prr-kit 1.3.0 → 2.0.0

package/README.md

@@ -16,6 +16,10 @@ Module system, agent YAML, step-file workflows, CLI installer with full IDE inte
 
 **[🌐 Website](https://prrkit.sitenow.cloud)** **[📖 Full Documentation](https://prrkit.sitenow.cloud/docs)**
 
+<a href="https://unikorn.vn/p/prr-kit?ref=embed" target="_blank"><img src="https://unikorn.vn/api/widgets/badge/prr-kit?theme=light" alt="PR Review Kit trên Unikorn.vn" style="width: 256px; height: 64px;" width="256" height="64" /></a>
+<a href="https://unikorn.vn/p/prr-kit?ref=embed" target="_blank"><img src="https://unikorn.vn/api/widgets/badge/prr-kit/rank?theme=light&type=daily" alt="PR Review Kit - Hàng ngày" style="width: 250px; height: 64px;" width="250" height="64" /></a>
+
+
 ## Quick Start
 
 ```bash
@@ -38,9 +42,137 @@ Then open your IDE in the installed project and use one of these commands to sta
 
 ## How It Works
 
-<p align="center">
-  <img src="docs/assets/how-it-works.svg" alt="How It Works" width="100%"/>
-</p>
+```
+┌─────────────────────────────────────────────────────────┐
+│                    /prr-quick                           │
+│              Load config.yaml                           │
+└───────────────────────┬─────────────────────────────────┘
+                        │
+        ╔═══════════════▼════════════════╗
+        ║       PHASE 1 — SELECT PR      ║
+        ╚═══════════════╤════════════════╝
+                        │
+             ┌──────────▼──────────┐
+             │ 1a. git fetch origin │
+             └──────────┬──────────┘
+                        │
+             ┌──────────▼───────────────┐
+             │ 1b. List open PRs/MRs    │
+             │     + recent branches    │
+             └──────────┬───────────────┘
+                        │
+             ┌──────────▼───────────────┐
+             │ 1c. ⌨️  Select PR/branch  │  ← USER INPUT
+             │     Enter PR# or name    │
+             └──────────┬───────────────┘
+                        │
+             ┌──────────▼──────────┐
+             │ 1d. Load diff        │
+             │     count files/lines│
+             └──────────┬──────────┘
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ 1e. Create session folder            │
+             │     {output}/{date}-{slug}/          │
+             └──────────┬──────────────────────────┘
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ 1f. Generate diffs/ folder           │
+             │     one .md per changed file         │
+             └──────────┬──────────────────────────┘
+                        │
+        ╔═══════════════▼════════════════╗
+        ║      PHASE 2 — DESCRIBE PR     ║
+        ╚═══════════════╤════════════════╝
+                        │
+             ┌──────────▼──────────────┐
+             │ 2a. Classify PR type     │
+             │     bugfix/feature/...   │
+             └──────────┬──────────────┘
+                        │
+             ┌──────────▼──────────────┐
+             │ 2b. File-by-file         │
+             │     walkthrough          │
+             └──────────┬──────────────┘
+                        │
+             ┌──────────▼──────────────┐
+             │ 2c. Print PR description │
+             └──────────┬──────────────┘
+                        │
+        ╔═══════════════▼═══════════════════════╗
+        ║   PHASE 2.5 — COLLECT PR CONTEXT      ║
+        ╚═══════════════╤═══════════════════════╝
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ Step 1. Analyze changed files        │
+             │  detect stacks, domains, file types  │
+             └──────────┬──────────────────────────┘
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ Step 2. Collect context from:        │
+             │  CLAUDE.md · CONTRIBUTING.md         │
+             │  .eslintrc · tsconfig · pyproject    │
+             │  ARCHITECTURE.md · docs/**           │
