Commit Graph

4622 Commits

Author SHA1 Message Date
Mario Zechner
592c34c056 Release v0.78.1 2026-06-04 18:31:33 +02:00
Mario Zechner
1d33a8eb7a Update generated image model list 2026-06-04 18:31:11 +02:00
Mario Zechner
4f7d756df8 Exclude optional Gondolin example from root check 2026-06-04 18:27:18 +02:00
Mario Zechner
e0c2813a2a Audit unreleased changelog entries 2026-06-04 18:22:58 +02:00
Mario Zechner
f9ce0bf0e7 Update generated model lists 2026-06-04 18:22:58 +02:00
Alexey Zaytsev
e4d6f45efe docs: document commit message format 2026-06-03 23:15:15 -05:00
Sviatoslav Abakumov
e9a9322199 fix(coding-agent): add a space between the skill and user messages 2026-06-03 22:42:38 +04:00
Vegard Stikbakke
dc7b547f62 docs(coding-agent): remove containerization platform note 2026-06-03 15:55:33 +02:00
Vegard Stikbakke
86314bf38d docs: add containerization guide and Gondolin example (#5356) 2026-06-03 15:53:16 +02:00
Mario Zechner
564ad70fb8 Merge pull request #5333 from vastxie/zai-coding-cn-provider
feat(ai): add ZAI Coding Plan China provider
2026-06-03 01:07:01 +02:00
Mario Zechner
4ac20511be Merge pull request #5346 from mattiacerutti/fix/remove-codex-models
fix(ai): remove stale codex models
2026-06-03 00:54:27 +02:00
Armin Ronacher
ea3465a8e3 fix(coding-agent): move temporary extension cache (#5345) 2026-06-03 00:44:21 +02:00
Armin Ronacher
135fb545f9 fix(coding-agent): set auth file mode on creation 2026-06-03 00:32:54 +02:00
Mattia Cerutti
83afcdc24f fix(ai): remove stale codex models 2026-06-03 00:09:30 +02:00
Armin Ronacher
ba6e5298df fix(oauth): harden browser launch handling 2026-06-02 23:15:46 +02:00
Armin Ronacher
a98e087e5d fix(coding-agent): harden git package install paths 2026-06-02 18:20:35 +02:00
弎水
51df39b9b9 feat(ai): add ZAI Coding Plan China provider 2026-06-02 23:39:56 +08:00
Armin Ronacher
0462d44f56 doc: clarify wording in SECURITY.md 2026-06-02 17:24:41 +02:00
Armin Ronacher
e30b1b18d0 Added security file 2026-06-02 17:03:40 +02:00
Mario Zechner
25a4a8ed1e Add Ant Ling provider 2026-06-02 16:37:44 +02:00
Mario Zechner
6cb23f9b5d Fix HTML export URL sanitization 2026-06-02 16:32:18 +02:00
Mario Zechner
7e72ca47c8 Add MiniMax-M3 to direct minimax providers
closes #5313
2026-06-02 16:00:29 +02:00
Mario Zechner
276cb1bb89 Fix stale SDK stream options test after httpIdleTimeoutMs universalization 2026-06-02 15:53:37 +02:00
Mario Zechner
2125221bfc Fix OpenRouter Kimi reasoning compat
closes #5309
2026-06-02 15:36:52 +02:00
Mario Zechner
0d38e17b68 Fix empty self-rendered tool rows
closes #5299
2026-06-02 15:25:27 +02:00
Mario Zechner
6e269edfd0 Restore NVIDIA Qwen 3.5 122B model 2026-06-02 15:10:36 +02:00
Mario Zechner
6014801229 Add NVIDIA NIM provider 2026-06-02 15:09:36 +02:00
Mario Zechner
13898f048f Fix TUI tab width accounting
closes #5218
2026-06-02 13:54:47 +02:00
Mario Zechner
4c6c4482b4 Fix SDK embed ENOENT when package.json missing (closes #5226)
- Wrap package.json read in try/catch to handle missing file gracefully
- Use defaults (APP_NAME=pi, CONFIG_DIR_NAME=.pi, etc.) when package.json not found
- Preserves rebranding via piConfig when package.json exists
- Only ignores ENOENT; other errors still throw
2026-06-02 12:12:10 +02:00
Mario Zechner
7c08227019 Fix stale model references in AI tests after model regeneration
- Update GitHub Copilot tests to use available models (claude-haiku-4.5, gemini-2.5-pro)
- Update OpenRouter tests to use available models (google/gemini-2.5-flash, deepseek/deepseek-chat)
- Fix over-broad sed that incorrectly renamed OpenAI Responses gpt-4o test
- Remove nvidia.md from repo root
- Update packages/ai/CHANGELOG.md
2026-06-02 11:37:32 +02:00
Mario Zechner
7c531d0518 fix: apply httpIdleTimeoutMs to all providers, not just Codex Responses
The HTTP timeout setting (httpIdleTimeoutMs) was only used as a fallback for the
openai-codex-responses API. For other providers like openai-completions
(llama.cpp), the SDK default timeout (10 min) was used instead, ignoring the
user's disabled timeout setting.

