Commit graph

4 commits

Author SHA1 Message Date
Ian
dca9482c82 feat(core): opt-in parallel tool calls via STRIX_PARALLEL_TOOL_CALLS 2026-10-24 20:32:27 +03:00
Szymon Nastaly
972f5097c2
feat(llm): extra request-body fields via LLM_EXTRA_BODY (#1495)
Some checks failed
CI / python (push) Has been cancelled
CI / tui (push) Has been cancelled
CI / viewer (push) Has been cancelled
CI / package (push) Has been cancelled
CI / workflows (push) Has been cancelled
CI / ci-passed (push) Has been cancelled
* feat(llm): extra request-body fields via LLM_EXTRA_BODY

Some provider parameters, such as OpenAI's service_tier and
safety_identifier, are read only from the request body, so
LLM_EXTRA_HEADERS can't set them. LLM_EXTRA_BODY merges a JSON object
into the body of every request to the configured model, on both routing
paths. A dedicated dedupe model gets its own DEDUPE_LLM_EXTRA_BODY
instead, as with headers.

* fix(config): decode saved JSON-object settings when loading

persist_current() saves env values verbatim, so LLM_EXTRA_HEADERS,
LLM_EXTRA_BODY and their DEDUPE_ variants land in cli-config.json as JSON
text. The loader passed that text unchanged to the dict fields, so a later
launch without the env var failed validation. Decode saved strings for
dict fields, as pydantic-settings does for env vars.

---------

Co-authored-by: Szymon Nastaly <szymon.nastaly@autoform.ch>
2026-10-15 16:37:51 -04:00
ian-at-strix
d6db4f1f89
Stop false "ended without calling finish_scan" error on PR reviews (#1449)
Some checks are pending
CI / python (push) Waiting to run
CI / tui (push) Waiting to run
CI / viewer (push) Waiting to run
CI / package (push) Waiting to run
CI / workflows (push) Waiting to run
CI / ci-passed (push) Blocked by required conditions
* fix: don't log missing finish_scan when a PR review finished with finish_pr_review

* Updated comment
2026-10-05 19:58:20 -04:00
Ahmed Allam
06b158d1fa
fix(runner): settle child agents before closing sessions at wind-down (#1025) 2026-08-08 18:17:58 -07:00