The agent system prompts and task descriptions implied agents could
explicitly read/write shared memory keys, but the framework handles
this automatically. Simplified to match actual behavior.
- Use 'task_start'/'task_complete' (underscores) instead of colons
- Use event.task/event.agent instead of non-existent taskTitle/agentName
- Remove Task import; runTasks() accepts a lighter inline type
Adds an example showing a generator agent producing code, then
three reviewer agents (security, performance, style) analyzing it
in parallel, followed by a synthesizer merging all feedback into
a prioritized action item report.
Closes#75
Demonstrates parallel analyst execution with dependency-based
synthesis using runTasks(), sharedMemory, and dependsOn:
1. Three analyst agents research the same topic in parallel
(technical, market, community perspectives)
2. Synthesizer waits for all analysts via dependsOn, reads
shared memory, cross-references findings, and produces
a unified report
Fixes#76
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
Add lightweight onTrace callback to OrchestratorConfig that emits
structured span events (llm_call, tool_call, task, agent) with timing,
token usage, and runId correlation. Zero overhead when not subscribed.
Closes#18
- Merge examples 08 (runTasks) and 09 (runTeam) into a single Gemma 4 example
- Renumber: structured output → 09, task retry → 10
- Move Author and Contributors sections to bottom in both READMEs
- Add Author section to English README
Add examples/09-gemma4-auto-orchestration.ts demonstrating runTeam()
with Gemma 4 as the coordinator — the framework's key feature running
fully local. The coordinator successfully decomposes goals into JSON
task arrays, schedules dependencies, and synthesises results.
Verified on gemma4:e2b (5.1B params) with Ollama 0.20.0-rc1.
Add examples/08-gemma4-local.ts demonstrating a pure-local multi-agent
team using Gemma 4 via Ollama — zero API cost. Two agents (researcher +
summarizer) collaborate through a task pipeline with bash, file_write,
and file_read tools. Verified on gemma4:e2b with Ollama 0.20.0-rc1.
Update both READMEs: add example 08 to the examples table and note
Gemma 4 as a verified local model with tool-calling support.
- 06-local-model.ts: mix Ollama (local) + Claude (cloud) in a runTasks pipeline,
demonstrating baseURL and apiKey placeholder for OpenAI-compatible servers
- 07-fan-out-aggregate.ts: MapReduce pattern using AgentPool.runParallel() to
fan out analysis to 3 perspective agents, then aggregate via a synthesizer
- 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
hkalex
JackChen
Ibrahim Kazimov
MrAvalonApple
JackChen
Matt Van Horn
Marcelo Ceccon
Deathwing