Commit Graph

13 Commits

Author SHA1 Message Date
hkalex 0485bfb82f Change the default URL of deepseek. Change the example to use reasoner for architect. 2026-04-16 12:17:22 +10:00
hkalex fa4533e8d0 Support DeepSeek 2026-04-16 11:36:03 +10:00
hkalex 5305cb2321 Support MiniMax 2026-04-16 11:06:37 +10:00
JackChen 6ea66afab5 fix: propagate AbortSignal through tool execution, Gemini adapter, and abort queue path (#99, #100, #101)
- #99: pass per-call effectiveAbortSignal to buildToolContext() so tools
  receive the correct signal instead of the static runner-level one
- #100: replace manual pending-task loop with queue.skipRemaining() on
  abort, fixing blocked tasks left non-terminal and missing events
- #101: forward abortSignal in Gemini adapter's buildConfig() so the
  SDK can cancel in-flight API calls
- Add 8 targeted tests for all three fixes
2026-04-12 23:20:30 +08:00
JackChen bc31008f4e feat(llm): add fallback tool-call extraction for local models (#15)
Local models (Ollama, vLLM) sometimes return tool calls as text instead
of using the native tool_calls wire format. This adds a safety-net
extractor that parses tool calls from model text output when native
tool_calls is empty.

- Add text-tool-extractor with support for bare JSON, code fences,
  and Hermes <tool_call> tags
- Wire fallback into OpenAI adapter chat() and stream() paths
- Add onWarning callback when model ignores configured tools
- Add timeoutMs on AgentConfig for per-run abort (local models can
  be slow)
- Add 26 tests for extractor and fallback behavior
- Document local model compatibility in README
2026-04-05 11:49:10 +08:00
MrAvalonApple 553bf24e61 chore: support Node >=18, add optional @google/genai peer dependency and API key fallback 2026-04-04 22:12:28 +03:00
Ibrahim Kazimov 944918d5ae
Merge branch 'main' into main 2026-04-04 13:43:40 +03:00
Marcelo Ceccon 10074c9b7d
feat(llm): add first-class Grok (xAI) support with dedicated GrokAdapter (#44)
feat(llm): add first-class Grok (xAI) support with dedicated GrokAdapter
2026-04-04 18:20:55 +08:00
MrAvalonApple 2bb220fc63 feat: add support for Gemini model 2026-04-02 21:41:56 +03:00
JackChen 62d6fa9e26 feat: add baseURL and apiKey support for OpenAI-compatible APIs
Enable connecting to any OpenAI-compatible API (Ollama, vLLM, LM Studio,
etc.) by adding baseURL and apiKey fields to AgentConfig and
OrchestratorConfig, threaded through to adapter constructors.

- OpenAIAdapter and AnthropicAdapter accept optional baseURL
- createAdapter() forwards baseURL to both adapters, warns if used with copilot
- All execution paths (runAgent, runTeam coordinator, buildPool) merge defaults
- Fully backward compatible — omitting new fields preserves existing behavior
2026-04-02 19:33:10 +08:00
Deathwing 8371cdb7c0 refactor: address all 7 PR review comments
1. Fix header comment — document correct env var precedence
   (apiKey → GITHUB_COPILOT_TOKEN → GITHUB_TOKEN → device flow)
2. Use application/x-www-form-urlencoded for device code endpoint
3. Use application/x-www-form-urlencoded for poll endpoint
4. Add mutex (promise-based) on #getSessionToken to prevent
   concurrent token refreshes and duplicate device flow prompts
5. Add DeviceCodeCallback + CopilotAdapterOptions so callers can
   control device flow output instead of hardcoded console.log
6. Extract shared OpenAI wire-format helpers into openai-common.ts,
   imported by both openai.ts and copilot.ts (-142 lines net)
7. Update createAdapter JSDoc to mention copilot env vars
2026-04-02 02:19:06 +02:00
Deathwing eedfeb17a2 feat: add GitHub Copilot as LLM provider
- Add CopilotAdapter with OAuth2 device flow authentication
- Token exchange via /copilot_internal/v2/token with caching
- Premium request multiplier system (getCopilotMultiplier)
- Full model metadata catalog (COPILOT_MODELS)
- Add 'copilot' to SupportedProvider and provider union types
- Add example: examples/05-copilot-test.ts
2026-04-02 01:45:43 +02:00
JackChen a6244cfe64 Initial release: open-multi-agent v0.1.0
Production-grade multi-agent orchestration framework.
Model-agnostic, supports team collaboration, task scheduling
with dependency resolution, and inter-agent communication.
2026-04-01 04:33:15 +08:00