+             │  @context/@security annotations      │
+             │  stack rules (vue3/react/django/...)  │
+             │  MCP tools · RAG · URL sources       │
+             └──────────┬──────────────────────────┘
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ Step 3. ⌨️  User instructions        │  ← USER INPUT
+             │  scope / focus / requirements /      │
+             │  context — or Enter for full review  │
+             └──────────┬──────────────────────────┘
+                        │
+               ┌────────┴────────┐
+               ▼                 ▼
+          [provided]         [empty]
+        parse scope &      scope = "all"
+        focus/req/ctx      full standard
+               │                 │
+               └────────┬────────┘
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ Step 4. Build pr-context.yaml        │
+             │  all collected context + user_instr  │
+             │  → {session_output}/pr-context.yaml  │
+             └──────────┬──────────────────────────┘
+                        │
+        ╔═══════════════▼════════════════╗
+        ║       PHASE 3 — REVIEW         ║
+        ╚═══════════════╤════════════════╝
+                        │
+             ┌──────────▼──────────────────────────┐
+             │ Scope gate                           │
+             │ read user_instructions.review_scope  │
+             └──────┬───────────────────────────────┘
+                    │
+         ┌──────────┴──────────┐
+    [in scope]           [not in scope]
+         │                     │
+         ▼                     ▼
+  ┌─────────────┐        ⏭️ skipped
+  │  GR · SR    │        (no output file)
+  │  PR · AR    │
+  │     BR      │
+  └──────┬──────┘
+         │
+        ╔▼════════════════════════╗
+        ║  PHASE 4 — REPORT       ║
+        ╚╤════════════════════════╝
+         │
+         │  Compile findings → sort by severity
+         │  🔴 Blockers → 🟡 Warnings
+         │  🟢 Suggestions → ❓ Questions
+         │  Write → final-review.md
+         │
+        ╔▼════════════════════════╗
+        ║  PHASE 5 — DONE         ║
+        ╚╤════════════════════════╝
+         │
+         ├── auto_post_comment: true  → post inline comments automatically
+         └── auto_post_comment: false → ⌨️  type PC to post, Enter to finish
+```
 
 The framework installs into your project as a `_prr/` folder. Agents and workflows are Markdown/YAML files that your AI IDE reads and executes — no server, no background process, no API keys required beyond your IDE's AI.
 
@@ -71,9 +203,6 @@ auto_post_comment: false               # true → auto-post findings after every
 # ─── Context Collection ────────────────────────────────────────────────────
 context_collection:
   enabled: true                        # false → disable context collection entirely
-  skip_manual_input_context: false     # true → skip the manual context input prompt
-                                       # false (default) → agent asks user for additional context
-                                       # before building the knowledge base; input is marked ⚠️ IMPORTANT
   mode: pr-specific                    # only value: pr-specific (always fresh, never cached)
 
   # Sources below are auto-detected — override only if needed:
@@ -139,28 +268,30 @@ external_sources:
 ### Quick mode — one command, full pipeline
 
 ```
-/prr-quick    or    /prr-master → QR
+/prr-quick
 ```
 
-Runs automatically: **select PR → describe → collect context → 5 reviews → generate report**
-Only pauses once to ask which PR/branch to review.
+Runs automatically: **select PR → describe → collect context → review → report**
+Pauses **twice** for user input: once to select the PR/branch, once for review instructions (scope, focus, requirements — or Enter for a full standard review).
