getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-16 17:01:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1919 commits 13 branches 2 tags 46 MiB
Commit graph

576 commits

Author SHA1 Message Date
Mario Zechner
a613306e11 fix(ai): disable strict mode for OpenAI completions tool schemas 
OpenRouter with models like openai/gpt-5.2 enforces strict mode which
requires all properties in the required array. Setting strict: false
allows optional parameters without null unions, matching the approach
already used in openai-responses.ts.
 2026-01-10 00:19:02 +01:00
Mario Zechner
fe98895706 Better error messages on OpenRouter via openai-completions 2026-01-10 00:09:51 +01:00
Mario Zechner
c84f2f25de Fix lint warnings: use literal keys instead of bracket notation 2026-01-09 23:54:50 +01:00
Mario Zechner
c39250d0df Fix Google Cloud Code Assist OAuth for paid subscriptions 
- Properly handle long-running operations for project provisioning
- Support GOOGLE_CLOUD_PROJECT / GOOGLE_CLOUD_PROJECT_ID env vars for paid tiers
- Handle VPC-SC affected users
- Update docs for paid subscription requirements

Closes #582
 2026-01-09 23:32:46 +01:00
cmf
c7bac7583c Fix OAuth using Google Cloud Code Assist. 2026-01-09 23:31:11 +01:00
Aadish Verma
92eb6665fe
feat: add API pricing for antigravity models (#588) 2026-01-09 22:20:51 +01:00
Mario Zechner
35690f6d1a Merge branch 'fix/lazy-homedir-env-first' 2026-01-09 22:09:27 +01:00
Mario Zechner
32dd0d3cc4 Add changelog entries for PR 598 2026-01-09 20:50:23 +01:00
gnattu
58b903690b
Set strict parameter to false in OpenAI response mapping (#598) 
lm-studio hosted openai-like api endpoint requires this parameter to either be a defined boolean, or not specifying this option entirely. null will fail the API validation.
 2026-01-09 20:32:58 +01:00
Mario Zechner
60f5a03576 Add [Unreleased] section for next cycle 2026-01-09 20:24:50 +01:00
Mario Zechner
d856bb097c Release v0.42.1 2026-01-09 20:24:10 +01:00
Thomas Mustier
fbc4e89f84
fix(ai): skip zen tests when OPENCODE_API_KEY is not set (#605) 
The zen.test.ts file was added without the standard skipIf guard,
causing CI to fail on all PRs since no OPENCODE_API_KEY is configured.

This follows the same pattern used by other API-dependent tests.
 2026-01-09 18:41:12 +01:00
Helmut Januschka
b4351040a7
pi pi pi pew (#594) 2026-01-09 12:43:00 +01:00
jhyang
d2882c2643 Resolve os.homedir() lazily instead of at module load time 
- Move homedir() calls into functions for lazy evaluation
- Add GOOGLE_APPLICATION_CREDENTIALS support for Vertex AI
 2026-01-09 16:09:54 +08:00
Mario Zechner
5eb53cdb9e Add [Unreleased] section for next cycle 2026-01-09 07:00:09 +01:00
Mario Zechner
0752995424 Release v0.42.0 2026-01-09 06:59:26 +01:00
Mario Zechner
97d0189eae Add OpenCode Zen provider support 2026-01-09 06:58:20 +01:00
Mario Zechner
98b25baf4d Add [Unreleased] section for next cycle 2026-01-09 06:07:35 +01:00
Mario Zechner
ec9def84ef Release v0.41.0 2026-01-09 06:06:54 +01:00
Mario Zechner
19b5663340 Revert "Remove Anthropic OAuth support" 
This reverts commit f5e6bcac1b.
 2026-01-09 06:00:20 +01:00
Mario Zechner
f745321169 Clean-up. 2026-01-09 05:23:08 +01:00
Mario Zechner
439385afbc Add [Unreleased] section for next cycle 2026-01-09 05:12:52 +01:00
Mario Zechner
ebd661fe13 Release v0.40.1 2026-01-09 05:11:49 +01:00
Mario Zechner
f5e6bcac1b Remove Anthropic OAuth support 2026-01-09 05:10:33 +01:00
Mario Zechner
0cf4e1dbf9 Add [Unreleased] section for next cycle 2026-01-09 00:44:14 +01:00
Mario Zechner
070ef9c771 Release v0.40.0 2026-01-09 00:43:32 +01:00
Mario Zechner
36fbce85c2 Add [Unreleased] section for next cycle 2026-01-09 00:34:20 +01:00
Mario Zechner
39bfbb125c Release v0.39.1 2026-01-09 00:33:39 +01:00
Mario Zechner
307f9b4169 Add [Unreleased] section for next cycle 2026-01-09 00:10:41 +01:00
Mario Zechner
c25f1eab64 Release v0.39.0 2026-01-09 00:10:00 +01:00
Mario Zechner
ef7c52ffa1 chore: fix template literal lint, update AGENTS.md to require fixing all check output 2026-01-08 23:44:26 +01:00
Mario Zechner
16e142ef7d fix(ai): remove <thinking> tag wrapping, convert to plain text on cross-model handoff 
- Remove <thinking> tag generation from google-shared.ts, transorm-messages.ts, openai-completions.ts
- Thinking blocks now convert to plain text when switching models (prevents models mimicking tags)
- Skip empty thinking blocks to avoid API errors
- Keep thinking blocks only when same provider AND same model

