Integrate E23-T3 pr-review command and doctor workflow

Integrate E23-T3 pr-review command and doctor workflow

Author: dmoliveira

CHANGELOG.md

@@ -75,6 +75,8 @@ All notable changes to this project are documented in this file.
 - Added `/autoflow`, `/autoflow-status`, `/autoflow-report`, `/autoflow-dry-run`, and `/autoflow-stop` aliases in `opencode.json`.
 - Added `instructions/pr_review_rubric.md` defining Epic 23 Task 23.1 deterministic risk categories, severity/confidence scoring, blocker evidence thresholds, and low-noise recommendation mapping for `/pr-review`.
 - Added `scripts/pr_review_analyzer.py` implementing Epic 23 Task 23.2 diff parsing, changed-area classification, missing evidence detection, and deterministic rubric-aligned findings/recommendation output for PR risk triage.
+- Added `scripts/pr_review_command.py` implementing Epic 23 Task 23.3 `/pr-review` command integration with concise/JSON review output, pre-merge checklist generation, and subsystem doctor diagnostics.
+- Added `/pr-review`, `/pr-review-json`, `/pr-review-checklist`, and `/pr-review-doctor` aliases in `opencode.json`.
 
 ### Changes
 - Documented extension evaluation outcomes and when each tool is the better fit.
@@ -148,6 +150,7 @@ All notable changes to this project are documented in this file.
 - Marked Epic 23 as in progress and completed Task 23.1 rubric-definition notes in the roadmap.
 - Moved `plan_execution` runtime persistence out of `opencode.json` into `~/.config/opencode/my_opencode/runtime/plan_execution.json` to prevent OpenCode startup failures caused by unrecognized top-level config keys.
 - Added selftest coverage for `/pr-review` analyzer missing-evidence and blocker-evidence decision paths, and marked Task 23.2 complete in the roadmap.
+- Integrated `pr-review` checks into unified `/doctor`, updated installer self-check/hints for PR review workflows, and marked Task 23.3 complete in the roadmap.
 
 ## v0.2.0 - 2026-02-12
 

IMPLEMENTATION_ROADMAP.md

@@ -59,7 +59,7 @@ Use this map to avoid overlapping implementations.
 | E20 | Execution Budget Guardrails | done | High | E2, E11 | bd-63f | Bound time/tool/token usage for autonomous runs |
 | E21 | Bounded Loop Mode Presets | merged | Medium | E22, E28 | TBD | Merged into E22/E28 loop controls |
 | E22 | Autoflow Unified Orchestration Command | done | High | E14, E15, E17, E19, E20 | TBD | One command for plan-run-resume-report lifecycle |
-| E23 | PR Review Copilot | in_progress | High | E3 | bd-2zt | Pre-PR quality, output, and risk review automation |
+| E23 | PR Review Copilot | in_progress | High | E3 | bd-1hc | Pre-PR quality, output, and risk review automation |
 | E24 | Release Train Assistant | planned | High | E14, E23 | TBD | Validate, draft, and gate releases reliably |
 | E25 | Incident Hotfix Mode | planned | Medium | E20, E22 | TBD | Constrained emergency workflow with strict safety |
 | E26 | Repo Health Score and Drift Monitor | planned | Medium | E9, E12, E20 | TBD | Operational visibility and continuous diagnostics |
@@ -824,10 +824,11 @@ Every command-oriented epic must ship all of the following:
   - [x] Subtask 23.2.2: Detect missing tests/docs/changelog implications
   - [x] Subtask 23.2.3: Produce actionable findings with file-level references
   - [x] Notes: Added `scripts/pr_review_analyzer.py` with deterministic unified-diff parsing, changed-area classification, rubric-aligned finding generation, missing evidence detection (`tests`, `README`, `CHANGELOG`), and recommendation mapping (`approve|needs_review|changes_requested|block`) with file-level references and blocker evidence gates.
-- [ ] Task 23.3: Command surface and workflow integration
-  - [ ] Subtask 23.3.1: Add `/pr-review` with concise and JSON modes
-  - [ ] Subtask 23.3.2: Integrate with pre-merge checklist and doctor output
-  - [ ] Subtask 23.3.3: Document triage flow for warnings vs blockers
+- [x] Task 23.3: Command surface and workflow integration
+  - [x] Subtask 23.3.1: Add `/pr-review` with concise and JSON modes
+  - [x] Subtask 23.3.2: Integrate with pre-merge checklist and doctor output
+  - [x] Subtask 23.3.3: Document triage flow for warnings vs blockers
+  - [x] Notes: Added `scripts/pr_review_command.py` command surface with concise/JSON output and `checklist`/`doctor` subcommands, wired aliases in `opencode.json`, integrated `pr-review` into unified doctor checks, and documented blocker-vs-warning triage guidance in README.
 - [ ] Task 23.4: Verification
   - [ ] Subtask 23.4.1: Add tests for risk detection and false positive control
   - [ ] Subtask 23.4.2: Add tests for missing-evidence behavior

