Nuoya Jiang 48c8e6aba3 feat(orchestrator): add consensus / adversarial verification primitive (#280) ...

`runConsensus()` runs a proposer→judge propose/refute/converge loop, and an opt-in per-task `verify` hook applies the same check to a task's own result. Judges run sequentially to a quorum (refute or lens mode); only an accepted revision supersedes the task output, and judge usage counts against the parent `maxTokenBudget`.

Closes #275

2026-06-07 18:50:03 +08:00

..

e2e

chore: migrate package to org scope

2026-05-09 15:40:10 +08:00

helpers

test: add LLM adapter contract tests, improve coverage from 71% to 88% (#56)

2026-04-05 14:14:43 +08:00

abort-signal-propagation.test.ts

fix: propagate AbortSignal through tool execution, Gemini adapter, and abort queue path (#99, #100, #101)

2026-04-12 23:20:30 +08:00

abort-signal.test.ts

fix: correct Team constructor usage in abort-signal tests

2026-04-06 12:54:24 +08:00

advanced-sampling.test.ts

feat: expose parallelToolCalls option for OpenAI adapter (#173)

2026-04-25 16:16:21 +08:00

agent-hooks.test.ts

feat: implement token budget management in agent and orchestrator (#71)

2026-04-06 23:14:08 +08:00

agent-pool.test.ts

feat: agent delegation mechanism (#123)

2026-04-19 10:50:44 +08:00

ai-sdk-adapter.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

anthropic-adapter.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

approval.test.ts

feat(orchestrator): add onApproval callback for human-in-the-loop (#32)

2026-04-05 02:46:20 +08:00

azure-openai-adapter.test.ts

feat(llm): add ReasoningBlock.provenance + LLMAdapter.capabilities scaffolding (#223) (#243)

2026-05-21 11:58:40 +08:00

bedrock-adapter.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

built-in-tools.test.ts

feat(sandbox): narrow default root to .agent-workspace subdir

2026-05-28 19:34:18 +08:00

cli.test.ts

feat: add MiMo provider adapter (#265)

2026-05-28 15:47:53 +08:00

consensus.test.ts

feat(orchestrator): add consensus / adversarial verification primitive (#280)

2026-06-07 18:50:03 +08:00

context-strategy.test.ts

fix(runner): strip image blocks before summarize compression call (#196)

2026-05-01 13:33:23 +08:00

coordinator-dependency-contract.test.ts

[Bug] Fix Truncation and Tighten Coordinator's Dependency Guidance (#215)

2026-05-08 12:09:46 +08:00

copilot-adapter.test.ts

feat(llm): add ReasoningBlock.provenance + LLMAdapter.capabilities scaffolding (#223) (#243)

2026-05-21 11:58:40 +08:00

dashboard-layout-tasks.test.ts

feat(cli): runTeam DAG dashboard (--dashboard)

2026-04-21 02:22:03 +08:00

dashboard-render.test.ts

fix: redact secrets in traces, bash env, and dashboard payloads (#263)

2026-05-28 00:53:34 +08:00

deepseek-adapter.test.ts

test(deepseek): verify tool-calling via chat() and stream() (#252)

2026-05-27 19:08:51 +08:00

delegation-budget.test.ts

fix(runner): defer maxTokenBudget break until after tool_result is appended (#221)

2026-05-12 03:02:34 +08:00

delegation-concurrency.test.ts

feat: agent delegation mechanism (#123)

2026-04-19 10:50:44 +08:00

doubao-adapter.test.ts

feat: add Doubao (Volcengine) provider shortcut (#261)

2026-05-27 20:33:58 +08:00

errors.test.ts

test: add errors.ts unit tests (#290)

2026-06-06 01:02:14 +08:00

fs-walk.test.ts

feat(tools): per-agent filesystem sandbox (#264)

2026-05-28 17:20:14 +08:00

gemini-adapter-contract.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

gemini-adapter.test.ts

chore: support Node >=18, add optional @google/genai peer dependency and API key fallback

2026-04-04 22:12:28 +03:00

grok-adapter.test.ts

feat(llm): add first-class Grok (xAI) support with dedicated GrokAdapter (#44)

2026-04-04 18:20:55 +08:00

hunyuan-adapter.test.ts

feat(llm): add Tencent Hunyuan provider adapter (#281)

2026-06-02 01:29:12 +08:00

keywords.test.ts

refactor(orchestrator): address PR #70 review feedback

2026-04-07 21:46:03 +09:00

llm-adapter-capabilities.test.ts

feat(llm): add Tencent Hunyuan provider adapter (#281)

2026-06-02 01:29:12 +08:00

llm-adapters.test.ts

fix(openai): emit tool messages before user message in mixed content (#178)

