Nimrod Gutman
dadd7f99cd
fix(ci): scope secrets scan to branch changes
2026-03-08 22:21:49 +02:00
Peter Steinberger
a075baba84
refactor(browser): scope CDP sessions and harden stale target recovery
2026-03-08 19:52:33 +00:00
Peter Steinberger
3ada30e670
fix: restore gate after rebase
2026-03-08 18:40:15 +00:00
Peter Steinberger
11be305609
refactor: neutralize context engine runtime bridge
2026-03-08 18:40:15 +00:00
Mariano
404b1527e6
fix(acp): persist spawned child session history ( #40137 )
...
Merged via squash.
Prepared head SHA: 62de5d5669132747814+mbelinky@users.noreply.github.com >
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com >
Reviewed-by: @mbelinky
2026-03-08 19:37:00 +01:00
Peter Steinberger
72ebaf97c3
test: add implicit provider matrix coverage
2026-03-08 18:26:36 +00:00
Peter Steinberger
8ab762c005
test: standardize hermetic provider env snapshots
2026-03-08 18:26:36 +00:00
Peter Steinberger
52bc809143
refactor: extract provider stream wrappers
2026-03-08 18:26:36 +00:00
Peter Steinberger
6094035054
refactor: extract static provider builders
2026-03-08 18:26:36 +00:00
Peter Steinberger
e53d840fed
refactor: extract openai stream wrappers
2026-03-08 18:26:36 +00:00
Peter Steinberger
f66bd105a4
refactor: decompose implicit provider resolution
2026-03-08 18:26:36 +00:00
Peter Steinberger
ef2541ceb3
refactor: centralize transcript provider quirks
2026-03-08 18:26:35 +00:00
Peter Steinberger
749eb4efea
refactor: thread config runtime env through models config
2026-03-08 18:26:35 +00:00
Peter Steinberger
e5c06dd64a
refactor: use model compat for anthropic tool payload normalization
2026-03-08 18:26:35 +00:00
Vincent Koc
7856f5730c
Web search: allowlist Perplexity auth source type name
2026-03-08 11:16:03 -07:00
Vincent Koc
6f4de3cc23
Web search: rename Perplexity auth source helper
2026-03-08 11:16:03 -07:00
Vincent Koc
f19761cefa
Tests: reduce web search secret-scan noise
2026-03-08 11:16:03 -07:00
Vincent Koc
5387faa718
CI: satisfy provider merge fixture typing
2026-03-08 11:15:48 -07:00
GitBuck
caf1b84822
feat: allow compaction model override via config ( #38753 )
...
Merged via squash.
Prepared head SHA: a3d6d6c84525417736+starbuck100@users.noreply.github.com >
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com >
Reviewed-by: @jalehman
2026-03-08 10:47:34 -07:00
Peter Steinberger
95dff166cb
refactor: fold implicit provider injection into resolver
2026-03-08 16:22:52 +00:00
Peter Steinberger
bce9d93fb5
fix: publish models.json atomically
2026-03-08 16:22:52 +00:00
Peter Steinberger
bec3c0b71d
refactor: reuse one models.json read per write
2026-03-08 16:22:52 +00:00
Peter Steinberger
b41bcb08a2
refactor: expand provider capability registry
2026-03-08 16:22:52 +00:00
Peter Steinberger
75e1521660
refactor: extract pure models config merge helpers
2026-03-08 16:22:52 +00:00
Peter Steinberger
79c5c660bb
fix: treat model api drift as baseUrl refresh
2026-03-08 16:22:52 +00:00
Ayaan Zaidi
28e46d04e5
fix(web-search): restore OpenRouter compatibility for Perplexity ( #39937 ) ( #39937 )
2026-03-08 20:37:54 +05:30
Peter Steinberger
eba9dcc67a
Refactor release hardening follow-ups ( #39959 )
...
* build: fail fast on stale host-env swift policy
* build: sync generated host env swift policy
* build: guard bundled extension root dependency gaps
* refactor: centralize provider capability quirks
* test: table-drive provider regression coverage
* fix: block merge when prep branch has unpushed commits
* refactor: simplify models config merge preservation
2026-03-08 14:49:58 +00:00
Varun Chopra
097c588a6b
transcript-policy: use named Set for anthropic signature-excluded providers
2026-03-08 14:16:21 +00:00
Varun Chopra
2bf53c2cb6
transcript-policy: don't preserve thinking signatures for kimi-coding ( #39798 )
2026-03-08 14:16:21 +00:00
GeekCheyun
76e4b8277f
fix(issue-39839): address tool-call extra params parsing for kimi anthropic-messages
2026-03-08 14:14:06 +00:00
Peter Steinberger
acac7e3132
fix: land Brave llm-context gaps ( #33383 ) (thanks @thirumaleshp)
2026-03-08 13:57:12 +00:00
Thirumalesh
8a1015f1aa
feat: add Brave Search LLM Context API mode for web_search
...