Now httpIdleTimeoutMs applies universally as the default SDK request timeout
for all providers that support timeoutMs. Setting HTTP timeout = false (0)
correctly disables SDK timeouts across the board by sending max int32
(effectively infinite) instead of 0, since SDKs treat timeout=0 as immediate
timeout.

closes #5294
2026-06-02 11:26:36 +02:00
Mario Zechner
f58c1702cf fix: apply httpIdleTimeoutMs to all providers, not just Codex Responses
The HTTP timeout setting (httpIdleTimeoutMs) was only used as a fallback for the
openai-codex-responses API. For other providers like openai-completions
(llama.cpp), the SDK default timeout (10 min) was used instead, ignoring the
user's disabled timeout setting.

Now httpIdleTimeoutMs applies universally as the default SDK request timeout
for all providers that support timeoutMs. Setting HTTP timeout = false (0)
correctly disables SDK timeouts across the board.

closes #5294
2026-06-02 11:20:38 +02:00
Mario Zechner
afcf9ff0dc Merge pull request #5306 from xl0/system_prompt_options
Add system prompt options to extension commands
2026-06-02 11:09:30 +02:00
Alexey Zaytsev
8216cca5a7 Add system prompt options to extension commands 2026-06-01 15:42:56 -05:00
Mario Zechner
e56521e323 Add extension mode context 2026-06-01 18:32:03 +02:00
Mario Zechner
335e09ba0d Merge pull request #5264 from psoukie/fix/wsl-mntc-footer-branch-refresh
fix(coding-agent): refresh branch in footer on WSL /mnt repos
2026-06-01 18:07:52 +02:00
Mario Zechner
34719d3f4f Fix Bedrock blank text blocks
closes #4975
2026-06-01 18:04:04 +02:00
Mario Zechner
893ba99466 Merge pull request #5235 from nicobailon/feat/issue-5129-tui-overlay-focus
Feat/issue 5129 tui overlay focus
2026-06-01 17:58:01 +02:00
github-actions[bot]
ce065efa7e chore: approve contributor vastxie 2026-06-01 15:03:47 +00:00
Nico Bailon
91a2f86600 fix(tui): harden overlay focus restoration 2026-05-31 21:20:33 -07:00
Pavel Soukenik
654e4529d5 fix: refresh branch in footer on WSL /mnt repos 2026-05-31 17:12:11 -07:00
Mario Zechner
f429ddbffd Fix OpenAI GPT-5.5 thinking metadata
closes #5243
2026-06-01 00:39:48 +02:00
github-actions[bot]
d4fa41ae3c chore: approve contributor psoukie 2026-05-31 22:22:22 +00:00
Mario Zechner
b177333026 Merge pull request #5221 from PriNova/fix/openrouter-system-role
Fix OpenRouter reasoning instruction role
2026-06-01 00:09:58 +02:00
Mario Zechner
ad9081b7fa Merge pull request #5251 from yzhg1983/fix/anthropic-opus-temperature
fix(ai): suppress deprecated temperature param for Claude Opus 4.7+
2026-06-01 00:03:07 +02:00
Michael Yu
40832d1957 fix(ai): suppress deprecated temperature param for Claude Opus 4.7+ 2026-05-31 16:20:22 +08:00
Nico Bailon
82f29ea442 docs(coding-agent): expand overlay focus demo
Update the overlay QA focus demo to exercise three visible overlays with text input, focus cycling, per-panel dismissal, and visual focus ordering.
2026-05-30 13:29:36 -07:00
Nico Bailon
735ccbd00f fix(tui): release overlay focus to explicit targets
Add an explicit overlay unfocus target so callers can move input to the editor or another component while overlays remain visible. Align fallback overlay focus with visual focus order and cover blocked replacement release, null targets, and multi-overlay cycling.
2026-05-30 13:29:36 -07:00
Nico Bailon
5d9b28ee43 fix(tui): keep focused overlays interactive after UI
Preserve a focused visible overlay as the input owner across extension custom UI replacement, while letting the replacement receive and close its own input before focus is restored. Fixes #5129.
2026-05-30 13:29:36 -07:00
Mario Zechner
3911d6f5cd fix(coding-agent): stream large session files
closes #5231
2026-05-30 21:21:42 +02:00