2026-04-26 12:40:54 +08:00

llm-message-validation.test.ts

fix(llm): validate message content at adapter entry (#288)

2026-06-04 14:34:13 +08:00

loop-detection.test.ts

fix(agent): replay history into loop detector and inject warnings for text-only loops (#254)

2026-05-27 18:08:45 +08:00

mcp-tools.test.ts

feat(tools): per-agent filesystem sandbox (#264)

2026-05-28 17:20:14 +08:00

mimo-adapter.test.ts

feat: add MiMo provider adapter (#265)

2026-05-28 15:47:53 +08:00

minimax-adapter.test.ts

Support MiniMax

2026-04-16 11:06:37 +10:00

multi-perspective-code-review.test.ts

Upgrade multi-perspective code review example with structured output and free-provider support (#150)

2026-04-23 17:35:21 +08:00

onAgentStream.test.ts

fix(agent): polish onAgentStream stream path (#184)

2026-04-27 02:24:40 +08:00

openai-adapter.test.ts

refactor(llm): extract shared repairToolArgs helper (#282)

2026-06-02 17:30:50 +08:00

openai-common.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

openai-fallback-repair.test.ts

feat(llm): add robust regex fallback for malformed single-string JSON tools (#269)

2026-06-02 16:45:47 +08:00

openai-fallback.test.ts

feat(llm): add fallback tool-call extraction for local models (#15)

2026-04-05 11:49:10 +08:00

orchestrator.test.ts

fix(orchestrator): preserve memoryScope and retry config on plan replay (#287)

2026-06-04 13:03:18 +08:00

personalized-interview-simulator.test.ts

Add example: personalized interview simulator (closes #166) (#189)

2026-04-28 15:28:39 +08:00

qiniu-adapter.test.ts

feat: add Qiniu provider support (#154)

2026-04-24 15:10:14 +08:00

reasoning-fallback.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

redaction.test.ts

fix: redact secrets in traces, bash env, and dashboard payloads (#263)

2026-05-28 00:53:34 +08:00

research-aggregation.test.ts

examples: research aggregation schema + provider env + test (#159)

2026-04-23 22:43:56 +08:00

runner-error-propagation.test.ts

fix: propagate error events in AgentRunner.run() (#98)

2026-04-12 22:16:33 +08:00

runner-reasoning-flags.test.ts

feat(llm): cross-provider reasoning text fallback with opt-in (#223 Phase 2) (#260)

2026-05-28 15:17:36 +08:00

sampling-wire-format.test.ts

feat: expose parallelToolCalls option for OpenAI adapter (#173)

2026-04-25 16:16:21 +08:00

scheduler.test.ts

test: improve coverage from 37% to 71% (#41) (#53)

2026-04-05 13:37:00 +08:00

semaphore.test.ts

feat: agent delegation mechanism (#123)

2026-04-19 10:50:44 +08:00

shared-memory.test.ts

fix: support structured shared memory handoff (#284)

2026-06-04 11:10:31 +08:00

short-circuit.test.ts

fix: eliminate duplicate progress events and double completedTaskCount in short-circuit path (#82)

2026-04-08 12:49:13 +08:00

structured-output.test.ts

feat(streaming): add reasoning events for OpenAI and Anthropic (#174)

2026-04-29 01:22:41 +08:00

task-queue.test.ts

feat: enforce dependency-scoped agent context (default-deny) (#87)

2026-04-10 03:09:58 +08:00

task-retry.test.ts

feat: task-level retry with exponential backoff (#37)

2026-04-03 14:08:36 +08:00

task-utils.test.ts

chore: add tests, CI, contributing guide, and PR template

2026-04-02 23:43:54 +08:00

team-messaging.test.ts

test: improve coverage from 37% to 71% (#41) (#53)

2026-04-05 13:37:00 +08:00

text-tool-extractor.test.ts

fix(text-tool-extractor): keep depth non-negative on stray closing brace (#217)

2026-05-09 10:39:28 +08:00

token-budget.test.ts

refactor(orchestrator): address PR #70 review feedback

2026-04-07 21:46:03 +09:00

tokens.test.ts

feat(streaming): add reasoning events for OpenAI and Anthropic (#174)

2026-04-29 01:22:41 +08:00

tool-executor.test.ts

feat: enforce optional outputSchema validation and wire defineTool passthrough (#149)

2026-04-24 17:57:27 +08:00

tool-filtering.test.ts

fix: redact secrets in traces, bash env, and dashboard payloads (#263)

2026-05-28 00:53:34 +08:00

tool-result-compression.test.ts

feat: agent delegation mechanism (#123)

2026-04-19 10:50:44 +08:00

trace.test.ts

fix: redact secrets in traces, bash env, and dashboard payloads (#263)

2026-05-28 00:53:34 +08:00