torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
930 Commits 1 Branch 0 Tags
bd666227c8f7557483f7e24fb8544fc0456600dc
Commit Graph

930 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Fahad
bd666227c8 docs: instructions for OpenCode 2025-10-04 23:22:26 +04:00
Fahad
615873c3db docs: updated intro 2025-10-04 23:11:37 +04:00
github-actions[bot]
8296bf871c chore: sync version to config.py [skip ci] 2025-10-04 19:08:56 +00:00
semantic-release
6375aa16ac chore(release): 6.1.0 
Automatically generated by python-semantic-release
 2025-10-04 19:08:52 +00:00
Fahad
fe9968b633 feat: support for Qwen Code 2025-10-04 23:07:50 +04:00
Fahad
aa6539472c docs: Updated intro 2025-10-04 21:58:00 +04:00
github-actions[bot]
18095d7d39 chore: sync version to config.py [skip ci] 2025-10-04 17:21:42 +00:00
semantic-release
16be7d77b0 chore(release): 6.0.0 
Automatically generated by python-semantic-release
 2025-10-04 17:21:37 +00:00
Fahad
3824d13161 feat: OpenAI/compatible models (such as Azure OpenAI) can declare if they use the response API instead via use_openai_responses_api 2025-10-04 21:20:47 +04:00
Fahad
ff9a07a37a feat!: breaking change - OpenRouter models are now read from conf/openrouter_models.json while Custom / Self-hosted models are read from conf/custom_models.json 
feat: Azure OpenAI / Azure AI Foundry support. Models should be defined in conf/azure_models.json (or a custom path). See .env.example for environment variables or see readme. https://github.com/BeehiveInnovations/zen-mcp-server/issues/265

feat: OpenRouter / Custom Models / Azure can separately also use custom config paths now (see .env.example )

refactor: Model registry class made abstract, OpenRouter / Custom Provider / Azure OpenAI now subclass these

refactor: breaking change: `is_custom` property has been removed from model_capabilities.py (and thus custom_models.json) given each models are now read from separate configuration files
 2025-10-04 21:10:56 +04:00
Fahad
e91ed2a924 docs: updated 2025-10-04 17:33:49 +04:00
github-actions[bot]
ae8749ab37 chore: sync version to config.py [skip ci] 2025-10-04 10:33:34 +00:00
semantic-release
f5da38d1bb chore(release): 5.22.0 
Automatically generated by python-semantic-release
 2025-10-04 10:33:30 +00:00
Fahad
bc93b5343b fix: CI test 2025-10-04 14:32:47 +04:00
Fahad
2c534ac06e feat: centralized environment handling, ensures ZEN_MCP_FORCE_ENV_OVERRIDE is honored correctly 
fix: updated tests to override env variables they need instead of relying on the current values from .env
 2025-10-04 14:28:56 +04:00
Fahad
4015e917ed fix: listmodels to always honor restricted models 
fix: restrictions should resolve canonical names for openrouter
fix: tools now correctly return restricted list by presenting model names in schema
fix: tests updated to ensure these manage their expected env vars properly
perf: cache model alias resolution to avoid repeated checks
 2025-10-04 13:46:22 +04:00
github-actions[bot]
054e34e31c chore: sync version to config.py [skip ci] 2025-10-04 06:36:15 +00:00
Fahad
06d7701cc3 refactor: removed subclass override when the base class should be resolving the model name 
refactor: always disable "stream"
 2025-10-04 10:35:32 +04:00
Fahad
d184024820 refactor: don't retry on 429 2025-10-03 23:52:03 +04:00
Fahad
f955100f3a refactor: improved retry logic and moved core logic to base class 2025-10-03 23:48:55 +04:00
Fahad
828c4eed5b Merge remote-tracking branch 'origin/main' 2025-10-03 23:27:23 +04:00
Fahad
4968e1f7bc refactor: cleanup, remove unused method 2025-10-03 23:26:22 +04:00
github-actions[bot]
c0334d7792 chore: sync version to config.py [skip ci] 2025-10-03 19:10:04 +00:00
semantic-release
a190023c09 chore(release): 5.21.0 
Automatically generated by python-semantic-release
 2025-10-03 19:09:58 +00:00
Fahad
5b0601bea8 Merge remote-tracking branch 'origin/main' 2025-10-03 23:09:19 +04:00
Fahad
a8fbafd5a7 feat: minor tweaks to chat system prompt to help with alignment 2025-10-03 23:09:12 +04:00
github-actions[bot]
ddb20a6cdb chore: sync version to config.py [skip ci] 2025-10-03 18:42:29 +00:00
semantic-release
9ad59c7ec0 chore(release): 5.20.1 
Automatically generated by python-semantic-release
 2025-10-03 18:42:24 +00:00
Fahad
3a8a9eb21b Merge remote-tracking branch 'origin/main' 2025-10-03 22:41:34 +04:00
Fahad
8759edc817 fix: consensus now advertises a short list of models to avoid the CLI getting the names wrong 2025-10-03 22:41:28 +04:00
github-actions[bot]
03addcfa2d chore: sync version to config.py [skip ci] 2025-10-03 17:21:35 +00:00
semantic-release
26462abebf chore(release): 5.20.0 
Automatically generated by python-semantic-release
 2025-10-03 17:21:30 +00:00
Fahad
9780c8ef02 Merge remote-tracking branch 'origin/main' 2025-10-03 21:20:47 +04:00
Fahad
3533568e79 feat: gpt5-codex support via native / OpenRouter config (via PRs) 2025-10-03 21:20:42 +04:00
github-actions[bot]
539bc72f1c chore: sync version to config.py [skip ci] 2025-10-03 17:17:46 +00:00
semantic-release
e181da94df chore(release): 5.19.0 
Automatically generated by python-semantic-release
 2025-10-03 17:17:42 +00:00
Beehive Innovations
3d266fe5f5 Merge pull request #270 from zainab-gilani/main 
feat: Added support for gpt-5-codex from openrouter
 2025-10-03 21:16:40 +04:00
Beehive Innovations
775ac8ff58 Merge pull request #268 from Coquinate/feat/gpt5-codex-responses-api 
feat: add GPT-5-Codex support with Responses API integration
 2025-10-03 21:16:13 +04:00
Zainab
d8f5502b71 Added support for gpt-5-codex from openrouter 2025-10-03 19:32:49 +04:00
aberemia24
82b021d75a fix: add GPT-5-Codex to Responses API routing and simplify comments 
- Route GPT-5-Codex to /v1/responses endpoint (same as o3-pro)
- Simplify verbose comments per code review feedback

