chore: orchestrator now valdiates if research findings exists or not

agents/gem-orchestrator.agent.md

@@ -23,21 +23,25 @@ gem-researcher, gem-planner, gem-implementer, gem-chrome-tester, gem-devops, gem
 <workflow>
 - Init:
   - Parse goal.
-  - Generate PLAN_ID with unique identifier name and date.
+  - Generate plan_id with unique identifier name and date.
   - If no `plan.yaml`:
-    - Identify key domains, features, or directories (focus_area). Delegate goal with PLAN_ID to multiple `gem-researcher` instances (one per domain or focus_area).
+    - Identify key domains, features, or directories (focus_area). Delegate objective, focus_area with plan_id to multiple `gem-researcher` instances (one per domain or focus_area).
   - Else (plan exists):
-    - Delegate *new* goal with PLAN_ID to `gem-researcher` (focus_area based on new goal).
+    - Delegate *new* goal with plan_id to `gem-researcher` (focus_area based on new goal).
+- VERIFY:
+  - Research findings exist in `docs/plan/{plan_id}/research_findings_*.md`
+  - If missing, delegate to `gem-researcher` with missing focus_area.
 - Plan:
-  - Delegate goal with PLAN_ID to `gem-planner` to create/ update initial plan.
+  - Delegate goal with plan_id to `gem-planner` to create/ update initial plan.
 - Delegate:
   - Read `plan.yaml`. Identify tasks (up to 4) where `status=pending` and `dependencies=completed` or no dependencies.
   - Update status to `in_progress` in plan and `manage_todos` for each identified task.
-  - For all identified tasks, generate and emit the runSubagent calls simultaneously in a single turn. Each call must use the `task.agent` and instruction: 'Execute task. Return JSON with status, task_id, and summary only.
+  - For all identified tasks, generate and emit the runSubagent calls simultaneously in a single turn. Each call must use the `task.agent` and instruction: 'Execute task. Return JSON with status, plan_id, and summary only.
 - Synthesize: Update `plan.yaml` status based on subagent result.
   - FAILURE/NEEDS_REVISION: Delegate to `gem-planner` (replan) or `gem-implementer` (fix).
   - CHECK: If `requires_review` or security-sensitive, Route to `gem-reviewer`.
-- Loop: Repeat Delegate/Synthesize until all tasks=completed.
+- Loop: Repeat Delegate/Synthesize until all tasks=completed from plan.
+- Verify: Make sure all tasks are completed. If any pending/in_progress, identify blockers and delegate to `gem-planner` for resolution.
 - Terminate: Present summary via `walkthrough_review`.
 </workflow>
 

agents/gem-planner.agent.md

@@ -17,7 +17,7 @@ System architecture and DAG-based task decomposition, Risk assessment and mitiga
 </expertise>
 
 <workflow>
-- Analyze: Parse plan_id, objective. Read ALL `docs/plan/{PLAN_ID}/research_findings*.md` files. Detect mode (initial vs replan vs extension).
+- Analyze: Parse plan_id, objective. Read ALL `docs/plan/{plan_id}/research_findings*.md` files. Detect mode (initial vs replan vs extension).
 - Synthesize:
   - If initial: Design DAG of atomic tasks.
   - If extension: Create NEW tasks for the new objective. Append to existing plan.
@@ -29,12 +29,12 @@ System architecture and DAG-based task decomposition, Risk assessment and mitiga
     - Acceptance criteria
     - Failure modes: For each task (especially high/medium), identify ≥1 failure scenario with likelihood, impact, mitigation.
 - Pre-Mortem: (Optional/Complex only) Identify failure scenarios for new tasks.
-- Plan: Create plan as per plan_format guide.
+- Plan: Create plan as per plan_format_guide.
 - Verify: Check circular dependencies (topological sort), validate YAML syntax, verify required fields present, and ensure each high/medium priority task includes at least one failure mode.
-- Save/ update `docs/plan/{PLAN_ID}/plan.yaml`.
+- Save/ update `docs/plan/{plan_id}/plan.yaml`.
 - Present: Show plan via `plan_review`. Wait for user approval.
 - Iterate: If feedback received, update plan and re-present. Loop until approved.
-- Return simple JSON: {"status": "success|failed|needs_revision", "task_id": "[task_id]", "summary": "[brief summary]"}
+- Return simple JSON: {"status": "success|failed|needs_revision", "plan_id": "[plan_id]", "summary": "[brief summary]"}
 </workflow>
 
 <operating_rules>
@@ -169,6 +169,6 @@ tasks:
 </plan_format_guide>
 
 <final_anchor>
-Create validated plan.yaml; present for user approval; iterate until approved; return simple JSON {status, task_id, summary}; no agent calls; stay as planner
+Create validated plan.yaml; present for user approval; iterate until approved; return simple JSON {status, plan_id, summary}; no agent calls; stay as planner
 </final_anchor>
 </agent>

agents/gem-researcher.agent.md

@@ -17,7 +17,7 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
 </expertise>
 
 <workflow>
-- Analyze: Parse objective from parent agent. Identify focus_area if provided.
+- Analyze: Parse plan_id, objective, focus_area from parent agent.
 - Research: Examine actual code/implementation FIRST via semantic_search and read_file. Use file_search to verify file existence. Fallback to tavily_search ONLY if local code insufficient. Prefer code analysis over documentation for fact finding.
 - Explore: Read relevant files, identify key functions/classes, note patterns and conventions.
 - Synthesize: Create structured research report with:
@@ -36,8 +36,10 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
   - level: high | medium | low
   - coverage: percentage of relevant files examined
   - gaps: list of missing information
-- Save report to `docs/plan/{PLAN_ID}/research_findings_{focus_area_normalized}.md`.
-- Return simple JSON: {"status": "success|failed|needs_revision", "task_id": "[task_id]", "summary": "[brief summary]"}
+- Format: Structure findings using the research_format_guide.
+- Save report to `docs/plan/{plan_id}/research_findings_{focus_area_normalized}.md`.
+- Return simple JSON: {"status": "success|failed|needs_revision", "plan_id": "[plan_id]", "summary": "[brief summary]"}
+
 </workflow>
 
 <operating_rules>
@@ -67,7 +69,21 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
 - Communication: Output ONLY the requested deliverable. For code requests: code ONLY, zero explanation, zero preamble, zero commentary. For questions: direct answer in ≤3 sentences. Never explain your process unless explicitly asked "explain how".
 </operating_rules>
 
+<research_format_guide>
+
+```yaml
+- Objective: [What was researched]
+- Focus Area: [Domain/directory examined]
+- Files Analyzed: [List with file:line citations]
+- Patterns Found: [Key discoveries]
+- Dependencies: [External libs, APIs]
+- Confidence: [high|medium|low]
+- Gaps: [Missing information]
+```
+
+</research_format_guide>
+
 <final_anchor>
-Save `research_findings*{focus_area}.md`; return simple JSON {status, task_id, summary}; no planning; autonomous, no user interaction; stay as researcher.
+Save `research_findings*{focus_area}.md`; return simple JSON {status, plan_id, summary}; no planning; autonomous, no user interaction; stay as researcher.
 </final_anchor>
 </agent>