getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 19:05:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1037 commits 13 branches 2 tags 46 MiB
Commit graph

222 commits

Author SHA1 Message Date
Mario Zechner
299986f06b Release v0.25.2 2025-12-21 02:59:03 +01:00
Mario Zechner
c97702cf91 Release v0.25.1 2025-12-21 02:43:47 +01:00
Mario Zechner
df07a74ad5 Release v0.25.0 2025-12-20 22:02:47 +01:00
Mario Zechner
085294b764 Release v0.24.5 2025-12-19 22:09:35 +01:00
Mario Zechner
f377c3c9c3 Release v0.24.4 2025-12-19 21:54:36 +01:00
Mario Zechner
ad4eb3afa6 Release v0.24.3 2025-12-19 21:36:16 +01:00
Mario Zechner
5095b4eb02 Release v0.24.2 2025-12-19 21:12:53 +01:00
Mario Zechner
50b055f3ae Release v0.24.1 2025-12-19 20:51:44 +01:00
Mario Zechner
16685a36ec Release v0.24.0 2025-12-19 05:21:25 +01:00
Mario Zechner
f92147ffe8 Release v0.23.5 2025-12-19 05:15:34 +01:00
Ahmed Kamal
1167e84453
Fix expired OAuth tokens in long-running agent loops (#223) 
Add getApiKey hook to AgentLoopConfig that resolves API keys dynamically
before each LLM call. This allows short-lived OAuth tokens (e.g. GitHub
Copilot, Anthropic OAuth) to be refreshed between turns when tool
execution takes a long time.

Previously, the API key was resolved once when ProviderTransport.run()
was called and passed as a static string to the agent loop. If the loop
ran for longer than the token lifetime (e.g. 30 minutes for Copilot),
subsequent LLM calls would fail with expired token errors.

Changes:
- Add getApiKey hook to AgentLoopConfig (packages/ai)
- Call getApiKey before each LLM call in streamAssistantResponse
- Update ProviderTransport to pass getApiKey instead of static apiKey
- Update web-ui ProviderTransport with same pattern
 2025-12-19 01:36:25 +01:00
Mario Zechner
2f86c8bc3c Release v0.23.4 2025-12-18 16:56:50 +01:00
Mario Zechner
b02516a5cd Switch to more stable, oldder tsgo, switch all check scripts to tsgo 2025-12-18 15:20:41 +01:00
Mario Zechner
00851369fc Release v0.23.3 2025-12-17 22:29:46 +01:00
Mario Zechner
4894fa411c Release v0.23.2 
Fixed Claude models via GitHub Copilot re-answering all previous prompts.

fixes #209
 2025-12-17 17:56:00 +01:00
Mario Zechner
46ba48a35d Release v0.23.1 2025-12-17 16:43:09 +01:00
Mario Zechner
67b73d018f Release v0.23.0 2025-12-17 16:13:32 +01:00
Mario Zechner
295f51b53f Release v0.22.5 2025-12-17 01:22:13 +01:00
Mario Zechner
03b061773c Release v0.22.4 
- Add --list-models CLI flag for listing/finding models with fuzzy search

fixes #203
 2025-12-17 00:39:14 +01:00
Mario Zechner
deee1c2952 Release v0.22.3 2025-12-16 20:06:05 +01:00
Mario Zechner
fd5134f88c Release v0.22.2 2025-12-15 22:09:14 +01:00
Mario Zechner
a7e3b8625b Release v0.22.1 2025-12-15 21:53:27 +01:00
Mario Zechner
04058d5812 Release v0.22.0 2025-12-15 20:14:25 +01:00
Mario Zechner
3b440bb13b Release v0.21.0 2025-12-13 23:55:31 +01:00
Mario Zechner
aed17da044 Release v0.20.2 2025-12-13 01:11:36 +01:00
Mario Zechner
59cf6c717b Release v0.20.1 2025-12-13 00:57:12 +01:00
Mario Zechner
a5268d2aa7 Release v0.20.0 2025-12-12 23:25:01 +01:00
Mario Zechner
236856aa48 Release v0.19.2 2025-12-12 23:03:01 +01:00
Mario Zechner
948b4115c1 Release v0.19.1 2025-12-12 17:53:45 +00:00
Mario Zechner
e3dadeb4e7 Release v0.19.0 2025-12-12 17:33:16 +00:00
Mario Zechner
c6a4c1da95 Release v0.18.8 2025-12-12 11:30:11 +01:00
Mario Zechner
80a04fb1aa Release v0.18.7 2025-12-12 11:15:26 +01:00
Mario Zechner
dba2674681 Release v0.18.6 2025-12-12 10:53:53 +01:00
Mario Zechner
44e9b1c8e9 Release v0.18.5 2025-12-12 10:00:57 +01:00
Mario Zechner
652ac0fa36 Release v0.18.4 2025-12-12 00:00:08 +01:00
Mario Zechner
a13c8c34f5 Release v0.18.3 2025-12-11 20:34:04 +01:00
Mario Zechner
b40ecf0ee1 Release v0.18.2 2025-12-10 23:39:16 +01:00
Mario Zechner
f931c57726 Release v0.18.1 2025-12-10 21:25:15 +01:00
Mario Zechner
7785b7c93f Release v0.18.0 2025-12-10 01:18:13 +01:00
Mario Zechner
2d9ecd1750 Release v0.17.0 2025-12-09 21:47:39 +01:00
Mario Zechner
5a9d844f9a Simplify compaction: remove proactive abort, use Agent.continue() for retry 
- Add agentLoopContinue() to pi-ai for resuming from existing context
- Add Agent.continue() method and transport.continue() interface
- Simplify AgentSession compaction to two cases: overflow (auto-retry) and threshold (no retry)
- Remove proactive mid-turn compaction abort
- Merge turn prefix summary into main summary
- Add isCompacting property to AgentSession and RPC state
- Block input during compaction in interactive mode
- Show compaction count on session resume
- Rename RPC.md to rpc.md for consistency

Related to #128
 2025-12-09 21:43:49 +01:00
Mario Zechner
796112f40f Release v0.16.0 2025-12-09 15:43:29 +01:00
Mario Zechner
dcf81a6a1a Release v0.15.0 
closes #153
 2025-12-09 13:41:12 +01:00
Mario Zechner
33a2bcf203 Release v0.14.2 2025-12-08 23:29:05 +01:00
Mario Zechner
a054fecd11 Release v0.14.1 2025-12-08 22:59:46 +01:00
Mario Zechner
0bc8d79216 Release v0.14.0 2025-12-08 22:51:29 +01:00
Mario Zechner
a0bbc29201 Release v0.13.2 2025-12-07 01:25:17 +01:00
Mario Zechner
95eadb9ed7 Release v0.13.1 2025-12-06 23:12:36 +01:00
Mario Zechner
ecdbd88f5d Release v0.13.0 2025-12-06 22:48:39 +01:00
Mario Zechner
86e5a70ec4 Add totalTokens field to Usage type 
- Added totalTokens field to Usage interface in pi-ai
- Anthropic: computed as input + output + cacheRead + cacheWrite
- OpenAI/Google: uses native total_tokens/totalTokenCount
- Fixed openai-completions to compute totalTokens when reasoning tokens present
- Updated calculateContextTokens() to use totalTokens field
- Added comprehensive test covering 13 providers

fixes #130
 2025-12-06 22:46:02 +01:00