10 Commits

Author SHA1 Message Date
devin-ai-integration[bot]
afa7c4a77f feat(web_search): add Exa as a web search provider alongside Perplexity (#1270) 2026-09-04 10:34:28 -07:00
Ahmed Allam
c514f712f4 fix(config): persist only the alias the runtime settings read
pydantic-settings takes the first alias present in the environment, even
when it is empty. persist_current() must save that same alias, so an empty
LLM_API_KEY does not let a non-empty OPENAI_API_KEY sibling land in the
file and restore a credential the run did not use.
2026-09-02 16:10:52 +03:00
Ahmed Allam
3e88e498b9 fix(config): drop the stored LLM connection when a linked env var changes
A new STRIX_LLM, LLM_API_KEY, or LLM_API_BASE exported in the shell must not
be combined with the key, base, or model still stored in cli-config.json.
Restore the pre-refactor rule: when any linked LLM connection var differs
from the stored value, discard the whole stored connection before loading
and before persisting. Unrelated stored settings are kept.
2026-09-02 16:10:52 +03:00
Ahmed Allam
ce0db30252 fix(config): merge env into cli-config.json instead of overwriting it
persist_current rewrote the config file with only the env vars set in the
shell, so a run whose STRIX_LLM or LLM_API_KEY came from the file erased
them and the next launch failed with MISSING REQUIRED ENVIRONMENT
VARIABLES. Start from the stored env block, let a set env var override or
replace the aliases of its field, and let an empty env var clear it.
2026-09-02 16:10:52 +03:00
devin-ai-integration[bot]
dbc427d816 feat(runtime): mount local targets instead of copying them in (#958)
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-08-02 07:45:10 -07:00
Ahmed Allam
74f334cb93 refactor(context): trim verbose comments 2026-07-26 14:38:12 -07:00
Ahmed Allam
8e9a6bf903 fix(context): reject tool-output byte ceilings below the notice size
A configured tool_output_max_bytes smaller than the truncation notice
itself can't fit a bounded preview, so a persisted result could exceed the
ceiling. Enforce a config floor (ge=1024) so nonsensical values are
rejected at load time instead of being worked around at runtime.
2026-07-26 14:38:12 -07:00
alex s
22d327d21f feat(settings): add force_required_tool_choice to LlmSettings (#730)
feat(inputs): implement logic for required tool choice based on model

test(inputs): add tests for force_required_tool_choice behavior

test(runner): update tests to include force_required_tool_choice in settings
2026-07-10 18:36:33 -04:00
sean-kim05
a5112f9433 fix(config): make env vars win over persisted JSON across all aliases (#689)
_read_json_overrides is documented to let env vars outrank the
persisted cli-config.json, but it decided per-alias and broke on the
first alias found in either env or the file. When a multi-alias field
(e.g. api_key via LLM_API_KEY/OPENAI_API_KEY) was set in the env under
one alias but stored in the file under another, the stale file value
was surfaced as an init kwarg and overrode the live env var. A
lowercase env var was also missed (settings use case_sensitive=False).

Decide whether a field is already set in the environment by checking
all of its aliases case-insensitively before consulting the file. Add
regression tests for the cross-alias and case-insensitive cases.

Closes #688
2026-07-06 11:36:41 -04:00
Rome Thorstenson
f342808d2b test: add unit tests for config loader (strix/config/loader.py) (#596)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-30 04:31:29 -07:00