README.md

@@ -234,6 +234,27 @@ python3 ~/.config/opencode/my_opencode/scripts/pr_review_analyzer.py analyze --b
 python3 ~/.config/opencode/my_opencode/scripts/pr_review_analyzer.py analyze --diff-file /tmp/pr.diff --json
 ```
 
+Task 23.3 command integration:
+
+- command module: `scripts/pr_review_command.py`
+- command surface: `/pr-review`, `/pr-review-json`, `/pr-review-checklist`, `/pr-review-doctor`
+- doctor integration: unified `/doctor run --json` includes `pr-review` subsystem readiness
+
+Warning vs blocker triage flow:
+
+- `block`: at least one `S3` finding with `C2+` confidence and hard evidence; do not merge until fixed.
+- `changes_requested`: repeated `S2` findings with concrete remediation and missing evidence.
+- `needs_review`: medium-risk findings or uncertain evidence requiring reviewer attention.
+- `approve`: no meaningful risk findings beyond informational noise.
+
+Examples:
+
+```text
+/pr-review --base main --head HEAD --json
+/pr-review checklist --base main --head HEAD --json
+/pr-review doctor --json
+```
+
 ## Installed plugin stack 🔌
 
 - `@mohak34/opencode-notifier@latest` - desktop and sound alerts for completion, errors, and permission prompts.

install.sh

@@ -90,6 +90,12 @@ fi
 if [ -f "$INSTALL_DIR/scripts/autoflow_command.py" ]; then
   chmod +x "$INSTALL_DIR/scripts/autoflow_command.py"
 fi
+if [ -f "$INSTALL_DIR/scripts/pr_review_analyzer.py" ]; then
+  chmod +x "$INSTALL_DIR/scripts/pr_review_analyzer.py"
+fi
+if [ -f "$INSTALL_DIR/scripts/pr_review_command.py" ]; then
+  chmod +x "$INSTALL_DIR/scripts/pr_review_command.py"
+fi
 ln -sfn "$INSTALL_DIR/opencode.json" "$CONFIG_PATH"
 
 if [ "$RUN_WIZARD" = true ]; then
@@ -141,12 +147,13 @@ if [ "$SKIP_SELF_CHECK" = false ]; then
   fi
   if [ -f "$INSTALL_DIR/scripts/resume_command.py" ]; then
     python3 "$INSTALL_DIR/scripts/resume_command.py" status --json || true
-    python3 -c "import json,pathlib; p=pathlib.Path('$CONFIG_PATH'); data=json.loads(p.read_text(encoding='utf-8')); pe=data.get('plan_execution', {}); steps=pe.get('steps', []); pe['status']='failed'; pe['resume']={'enabled': True, 'attempt_count': 0, 'max_attempts': 3, 'trail': []};
+    RUNTIME_PATH="$HOME/.config/opencode/my_opencode/runtime/plan_execution.json"
+    python3 -c "import json,pathlib; p=pathlib.Path('$RUNTIME_PATH'); data=json.loads(p.read_text(encoding='utf-8')) if p.exists() else {}; steps=data.get('steps', []); data['status']='failed'; data['resume']={'enabled': True, 'attempt_count': 0, 'max_attempts': 3, 'trail': []};
 if isinstance(steps, list) and len(steps) >= 2:
   steps[0]['state']='done';
   steps[1]['state']='pending';
   steps[1]['idempotent']=False;
-data['plan_execution']=pe; p.write_text(json.dumps(data, indent=2)+'\n', encoding='utf-8')"
+p.parent.mkdir(parents=True, exist_ok=True); p.write_text(json.dumps(data, indent=2)+'\n', encoding='utf-8')"
     python3 "$INSTALL_DIR/scripts/resume_command.py" now --interruption-class tool_failure --json || true
     python3 "$INSTALL_DIR/scripts/resume_command.py" now --interruption-class tool_failure --approve-step 2 --json
   fi
@@ -174,6 +181,13 @@ data['plan_execution']=pe; p.write_text(json.dumps(data, indent=2)+'\n', encodin
     python3 "$INSTALL_DIR/scripts/autoflow_command.py" stop --reason install-self-check --json
     python3 "$INSTALL_DIR/scripts/start_work_command.py" "$SELF_CHECK_PLAN" --deviation "install self-check" --json
