b4bff7f0d0
fix(coding-agent): avoid project trust prompt for update ( #5674 )
2026-06-12 23:37:16 +02:00
adf567c1c6
fix(coding-agent): rechain fork paths without labels
...
closes #5669
2026-06-12 18:50:31 +02:00
1b2c32c653
fix(coding-agent): resolve authenticated slash model ids
...
closes #5643
2026-06-12 18:32:42 +02:00
6102dd2084
fix(coding-agent): handle missing export themes
...
closes #5596
2026-06-12 17:56:43 +02:00
1fc80f4f6c
fix(coding-agent): preserve custom fallback thinking
...
closes #5552
2026-06-12 17:26:42 +02:00
1da903983a
fix(coding-agent): skip first-time setup for forks ( #5627 )
2026-06-11 21:36:26 +02:00
406a2214aa
fix(coding-agent): refine setup copy
2026-06-10 19:55:19 +02:00
0ab2aa86af
feat(coding-agent): add experimental first-time setup flow ( #5587 )
...
Behind PI_EXPERIMENTAL=1, show a first-time setup dialog on interactive startup when the default agent directory is used and settings.json does not exist. The dialog preselects the detected terminal appearance with an explicit dark/light choice (live preview) and asks for opt-in analytics data sharing. Submitting writes settings.json, which serves as the completion marker; opting in stores a generated trackingId. Escape at any point skips out of setup.
2026-06-10 12:11:49 +02:00
aa03982169
fix(coding-agent): parse :thinking suffix from custom model IDs in fallback path
...
Fixes #5552
2026-06-10 02:01:35 +08:00
143b251e77
Merge branch 'main' into prompt-template-defaults
2026-06-09 14:23:00 +02:00
ae7a885da2
Closes #5045 , /new should not persist if original session was ephemeral
2026-06-09 14:17:33 +02:00
b7e721cb38
feat(tui): support autocomplete trigger characters
...
closes #4703
2026-06-09 14:15:39 +02:00
d81ac20920
feat(coding-agent): add prompt template argument defaults
2026-06-09 15:12:07 +03:00
d041b5cc35
Merge pull request #5549 from earendil-works/approval-settings
...
feat(ui): Improved project approval settings
2026-06-09 13:47:29 +02:00
c20ea06d4a
fix: --help and --version redirect
2026-06-09 13:43:54 +02:00
9632bddd38
fix(coding-agent): stabilize OAuth login prompt rows
...
closes #5433
2026-06-09 13:41:08 +02:00
359a0769f1
fix: simplify help
2026-06-09 13:36:05 +02:00
5cb4f597f7
feat(ui): Improved project approval settings
2026-06-09 13:25:54 +02:00
66335d3a49
feat(coding-agent): add experimental feature guard ( #5547 )
2026-06-09 13:23:07 +02:00
28c83e8385
fix(coding-agent): sync queue modes on reload
...
closes #5377
2026-06-09 13:21:59 +02:00
1906074369
fix(coding-agent): handle invalid models json during migration
...
closes #5418
2026-06-09 13:14:24 +02:00
e4907b3b09
fix(tui): restore prompt draft after history browsing
...
closes #5494
2026-06-09 13:06:13 +02:00
db3f9953ee
feat(coding-agent): expose project trust to extensions
...
closes #5523
2026-06-09 13:03:59 +02:00
20b78eafb4
fix(coding-agent): fix changelog links
...
Fixes #5516
2026-06-08 20:31:20 +02:00
d8aef0feff
feat(coding-agent): allow project trust extensions to defer
2026-06-08 13:38:29 +02:00
718215bd95
feat(coding-agent): add extension project trust decisions
2026-06-08 12:59:08 +02:00
38f18be447
fix(coding-agent): persist implicit project trust on reload
2026-06-08 10:08:01 +02:00
72fd911356
fix(coding-agent): neutralize compaction summarization prompt
...
closes #5401
2026-06-07 11:28:27 +02:00
eb43bd4493
fix(coding-agent): export package asset path helpers
...
closes #5415
2026-06-07 11:25:15 +02:00
b8f6f660e7
fix(ai): honor OpenAI Responses developer role compat
...
closes #5456
2026-06-07 11:07:36 +02:00
22ac2713a3
feat(coding-agent): export RPC extension UI types
...
closes #5455
2026-06-07 10:56:01 +02:00
ff3e9df5f5
fix(coding-agent): make trust input traversal portable
2026-06-06 22:32:35 +02:00
89a92207f1
feat(coding-agent): add project trust gating
2026-06-05 10:51:43 +02:00
db594d3a59
feat(coding-agent): show cache hit rate in footer
2026-06-05 10:51:43 +02:00
3e73204242
Merge pull request #5371 from Perlence/fix/skill-user-message-spacing
...
fix(coding-agent): add a space between the skill and user messages
2026-06-04 23:52:17 +02:00
c45787411e
Fix tool expand hint punctuation styling
...
closes #5359
2026-06-04 23:44:25 +02:00
e9a9322199
fix(coding-agent): add a space between the skill and user messages
2026-06-03 22:42:38 +04:00
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
ea3465a8e3
fix(coding-agent): move temporary extension cache ( #5345 )
2026-06-03 00:44:21 +02:00
135fb545f9
fix(coding-agent): set auth file mode on creation
2026-06-03 00:32:54 +02:00
ba6e5298df
fix(oauth): harden browser launch handling
2026-06-02 23:15:46 +02:00
a98e087e5d
fix(coding-agent): harden git package install paths
2026-06-02 18:20:35 +02:00
51df39b9b9
feat(ai): add ZAI Coding Plan China provider
2026-06-02 23:39:56 +08:00
25a4a8ed1e
Add Ant Ling provider
2026-06-02 16:37:44 +02:00
6cb23f9b5d
Fix HTML export URL sanitization
2026-06-02 16:32:18 +02:00
0d38e17b68
Fix empty self-rendered tool rows
...
closes #5299
2026-06-02 15:25:27 +02:00
6014801229
Add NVIDIA NIM provider
2026-06-02 15:09:36 +02:00
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
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
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
Armin Ronacher