 
 ### Manual mode — step by step
 
 | Code | Command | Description |
 |------|---------|-------------|
-| `SP` | Select PR | Fetch latest → list open PRs (via `gh`) or branches → select head + base → load diff |
+| `SP` | Select PR | Fetch latest → list open PRs or branches → select head + base → load diff |
 | `DP` | Describe PR | Classify PR type, generate summary, file-by-file walkthrough |
+| `CC` | Collect Context | Build PR-specific knowledge base from project docs, config files, standards, and external tools — run after DP, before any review |
 | `GR` | General Review | Logic, naming, readability, DRY, best practices, etc. — adapted to your stack |
 | `SR` | Security Review | OWASP Top 10, secrets, auth, rate limits, injection, etc. — adapted to your project |
 | `PR` | Performance Review | N+1 queries, memory leaks, async patterns, caching, etc. — adapted to your stack |
 | `AR` | Architecture Review | SOLID, layers, coupling, consistency with codebase, etc. — adapted to your architecture |
 | `BR` | Business Review | User impact, business risk, feature completeness, data safety, observability — adapted to your project |
+| `PM` | Party Mode 🎉 | All reviewers discuss the PR together in one collaborative session |
 | `IC` | Improve Code | Concrete BEFORE/AFTER code suggestions |
 | `AK` | Ask Code | Q&A about specific changes in this PR |
 | `RR` | Generate Report | Compile all findings → Markdown report in `_prr-output/reviews/` |
-| `PC` | Post Comments | Post inline code comments to GitHub PR via `gh` Reviews API |
-| `PM` | Party Mode 🎉 | All reviewers in one collaborative session |
+| `PC` | Post Comments | Post inline review comments to GitHub, GitLab, Azure DevOps, or Bitbucket PR |
+| `SS` | Select Session | List past review sessions and resume one |
 | `CL` | Clear | Remove context files and/or review reports from output folder |
 | `HH` | Help | Show this guide |
 
@@ -191,7 +322,7 @@ Enter PR number → base and head resolved automatically.
 | PRR Master | `/prr-master` | Orchestrator — routes all workflows, full menu |
 | PRR Quick | `/prr-quick` | One-command full pipeline (select → review → report) |
 
-Specialist reviewer agents are orchestrated internally by the master agent and party-mode workflow. Use `[PM] Party Mode` from the master menu to run all reviewers in a collaborative session.
+Specialist reviewer agents are orchestrated internally by the master agent and party-mode workflow. Use **[PM] Party Mode** from the master menu (`/prr-master`) to run all reviewers together in one collaborative session.
 
 ## Reviewers at a Glance
 
@@ -218,13 +349,17 @@ All findings use a standard format:
 
 ## Context Collection
 
-After [DP] Describe PR, context is collected **automatically** — no manual step needed:
+**In [QR] Quick Review:** context is collected automatically as Phase 2.5 — no manual step needed.
+**In manual mode (SP → DP → reviews):** run **[CC] Collect Context** after [DP] and before starting any review.
+
+Either way, the agent pauses once for your instructions before building the knowledge base:
 
 1. Analyzes changed files to detect domains (`authentication`, `state-management`, etc.)
 2. Reads relevant config files (`.eslintrc`, `.prettierrc`, `tsconfig.json`) and standards docs (`CONTRIBUTING.md`, `ARCHITECTURE.md`)
 3. Extracts inline `@context:` / `@security:` / `@pattern:` annotations from the diff
 4. Optionally queries **MCP tools** (Confluence, Jira, Figma) and **RAG systems** if configured
-5. Writes `pr-{branch}-context.yaml` — loaded by all reviewers
+5. Asks for **review instructions** — scope (`only security`), focus, requirements, or context. Press Enter for a full standard review
+6. Writes `pr-context.yaml` inside the session folder — loaded by all reviewers
 
 > See [CONFIGURATION.md](CONFIGURATION.md) for MCP intents, RAG setup, and URL sources.
