e4172e68d0
feat(ai): add claude-sonnet-4-6 to Antigravity, fix Claude thinking header detection, bump UA to 1.18.4
...
closes #1859
2026-03-06 13:27:35 +01:00
b4e7d5c445
fix(ai): restore OpenAI Responses reasoning replay closes #1878
2026-03-06 12:39:55 +01:00
b14c359289
Add [Unreleased] section for next cycle
2026-03-06 00:42:35 +01:00
45a8499c8f
Release v0.56.2
2026-03-06 00:41:33 +01:00
4110d93369
docs(changelog): audit unreleased entries
2026-03-06 00:39:41 +01:00
863135d429
fix(ai): keep mistral browser-safe
2026-03-06 00:16:18 +01:00
a31065166d
Merge branch 'feat/use-mistral-sdk'
2026-03-05 23:49:29 +01:00
4c175790b1
fix(ai): preserve mistral thinking replay
2026-03-05 23:49:18 +01:00
0573612a89
fix(ai,coding-agent): simplify oauth subpath exports closes #1856
2026-03-05 23:28:56 +01:00
a74b18ca5a
docs(changelog): add gpt-5.4 entries
2026-03-05 23:07:43 +01:00
16ec7de29c
fix(ai): cap gpt-5.4 context windows to 272k
2026-03-05 22:57:20 +01:00
f8d731a134
fix codex context window and add a few tests
2026-03-05 22:54:16 +01:00
8a6384a925
add support for gpt-5.4
2026-03-05 22:53:08 +01:00
a0d839ce84
fix(ai): use skip_thought_signature_validator for unsigned Gemini 3 tool calls
...
Replace text fallback with the official sentinel value so unsigned function
calls retain structured context in multi-turn conversations.
closes #1829
2026-03-05 22:04:00 +01:00
cfbb15876a
fix(ai): antigravity endpoint cascade on 403/404, add autopush fallback, strip extra headers
...
closes #1830
2026-03-05 21:59:43 +01:00
8f2af2ae7e
feat(ai): add github-copilot gpt-5.3-codex fallback closes #1853
2026-03-05 21:47:52 +01:00
8fc2b76827
fix(ai): omit empty OpenAI Responses thinking blocks on replay
2026-03-05 21:28:16 +01:00
87d71380e2
fix(ai): preserve OpenAI Responses assistant phase across turns closes #1819
2026-03-05 21:13:06 +01:00
708ce9d4ce
Add [Unreleased] section for next cycle
2026-03-05 07:14:13 +01:00
ab00c80892
Release v0.56.1
2026-03-05 07:13:27 +01:00
3e611c135b
Add [Unreleased] section for next cycle
2026-03-04 21:24:33 +01:00
e39c7d163b
Release v0.56.0
2026-03-04 21:23:47 +01:00
cefb17dbd7
docs(changelog): add missing unreleased entries after v0.55.4
2026-03-04 21:19:14 +01:00
668ebc0941
fix(ai): replace Function-based dynamic imports with module imports ( fixes #1814 )
2026-03-04 20:50:14 +01:00
0199abfd11
fix(binary): preload Bedrock provider module for Bun bundle
...
refs #1814
2026-03-04 20:47:41 +01:00
e0754fdbb3
fix(ai,coding-agent): make pi-ai browser-safe and move OAuth runtime exports
...
