adam/orchestrator
Archived
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
This repository has been archived on 2026-08-04. You can view files and clone it, but cannot push or open issues or pull requests.
orchestrator/agent-team/tests
History
Adam Moussa e7ef4387e6 fix(pipeline): single-shot Claude calls + planner actually reads review findings 
Two root causes behind 'every task parks, and slowly':
1. SINGLE-SHOT INVOKER: subscription Claude calls ran as 40-turn, tool-enabled
   agentic sessions (--max-turns 40, $2 budget) for what are pure reasoning->JSON
   completions — minutes-long, and Claude wandered/returned unparseable output.
   _DEFAULT_MAX_TURNS 40->1 + allowed_tools=[] -> fast deterministic single turn.
2. PLANNER FEEDBACK KEY MISMATCH: the review stage writes verdict/findings, but
   _format_review_feedback read decision/notes/comment (never present) -> the
   planner re-planned with EMPTY feedback, re-introduced the rejected flaw
   ('assumptions persist'), hit the review cap, parked. Now reads verdict/findings
   (old keys kept as fallback) so GPT-4.1's objections reach the re-plan.
Plus: park notifications infer the phase the task was IN (review/plan/clarify)
instead of the terminal 'parked'.
Tests: planner real-verdict-keys regression + coordinator phase-inference. 1149 pass.
2026-06-23 15:49:40 -04:00
..
sim Prove P1 exit criteria against the real LangGraph graph; fix question_id stability 2026-06-17 15:16:12 -04:00
__init__.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
conftest.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
test_apply_verify_workflow_hardening.py fix(ws3): keep agent-apply environment gate; drop fail-open Slack step 2026-06-23 12:17:19 -04:00
test_billing.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
test_build_verify_subgraph.py feat(agent-team): P3-inert build/verify subgraph topology (opt-in, no live CI) 2026-06-18 13:23:03 -04:00
test_builders.py Resolve security-review BLOCK: CI-guard bypasses, denylist parity, force-resume 2026-06-17 15:16:12 -04:00
test_builders_llm.py fix(ws1): skip fastapi TestClient tests when fastapi absent + ruff format 2026-06-23 11:40:46 -04:00
test_checker_intake.py feat(agent-team): P5 cross-plane loop — checker finding -> pipeline task (opt-in) (#18) 2026-06-18 15:56:52 -04:00
test_ci_fetcher.py feat(agent-team): P3-live CI apply/verify hardening + ci_fetcher (gate-passed, provisioning-gated) (#17) 2026-06-18 15:53:26 -04:00
test_ci_gate.py feat(agent-team): P3-flip Phase 1 — CI trust-boundary hardening (WIP, gated) (#34) 2026-06-22 18:51:52 -04:00
test_ci_gate_workflow.py feat(agent-team): wire apply/verify into .github/workflows (make it a live GitHub Actions workflow) (#37) 2026-06-22 19:12:17 -04:00
test_clarifier.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_clarifier_llm.py feat(agent-team): bind P1 clarifier to real Claude via subscription-OAuth invoker 2026-06-18 12:56:42 -04:00
test_claude_code_adapter.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_claude_code_live.py feat(agent-team): P4 live github/claude_code transports + GitHub-issue intake 2026-06-18 13:23:02 -04:00
test_coordinator.py fix(pipeline): single-shot Claude calls + planner actually reads review findings 2026-06-23 15:49:40 -04:00
test_deadline_timer.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_dispatcher.py feat(agent-team): P3-flip Phase 1 — CI trust-boundary hardening (WIP, gated) (#34) 2026-06-22 18:51:52 -04:00
test_fixer.py feat(agent-team): Plane-1 fixer — finding→patch→CI draft-PR (dep-bumps, opt-in/inert) (#21) 2026-06-18 16:17:33 -04:00
test_github_adapter.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_github_intake.py feat(agent-team): durable GitHub-issue intake de-dup + intake hardening (#32) 2026-06-22 17:20:43 -04:00
test_github_live.py feat(agent-team): P4 live github/claude_code transports + GitHub-issue intake 2026-06-18 13:23:02 -04:00
test_graph.py fix(intake): seed the task description into graph state (was silently dropped) 2026-06-23 15:49:40 -04:00
test_invoker.py feat(agent-team): bind P1 clarifier to real Claude via subscription-OAuth invoker 2026-06-18 12:56:42 -04:00
test_ledger.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_operator_cli.py fix(agent-team): harden listener respawn/close, broaden handle_event guard, channel_ref partial-unique (#29) 2026-06-22 16:14:22 -04:00
test_planner.py fix(pipeline): single-shot Claude calls + planner actually reads review findings 2026-06-23 15:49:40 -04:00
test_recovery.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_responder.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_resume_worker.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_review_loop.py feat(agent-team): bind planner/review/builder/verifier nodes to their models 2026-06-18 12:56:42 -04:00
test_review_loop_llm.py feat(agent-team): bind planner/review/builder/verifier nodes to their models 2026-06-18 12:56:42 -04:00
test_run_team.py feat(notify): Slack lifecycle notifications + deliver multi-turn questions 2026-06-23 15:49:40 -04:00
test_schema.py feat(agent-team): durable GitHub-issue intake de-dup + intake hardening (#32) 2026-06-22 17:20:43 -04:00
test_slack_adapter.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_slack_listener.py fix(agent-team): harden listener respawn/close, broaden handle_event guard, channel_ref partial-unique (#29) 2026-06-22 16:14:22 -04:00
test_slack_live.py test(agent-team): make slack_live token test independent of slack_sdk presence 2026-06-18 13:00:34 -04:00
test_state_store.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
test_task_model.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
test_transport_base.py Plane 2 foundation: interfaces, SQLite schemas, state-store, billing seam 2026-06-17 15:16:12 -04:00
test_verifier.py Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI) 2026-06-17 15:16:12 -04:00
test_verifier_llm.py feat(agent-team): bind planner/review/builder/verifier nodes to their models 2026-06-18 12:56:42 -04:00
test_ws0_ws2_ws4_plugin_slack_hook.py style(ws0+ws2+ws4): ruff format slack_listener, hook, test (CI ruff format --check) 2026-06-23 11:38:58 -04:00
test_ws1_invoker_multi_api.py fix(ws1): harden HTTP API + declare fastapi/uvicorn deps 2026-06-23 12:27:23 -04:00
test_ws3_dispatch_invoker.py style(ws3): ruff format dispatch_invoker + test (CI ruff format --check) 2026-06-23 11:38:31 -04:00
test_ws5_memory_handbook.py fix(ws5): allowlist save_memory names + symlink-safe write 2026-06-23 12:29:25 -04:00
test_ws_activation_wiring.py fix(ws1/ws5): bootstrap orchestrator root in in-process invokers (G1); thread handbook into clarifier (G4) 2026-06-23 15:49:40 -04:00