
-
-def test_exa_page_text_requests_full_text_and_renders_pages(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    captured: dict[str, Any] = {}
-
-    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
-        captured["url"] = url
-        captured["headers"] = kwargs["headers"]
-        captured["json"] = kwargs["json"]
-        return _FakeResponse(
-            {
-                "results": [
-                    {
-                        "url": "https://nvd.example/cve",
-                        "title": "NVD entry",
-                        "text": "  Full advisory body.  ",
-                    },
-                    {"url": "https://empty.example", "text": "   "},
-                    "not-a-dict",
-                    {"text": "no url"},
-                ],
-            }
-        )
-
-    monkeypatch.setattr(requests, "post", fake_post)
-
-    content, fetched = tool._exa_page_text("ek", ["https://nvd.example/cve"])
-
-    assert captured["url"] == "https://api.exa.ai/contents"
-    assert captured["headers"]["x-api-key"] == "ek"
-    assert captured["json"] == {"urls": ["https://nvd.example/cve"], "text": True}
-    assert content == "### NVD entry\nhttps://nvd.example/cve\n\nFull advisory body."
-    assert fetched == {"https://nvd.example/cve"}
-
-
-def test_exa_page_text_truncates_a_long_page(monkeypatch: pytest.MonkeyPatch) -> None:
-    body = "A" * (tool._EXA_PAGE_MAX_CHARS + 500)
-    monkeypatch.setattr(
-        requests,
-        "post",
-        lambda *_a, **_kw: _FakeResponse(
-            {"results": [{"url": "https://ex.example", "text": body}]}
-        ),
-    )
-    content, _fetched = tool._exa_page_text("ek", ["https://ex.example"])
-    assert "truncated at" in content
-    assert content.count("A") == tool._EXA_PAGE_MAX_CHARS
-
-
-@pytest.mark.parametrize("body", [{}, {"results": []}, {"results": [{"url": "u"}]}])
-def test_exa_page_text_rejects_pages_without_text(
-    monkeypatch: pytest.MonkeyPatch, body: dict[str, Any]
-) -> None:
-    monkeypatch.setattr(requests, "post", lambda *_a, **_kw: _FakeResponse(body))
-    with pytest.raises(ValueError, match="no page contents"):
-        tool._exa_page_text("ek", ["https://ex.example"])
-
-
-@pytest.mark.parametrize("urls", [[], ["", "   "]])
-def test_do_get_contents_requires_a_url(urls: list[str]) -> None:
-    result = tool._do_get_contents(urls)
-    assert result["success"] is False
-    assert "at least one URL" in result["error"]
-
-
-def test_do_get_contents_caps_the_url_count() -> None:
-    urls = [f"https://ex{index}.example" for index in range(tool._EXA_MAX_CONTENT_URLS + 1)]
-    result = tool._do_get_contents(urls)
-    assert result["success"] is False
-    assert "Too many URLs" in result["error"]
-
-
-def test_do_get_contents_needs_an_exa_key(monkeypatch: pytest.MonkeyPatch) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(PERPLEXITY_API_KEY="pk")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-
-    result = tool._do_get_contents(["https://ex.example"])
-
-    assert result["success"] is False
-    assert "EXA_API_KEY" in result["error"]
-
-
-def test_do_get_contents_refuses_a_perplexity_pinned_provider(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(
-            EXA_API_KEY="ek",
-            PERPLEXITY_API_KEY="pk",
-            STRIX_WEB_SEARCH_PROVIDER="perplexity",
-        )
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-
-    result = tool._do_get_contents(["https://ex.example"])
-
-    assert result["success"] is False
-    assert "web_search" in result["error"]
-
-
-def test_do_get_contents_returns_page_text(monkeypatch: pytest.MonkeyPatch) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(tool, "_exa_page_text", lambda *_a: ("page", {"https://ex.example"}))
-
-    result = tool._do_get_contents([" https://ex.example "])
-
-    assert result == {
-        "success": True,
-        "urls": ["https://ex.example"],
-        "provider": "exa",
-        "content": "page",
-    }
-
-
-def test_do_get_contents_reports_urls_exa_did_not_return(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(
-        requests,
-        "post",
-        lambda *_a, **_kw: _FakeResponse(
-            {"results": [{"url": "https://ok.example/", "text": "Body."}]}
-        ),
-    )
-
-    result = tool._do_get_contents(["https://ok.example", "https://blocked.example"])
-
-    assert result["success"] is True
-    assert result["urls"] == ["https://ok.example"]
-    assert result["failed_urls"] == ["https://blocked.example"]
-    assert "1 of 2" in result["warning"]
-    assert "blocked.example" not in result["content"]
-
-
-def test_normalize_url_folds_only_scheme_and_host() -> None:
-    assert tool._normalize_url("HTTPS://Ex.Example/Path/") == tool._normalize_url(
-        "https://ex.example/Path"
-    )
-    assert tool._normalize_url("https://ex.example/Path") != tool._normalize_url(
-        "https://ex.example/path"
-    )
-    assert tool._normalize_url("https://ex.example/p?Q=A") != tool._normalize_url(
-        "https://ex.example/p?q=a"
-    )
-
-
-def test_do_get_contents_omits_the_warning_when_every_page_returns(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(
-        requests,
-        "post",
-        lambda *_a, **_kw: _FakeResponse(
-            {
-                "results": [
-                    {"url": "https://a.example", "text": "A."},
-                    {"url": "https://b.example", "text": "B."},
-                ]
-            }
-        ),
-    )
-
-    result = tool._do_get_contents(["https://a.example", "https://b.example"])
-
-    assert result["urls"] == ["https://a.example", "https://b.example"]
-    assert "failed_urls" not in result
-    assert "warning" not in result
-
-
-def test_do_get_contents_sanitizes_a_network_error(monkeypatch: pytest.MonkeyPatch) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    def boom(*_args: Any, **_kwargs: Any) -> None:
-        raise requests.exceptions.ConnectionError
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(requests, "post", boom)
-
-    result = tool._do_get_contents(["https://ex.example"])
-
-    assert result["success"] is False
-    assert "network error" in result["error"]
-    assert "ek" not in result["error"]
-
-
-def test_do_search_reports_the_provider_it_used(monkeypatch: pytest.MonkeyPatch) -> None:
-    class _Settings:
-        integrations = IntegrationSettings(EXA_API_KEY="ek")
-
-    monkeypatch.setattr(tool, "load_settings", _Settings)
-    monkeypatch.setattr(tool, "_exa_content", lambda *_a: "answer")
-
-    result = tool._do_search("OpenSSH 7.4 RCE?")
-
-    assert result == {
-        "success": True,
-        "query": "OpenSSH 7.4 RCE?",
-        "provider": "exa",
-        "content": "answer",
-    }

uv.lock

@@ -2378,7 +2378,7 @@ wheels = [
 
 [[package]]
 name = "strix-agent"
-version = "1.6.2"
+version = "1.6.0"
 source = { editable = "." }
 dependencies = [
     { name = "caido-sdk-client" },