Commit graph

6356 commits

Author SHA1 Message Date
Armin Ronacher
f9bcd351dc docs(ai): document Codex WebSocket cleanup 2026-09-14 23:58:15 +02:00
github-actions[bot]
53816d7dcc chore: approve contributors from issue #9440 2026-09-14 15:05:33 +00:00
Vegard Stikbakke
ceea48f5d5 Revert "fix(ci): Fix a broken test"
This reverts commit 71dca871bc.
2026-09-14 10:28:54 +02:00
Vegard Stikbakke
0c7bb7c5c7 fix(ai): identify Responses error providers
closes #9298
2026-09-14 10:14:48 +02:00
Armin Ronacher
71dca871bc fix(ci): Fix a broken test 2026-09-11 19:42:45 +02:00
Christian Klotz
b215884021
feat(coding-agent): add customization documentation evals (#9491)
* fix(coding-agent): isolate extension eval documentation treatment

* feat(coding-agent): add custom provider documentation eval

* feat(coding-agent): add customization documentation evals

* feat(coding-agent): add repeatable eval reports
2026-09-11 17:29:34 +02:00
Vegard Stikbakke
713bdf38d5 Revert "fix(ai): update stale DeepSeek Flash test model IDs"
This reverts commit e8413008cd.
2026-09-11 15:08:41 +02:00
Mario Zechner
f3c672245d docs(agent): require typed status payloads for pico task writes 2026-09-11 12:57:47 +02:00
Mario Zechner
7b4cfd6eb0 docs(agent): define pico system sections and mutable registries 2026-09-11 11:49:58 +02:00
Mario Zechner
e8413008cd fix(ai): update stale DeepSeek Flash test model IDs 2026-09-11 11:49:52 +02:00
badlogic
62129190d8 docs(agent): status lives in task state 2026-09-11 07:59:38 +00:00
badlogic
d12cd92e45 docs(agent): guide notes for appending entries 2026-09-10 23:13:57 +00:00
badlogic
66b72dd783 docs(agent): turn tasks gate model-visible appends 2026-09-10 23:13:36 +00:00
badlogic
2176b9dd8f docs(agent): runtime schema bundle as a work item 2026-09-10 21:28:48 +00:00
badlogic
c7eee01950 docs(agent): scope out permissions, migration and the wire schema 2026-09-10 21:21:05 +00:00
badlogic
66f3b138fe docs(agent): note foreground dependencies on background work 2026-09-10 21:18:34 +00:00
badlogic
378977cd3d docs(agent): simplify input results and unify queued input 2026-09-10 21:08:28 +00:00
badlogic
1b5aa80aec docs(agent): tagged-union task state and derived orphaned variant 2026-09-10 20:25:12 +00:00
badlogic
b734a75634 docs(agent): pico handoff for outstanding decisions 2026-09-10 19:30:41 +00:00
github-actions[bot]
fcdc40e175 chore: approve contributors from issue #9323 2026-09-10 19:23:57 +00:00
Vegard Stikbakke
d92eb8d4b1 feat(ai): enable Fireworks Messages deferred tool loading 2026-09-10 21:18:35 +02:00
Mario Zechner
08dc60bc52 docs(agent): settle pico driver and storage contracts 2026-09-10 16:31:15 +02:00
David Brailovsky
4bd3f48df0 fix(ai): enable GLM-5.2 reasoning on Mistral
Use reasoning_effort instead of the ignored prompt_mode parameter.

Fixes #9375
2026-09-10 14:31:58 +02:00
David Brailovsky
2e6fe2f988 fix(ai): remove retired GPT-5.4 Codex models
Remove GPT-5.4 and GPT-5.4 mini from the OpenAI Codex catalog and update affected tests.

Fixes #9394
2026-09-10 14:25:55 +02:00
David Brailovsky
12f59336af fix(ai): update DeepSeek Flash catalog
Replace retired Flash aliases with the canonical deepseek-flash model and refresh DeepSeek pricing metadata.