Addresses code review from @gemini-code-assist
 2025-10-03 13:59:55 +03:00
aberemia24
f2653427ca feat: add GPT-5-Codex support with Responses API integration 
Adds support for OpenAI's GPT-5-Codex model which uses the new Responses API
endpoint (/v1/responses) instead of the standard Chat Completions API.

Changes:
- Add GPT-5-Codex to MODEL_CAPABILITIES with 400K context, 128K output
- Prioritize GPT-5-Codex for EXTENDED_REASONING tasks
- Add aliases: codex, gpt5-codex, gpt-5-code
- Update tests to expect GPT-5-Codex for extended reasoning

Benefits:
- 40-80% cost savings through Responses API caching
- 3% better performance on coding tasks (SWE-bench)
- Leverages existing dual-API infrastructure
 2025-10-03 13:59:44 +03:00
Fahad
88493bd357 test: cross tool memory recall, testing continuation via cassette recording 2025-10-03 13:51:32 +04:00
Fahad
95d98a9bc0 docs: bumped defaults 2025-10-03 13:10:18 +04:00
Fahad
950b37a5d4 Merge remote-tracking branch 'origin/main' 2025-10-03 13:07:47 +04:00
Fahad
3c4b1368c6 test: http cassettes added for improved testing of consensus 2025-10-03 13:07:42 +04:00
github-actions[bot]
8e32ef33e3 chore: sync version to config.py [skip ci] 2025-10-03 07:29:52 +00:00
semantic-release
a22bc14fac chore(release): 5.18.3 
Automatically generated by python-semantic-release
 2025-10-03 07:29:48 +00:00
Fahad
d55130a430 fix: external model name now recorded properly in responses 
test: http cassettes added for improved integration tests
refactor: generic name for the CLI agent
 2025-10-03 11:29:06 +04:00
Fahad
e9b69476cd refactor: generic name for the CLI agent 2025-10-03 11:18:59 +04:00
Fahad
7a6fa0e77a refactor: generic name for the CLI agent 2025-10-03 10:55:10 +04:00