   fi
+  if [ -f "$INSTALL_DIR/scripts/pr_review_command.py" ]; then
+    SELF_CHECK_DIFF="$HOME/.config/opencode/my_opencode/.install-selfcheck-pr.diff"
+    python3 -c "from pathlib import Path; Path('$SELF_CHECK_DIFF').write_text('diff --git a/scripts/install_selfcheck.py b/scripts/install_selfcheck.py\nindex 0000000..1111111 100644\n--- a/scripts/install_selfcheck.py\n+++ b/scripts/install_selfcheck.py\n@@ -0,0 +1,1 @@\n+print(\"install\")\n', encoding='utf-8')"
+    python3 "$INSTALL_DIR/scripts/pr_review_command.py" --diff-file "$SELF_CHECK_DIFF" --json
+    python3 "$INSTALL_DIR/scripts/pr_review_command.py" checklist --diff-file "$SELF_CHECK_DIFF" --json
+    python3 "$INSTALL_DIR/scripts/pr_review_command.py" doctor --json
+  fi
   python3 "$INSTALL_DIR/scripts/nvim_integration_command.py" status
   python3 "$INSTALL_DIR/scripts/devtools_command.py" status
   python3 "$INSTALL_DIR/scripts/doctor_command.py" run || true
@@ -245,6 +259,9 @@ printf "  /autoflow dry-run ~/.config/opencode/my_opencode/plan.md --json\n"
 printf "  /autoflow status --json\n"
 printf "  /autoflow report --json\n"
 printf "  /autoflow stop --reason manual --json\n"
+printf "  /pr-review --base main --head HEAD --json\n"
+printf "  /pr-review-checklist --base main --head HEAD\n"
+printf "  /pr-review-doctor\n"
 printf "  /todo status --json\n"
 printf "  /todo enforce --json\n"
 printf "  /resume status --json\n"

opencode.json

@@ -310,6 +310,22 @@
       "description": "Trigger /autoflow kill-switch stop in JSON",
       "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/autoflow_command.py\" stop $ARGUMENTS --json`\nShow only the command output."
     },
+    "pr-review": {
+      "description": "Run PR review copilot analysis with checklist output",
+      "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/pr_review_command.py\" $ARGUMENTS`\nShow only the command output."
+    },
+    "pr-review-json": {
+      "description": "Run PR review analysis in JSON mode",
+      "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/pr_review_command.py\" $ARGUMENTS --json`\nShow only the command output."
+    },
+    "pr-review-checklist": {
+      "description": "Show pre-merge checklist for current review range",
+      "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/pr_review_command.py\" checklist $ARGUMENTS --json`\nShow only the command output."
+    },
+    "pr-review-doctor": {
+      "description": "Run PR review subsystem diagnostics in JSON",
+      "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/pr_review_command.py\" doctor --json`\nShow only the command output."
+    },
     "budget": {
       "description": "Manage execution budget controls (status|profile|override|doctor)",
       "template": "!`python3 \"$HOME/.config/opencode/my_opencode/scripts/budget_command.py\" $ARGUMENTS`\nShow only the command output."

scripts/doctor_command.py

@@ -204,6 +204,18 @@ def script_path(name: str) -> Path:
             "--json",
         ],
     },
+    {
+        "name": "pr-review",
+        "kind": "doctor-json",
+        "optional": True,
+        "required_path": str(script_path("pr_review_command.py")),
+        "command": [
+            sys.executable,
+            str(script_path("pr_review_command.py")),
+            "doctor",
+            "--json",
+        ],
+    },
     {
         "name": "budget",
         "kind": "doctor-json",