fixes #561
 2026-01-08 21:19:16 +01:00
Mario Zechner
aa89080ea0 fix(ai): add bridge prompt to override Antigravity behavior with Pi defaults 2026-01-08 20:20:24 +01:00
Mario Zechner
aa91864715 chore: add changelog for #571, init theme with watcher in interactive mode 2026-01-08 20:10:39 +01:00
Mario Zechner
31f155d7db
Merge pull request #571 from ben-vargas/fix-antigravity-patch 
fix(ai): align antigravity request payload
 2026-01-08 20:00:40 +01:00
Mario Zechner
ba46a52415 docs: add changelog entries for #568 2026-01-08 18:54:21 +01:00
Ben Vargas
74476be61d fix(ai): align antigravity request payload 2026-01-08 10:00:44 -07:00
Thomas Mustier
a65da1c14b fix: ESC key not interrupting during Working... state 
Three related fixes:

1. google-gemini-cli: Handle abort signal in stream reading loop
   - Add abort event listener to cancel reader immediately when signal fires
   - Fix AbortError detection in retry catch block (fetch throws AbortError,
     not our custom message)
   - Swallow reader.cancel() rejection to avoid unhandled promise

2. agent-session: Fix retry attempt counter showing 0 on cancel
   - abortRetry() was resetting _retryAttempt before the catch block could
     read it for the error message

3. interactive-mode: Restore main escape handler on agent_start
   - When auto-retry starts, onEscape is replaced with retry-specific handler
   - auto_retry_end (which restores it) fires on turn_end, after streaming begins
   - Now restore immediately on agent_start if retry handler is still active

Amended: suppress reader.cancel() rejection on abort.
 2026-01-08 12:35:34 +00:00
Mario Zechner
cfa63c255d Add [Unreleased] section for next cycle 2026-01-08 04:53:51 +01:00
Mario Zechner
4b084d0f9d Release v0.38.0 2026-01-08 04:52:55 +01:00
Mario Zechner
6bcce1914a Merge branch 'codex-error-details-clean' 2026-01-08 03:17:33 +01:00
Mario Zechner
946efe4b45 fix(ai): detect context_length_exceeded overflow 2026-01-08 03:16:59 +01:00
Thomas Mustier
6052453f4f fix(ai): improve codex stream error details 2026-01-07 22:44:22 +00:00
Melih Mucuk
d311978dfd Merge branch 'main' into feat/custom-thinking-budgets 2026-01-08 00:39:11 +03:00
Mario Zechner
39fa25eb67 fix(ai): clean up openai-codex models and token limits 
- Remove model aliases (gpt-5, gpt-5-mini, gpt-5-nano, codex-mini-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-chat-latest)
- Fix context window from 400k to 272k tokens to match Codex CLI defaults
- Keep maxTokens at 128k (original value)
- Simplify reasoning effort clamping

closes #536
 2026-01-07 20:39:46 +01:00
Zhou Rui
d893ba7f20
fix(ai): clean up openai-codex models and token limits 2026-01-07 23:09:20 +08:00
Melih Mucuk
acec56c6b5 feat: add customizable thinking budgets for token-based providers 
Fixes #521
 2026-01-07 15:17:18 +03:00
Melih Mucuk
0f27eae77e feat: add thinkingBudgets option to customize token budgets 2026-01-07 15:13:26 +03:00
Mario Zechner
fcb3b4aa72 Add [Unreleased] section for next cycle 2026-01-07 01:33:34 +01:00
Mario Zechner
5514d4ffdb Release v0.37.8 2026-01-07 01:32:53 +01:00