Examples grew to 19 flat files mixing basics, provider demos, orchestration
patterns, and integrations, with two files colliding on the number 16.
Reorganized into category folders so the structure scales as new providers
and patterns get added.
Layout:
examples/basics/ core execution modes (4 files)
examples/providers/ one example per supported model provider (8 files)
examples/patterns/ reusable orchestration patterns (6 files)
examples/integrations/ MCP, observability, AI SDK (3 entries)
examples/production/ placeholder for end-to-end use cases
Notable changes:
- Dropped numeric prefixes; folder + filename now signal category and intent.
- Rewrote former smoke-test scripts (copilot, gemini) into proper three-agent
team examples matching the deepseek/grok/minimax/groq template. Adapter
unit tests in tests/ already cover correctness, so this only improves
documentation quality.
- Added examples/README.md as the categorized index plus maintenance rules
for new submissions.
- Added examples/production/README.md with acceptance criteria for the new
production category.
- Updated all internal npx tsx paths and import paths (../src/ to ../../src/).
- Updated README.md and README_zh.md links.
- Fixed stale cd paths inside examples/integrations/with-vercel-ai-sdk/README.md.
Implements `delegate_to_agent` built-in tool (closes#63). Opt-in registration via `includeDelegateTool`; only wired up by `runTeam` / `runTasks` for pool workers. Guards: self-delegation, unknown target, cycle detection via `delegationChain`, depth cap (`maxDelegationDepth`, default 3), pool deadlock.
Delegation runs on ephemeral Agent instances via `AgentPool.runEphemeral` (pool semaphore only, no per-agent lock) so mutual delegation (A→B while B→A) can't deadlock. Delegated run `tokenUsage` surfaces via `ToolResult.metadata` and rolls into the parent runner's total before the next budget check; delegation tool_result blocks are exempt from `compressToolResults` and the `compact` strategy. Best-effort SharedMemory audit writes at `{caller}/delegation:{target}:{ts}-{rand}`.
Picks up @NamelessNATM's work from #84 and adds cycle detection, token aggregation, compression exemption, mutual-delegation deadlock fix (Codex P1), and tool_result-preservation on budget-exceeded (Codex P2).
Co-authored-by: NamelessNATM <hamzarstar@gmail.com>
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
JackChen
Matt Van Horn
hkalex
Ibrahim Kazimov
MrAvalonApple
JackChen
Matt Van Horn
Marcelo Ceccon
Deathwing