- add browser smoke bundling check to root check + pre-commit
- lazy-load Bedrock provider registration to avoid browser graph traversal
- remove top-level OAuth runtime exports from @mariozechner/pi-ai
- add @mariozechner/pi-ai/oauth subpath export and update coding-agent imports
- move proxy dispatcher init to coding-agent CLI (Node-only)
- document Bedrock/OAuth browser limitations
closes #1814
2026-03-04 20:21:25 +01:00
2af0c98b5f
fix(ai): support gemini-3.1 flash-lite and thinking matching
...
closes #1785
2026-03-04 20:17:58 +01:00
8e157412a6
Update AGENTS.md
2026-03-04 18:06:26 +01:00
d4b473e298
fix(ai): respect region from profile config when AWS_PROFILE is set ( #1800 )
2026-03-04 08:56:06 +01:00
eb9f1183ad
refactor(ai): migrate mistral provider to conversations sdk
2026-03-03 17:25:50 +00:00
7b96041068
fix(ai): map groq qwen3 reasoning effort values closes #1745
2026-03-03 16:44:42 +01:00
42579dd923
feat(ai,coding-agent): add OpenCode Go provider support closes #1757
2026-03-03 16:02:29 +01:00
7bd4c45d81
fix(ai,coding-agent): update antigravity gemini 3.1 models and headers
...
fixes #1761
2026-03-03 14:54:43 +01:00
76a191c264
fix(scripts): make npm scripts cross-platform with shx ( closes #1771 )
2026-03-03 14:26:01 +01:00
c65de34e11
Add [Unreleased] section for next cycle
2026-03-02 23:25:10 +01:00
9a53d950c4
Release v0.55.4
2026-03-02 23:24:27 +01:00
105e296b69
chore(ai): update generated models data
2026-03-02 19:41:38 +01:00
95276df060
Add [Unreleased] section for next cycle
2026-02-27 22:54:44 +01:00
9d68043cbc
Release v0.55.3
2026-02-27 22:54:03 +01:00
edca5dd769
Add [Unreleased] section for next cycle
2026-02-27 22:26:46 +01:00
10180037d2
Release v0.55.2
2026-02-27 22:26:00 +01:00
15e0a74a3c
docs: audit and add missing changelog entries for v0.55.1..HEAD
2026-02-27 22:25:03 +01:00
9825c13f5f
fix(ai): handle redacted_thinking blocks, skip interleaved beta for adaptive models, drop temperature with thinking
...
- Map redacted_thinking to ThinkingContent with redacted: true instead of
adding a new content type. The opaque payload goes in thinkingSignature,
thinking text is set to "[Reasoning redacted]" so it renders naturally
everywhere. Cross-model transform drops redacted blocks.
- Skip interleaved-thinking-2025-05-14 beta header for Opus 4.6 / Sonnet 4.6
where adaptive thinking makes it deprecated/redundant.
- Do not send temperature when thinkingEnabled is true (incompatible with
both adaptive and budget-based thinking).
Based on #1665 by @tctev
2026-02-27 21:53:25 +01:00
afe9ae06e8
Closes #1671 , switch to GLM-5 for tests
2026-02-27 21:35:40 +01:00
187a99c720
docs(ai): add changelog entry for Z.ai thinking fix #1674
2026-02-27 21:33:42 +01:00
22b3be834e
fix(ai): use enable_thinking for Z.ai instead of thinking param ( #1674 )
...
Z.ai uses the same enable_thinking: boolean parameter as Qwen to control reasoning, not thinking: { type: "enabled" | "disabled" }.
The wrong parameter name means Z.ai ignores the disable request and always runs with thinking enabled, wasting tokens and adding latency.
Merge the Z.ai and Qwen branches since they use the same format.
PR by @okuyam2y
2026-02-27 21:33:14 +01:00
8880cd3cb8
Manual merge of #1677
2026-02-27 21:27:55 +01:00
3dcb3c1c77
Merge branch 'pr-1669-fixes'
...
# Conflicts:
# package-lock.json
# packages/ai/CHANGELOG.md
# packages/coding-agent/CHANGELOG.md
2026-02-27 21:04:00 +01:00
2f55890452
fix(coding-agent,ai): finalize provider unregister lifecycle and dependency security updates fixes #1669
2026-02-27 21:00:25 +01:00
9a0a8d7ccb
Add [Unreleased] section for next cycle
2026-02-26 01:10:55 +01:00
Mario Zechner