Add support for Brave's LLM Context API endpoint (/res/v1/llm/context)
as an optional mode for the web_search tool. When configured with
tools.web.search.brave.mode set to llm-context, the tool returns
pre-extracted page content optimized for LLM grounding instead of
standard URL/snippet results.
The llm-context cache key excludes count and ui_lang parameters that
the LLM Context API does not accept, preventing unnecessary cache
misses.
Closes #14992
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-08 13:57:12 +00:00
Peter Steinberger
d91d24e41d
refactor: tighten codex inline api fallback follow-up
2026-03-08 13:54:21 +00:00
justinhuangcode
c9f2d6b761
fix(agents): let forward-compat resolve api when inline model omits it
...
When a user configures `models.providers.openai-codex` with a models
array but omits the `api` field, `buildInlineProviderModels` produces
an entry with `api: undefined`. The inline-match early return then
hands this incomplete model straight to the caller, skipping the
forward-compat resolver that would supply the correct
`openai-codex-responses` api — causing a crash loop.
Let the inline match fall through to forward-compat when `api` is
absent so the resolver chain can fill it in.
Fixes #39682
2026-03-08 13:51:37 +00:00
Kros Dai
e9d51d874b
Models: fix codex follow-up CI issues
2026-03-08 13:48:13 +00:00
Kros Dai
ec75643a09
Models: scope implicit codex baseUrl override
2026-03-08 13:48:13 +00:00
Kros Dai
374001c4a0
fix: add implicit openai-codex provider snapshot
2026-03-08 13:48:13 +00:00
Peter Steinberger
eebee84093
fix(models): discover Vercel AI Gateway catalog
2026-03-08 13:44:10 +00:00
Peter Steinberger
f66cc886d3
test(agents): normalize live model not-found skips
2026-03-08 13:44:10 +00:00
arceus77-7
492fe679a7
feat(tui): infer workspace agent when launching TUI ( #39591 )
...
Merged via squash.
Prepared head SHA: 23533e24c4261276524+arceus77-7@users.noreply.github.com >
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com >
Reviewed-by: @altaywtf
2026-03-08 13:31:11 +03:00
gambletan
8a20f51460
fix: add rate limit patterns for 'too many tokens' and 'tokens per day' ( #39377 )
...
Merged via squash.
Prepared head SHA: 132a457286266203672+gambletan@users.noreply.github.com >
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com >
Reviewed-by: @altaywtf
2026-03-08 13:03:33 +03:00
Peter Lee
92648f9ba9
fix(agents): broaden 402 temporary-limit detection and allow billing cooldown probe ( #38533 )
...
Merged via squash.
Prepared head SHA: 282b9186c622994703+xialonglee@users.noreply.github.com >
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com >
Reviewed-by: @altaywtf
2026-03-08 10:27:01 +03:00
Peter Steinberger
5d22bd0297
fix: add google flash-lite forward compat
2026-03-08 05:22:38 +00:00
Peter Steinberger
59102a1ff7
fix: add gemini 3.1 flash-lite support
2026-03-08 05:12:48 +00:00
Peter Steinberger
a035a3ce48
fix: drop removed minimax lightning model
2026-03-08 04:06:26 +00:00
Peter Steinberger
a8c67affd8
test: cover gemini flash compat normalization
2026-03-08 02:34:49 +00:00
Peter Steinberger
100da9f45c
fix: correct gemini flash model id
2026-03-08 02:32:58 +00:00
Vincent Koc
f494e46ea0
Ollama: allowlist test api keys
2026-03-07 18:00:13 -08:00
Peter Steinberger
5b257c65d5
fix: default codex-cli sandbox to workspace-write
...
Landed from contributor PR #39336 by @0xtangping.
Co-authored-by: john <john.j@min123.net >
2026-03-08 01:58:34 +00:00
Vincent Koc
daecd2d8c3
Pi Runner: gate parallel_tool_calls to compatible APIs ( #39356 )
...
* Pi Runner: gate parallel_tool_calls payload injection
* Pi Runner: cover parallel_tool_calls alias precedence
* Changelog: note parallel_tool_calls compatibility fix
* Update CHANGELOG.md
* Pi Runner: clarify null parallel_tool_calls override logging
2026-03-07 17:57:53 -08:00