Closes #9423
2026-09-10 14:14:19 +02:00
David Brailovsky
bbb61e34aa fix(ai): send OpenRouter session affinity headers by default
Send x-session-id for OpenRouter Chat Completions and Anthropic Messages requests while preserving explicit opt-out and cache-disabled behavior.

closes #9102
2026-09-10 10:37:44 +02:00
Vegard Stikbakke
519184eb65 fix(ai): accept Fireworks models in adaptive thinking metadata test
Update the catalog-wide assertion for metadata-driven Fireworks support while retaining the model-name restrictions for other providers. Add representative Fireworks models to the expected subset.
2026-09-10 10:31:35 +02:00
Vegard Stikbakke
6b94ae2ece fix(ai): preserve Fireworks thinking and native effort levels
Enable unsigned thinking replay and metadata-driven adaptive effort for Fireworks Messages models, with verified fallbacks for incomplete catalog metadata. Remove redundant GLM 5.2 and Kimi K3 effort aliases and add regression tests.

closes #9323
2026-09-10 09:51:31 +02:00
Vegard Stikbakke
e86102f18f fix(ai): send Codex Off reasoning effort
closes #9191
2026-09-10 09:06:27 +02:00
Vegard Stikbakke
46bde88a1c feat(coding-agent): support per-model compaction token budgets
Closes #8133
2026-09-10 08:37:20 +02:00
Mario Zechner
400d6905ce docs(agent): make pico input attribution explicit 2026-09-09 23:29:53 +02:00
Mario Zechner
05c6229813 docs(agent): settle pico task lifecycle 2026-09-09 21:55:37 +02:00
Mario Zechner
ce5ec9ca35 docs(agent): persist pico entry projections 2026-09-09 20:40:04 +02:00
Mario Zechner
2188891bf3 docs(agent): resolve pico context and state ordering 2026-09-09 19:03:48 +02:00
Mario Zechner
e045ed2f33 docs(agent): add pico design drafts 2026-09-09 19:03:48 +02:00
Mario Zechner
73f3257ddc docs(agent): preserve pico2 spike design for review 2026-09-09 19:03:47 +02:00
Christian Klotz
f3564a1d41
docs: validate documentation navigation and reachability (#9380)
* feat: use docs manifest for documentation evals

* feat: support nested documentation navigation

* docs(coding-agent): validate documentation reachability

* docs(coding-agent): remove catalog schema version
2026-09-09 17:34:42 +02:00
David Brailovsky
acaa253cc8 fix(coding-agent): validate extension tool parameter schemas
Reject malformed extension tools during registration instead of allowing them to break provider request serialization.

Fixes #9300
2026-09-09 12:15:18 +02:00
David Brailovsky
c37b0e03b5 fix: cap agent retry backoff
Add a configurable 60-second default cap for assistant and summarization retry delays across coding-agent and the agent harness.

Fixes #8826
2026-09-09 11:54:56 +02:00
David Brailovsky
be26e32704
docs: extract interactive testing and release guidance into skills (#9370) 2026-09-09 10:44:24 +02:00
David Brailovsky
561a2e066c fix(ai): send OpenCode session header
Map sessionId to x-opencode-session across OpenCode and OpenCode Go provider adapters, including requests with cache retention disabled. Preserve explicit caller header overrides.

Closes #9326
2026-09-09 10:10:31 +02:00
David Brailovsky
6160683a4a fix(coding-agent): await queue operations in concurrent tests
Account for asynchronous input handlers before asserting queued message state.
2026-09-08 17:30:54 +02:00
David Brailovsky
faa9863cb8 fix(coding-agent): run input handlers for queued messages
Apply input extension transforms and handling to direct steering and follow-up messages while preserving their input source.

Fixes #8718
2026-09-08 17:18:37 +02:00
Armin Ronacher
4a6ed01945
fix(coding-agent): update runtime dependencies (#9341) 2026-09-08 16:04:35 +02:00
Vegard Stikbakke
f53ac11351 fix(coding-agent): collapse empty fullscreen footers
closes #8919
2026-09-08 14:16:18 +02:00
David Brailovsky
3e4bc2680e Merge branch 'dev-named-forks-streaming' 2026-09-08 13:37:01 +02:00
David Brailovsky
41218b3940 fix(agent): relax fork lane validation and sequence conformance 2026-09-08 13:34:58 +02:00
David Brailovsky
d0963bf06a docs(agent): relax WP08 fork streaming requirements 2026-09-08 12:23:14 +02:00
David Brailovsky
96617628e8 fix(ai): use reasoning_effort for reasoning-capable mistral-medium-* models
Closes #8700
2026-09-08 10:30:28 +02:00
Mario Zechner
b2602be77c fix(ai): optimize EventStream queue
closes #9055
2026-09-07 22:26:47 +02:00