 
@@ -241,7 +376,7 @@ When `[PC] Post Comments` is run with `platform_repo` configured, it posts findi
 
 ## Supported IDEs
 
-Antigravity, Auggie, Claude Code, Cline, Codex, Crush, Cursor, Gemini CLI, GitHub Copilot, iFlow, Kilo, Kiro, OpenCode, QwenCoder, Roo Cline, Rovo Dev, Trae, Windsurf
+Antigravity, Augment Code, Claude Code, Cline, Codex, Crush, Cursor, Gemini CLI, GitHub Copilot, iFlow, Kilo, Kiro, OpenCode, QwenCoder, Roo Code, Rovo Dev, Trae, Windsurf
 
 ## Requirements
 
@@ -268,10 +403,12 @@ prr-kit/
 │   ├── core/
 │   │   ├── agents/
 │   │   │   └── prr-master.agent.yaml   # Master orchestrator + menu
-│   │   └── tasks/
-│   │       ├── help.md                 # [HH] Help
-│   │       ├── clear.md                # [CL] Clear output files
-│   │       └── workflow.xml            # Workflow engine rules
+│   │   ├── tasks/
+│   │   │   ├── help.md                 # [HH] Help
+│   │   │   ├── clear.md                # [CL] Clear output files
+│   │   │   └── workflow.xml            # Workflow engine rules
+│   │   └── workflows/
+│   │       └── party-mode/             # [PM] Party Mode — all reviewers together
 │   └── prr/
 │       ├── agents/                     # Specialist reviewer agents (GR SR PR AR)
 │       ├── config-template.yaml        # Full config template with all options

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prr-kit",
-  "version": "1.3.0",
+  "version": "2.0.0",
   "description": "AI-driven Pull Request Review Kit — structured agent workflows for thorough, consistent code review",
   "main": "tools/cli/prr-cli.js",
   "bin": {

package/src/core/agents/prr-master.agent.yaml

@@ -24,10 +24,11 @@ agent:
       - When a PM MCP is available, extract issue key from branch name and fetch acceptance criteria to use as review checklist
 
   critical_actions:
-    - "Context is collected AUTOMATICALLY after Describe PR — no manual context collection needed"
+    - "In [QR] Quick Review: context is collected AUTOMATICALLY as part of the pipeline — no manual step needed"
+    - "In standalone mode (SP → DP → reviews): context is NOT auto-collected. After running DP, remind the user to run [CC] Collect Context before starting any review workflow for best results"
     - "Run [SP] Select PR FIRST before any review — never review without knowing the exact branch/diff"
     - "After Select PR, suggest running [DP] Describe PR to understand scope before diving into review"
-    - "Context collection happens automatically after DP — it's always fresh and PR-specific"
+    - "Context is always fresh and PR-specific — never stale or cached"
     - "Track completed reviews and remind user of remaining uncompleted review types"
     - "For PRs touching auth, API keys, or user data: always suggest [SR] Security Review"
     - "For feature PRs and PRs with data migration: always run [BR] Business Review to assess user impact and deployment risk"
@@ -46,6 +47,10 @@ agent:
       exec: "{project-root}/_prr/prr/workflows/2-analyze/describe-pr/workflow.md"
       description: "[DP] Describe PR: Auto-generate PR type, summary, file-by-file walkthrough"
 
+    - trigger: "CC or fuzzy match on collect-context"
+      exec: "{project-root}/_prr/prr/workflows/2-analyze/collect-pr-context/workflow.md"
+      description: "[CC] Collect Context: Build PR-specific knowledge base (run after DP, before reviews)"
+
     - trigger: "GR or fuzzy match on general-review"
       workflow: "{project-root}/_prr/prr/workflows/3-review/general-review/workflow.yaml"
       description: "[GR] General Review: Code quality analysis — adapted to your stack"
@@ -70,6 +75,10 @@ agent:
       workflow: "{project-root}/_prr/prr/workflows/4-improve/improve-code/workflow.yaml"
       description: "[IC] Improve Code: Concrete inline code suggestions with before/after fixes"
 
+    - trigger: "PM or fuzzy match on party-mode"
+      exec: "{project-root}/_prr/core/workflows/party-mode/workflow.md"
+      description: "[PM] Party Mode: All reviewers discuss the PR together in one collaborative session"
+
     - trigger: "AK or fuzzy match on ask-code"
       exec: "{project-root}/_prr/prr/workflows/5-ask/ask-code/workflow.md"
       description: "[AK] Ask: Interactive Q&A about specific code changes in this PR"
@@ -82,10 +91,14 @@ agent:
       exec: "{project-root}/_prr/prr/workflows/6-report/post-comments/workflow.md"
       description: "[PC] Post Comments: Post inline review comments to GitHub/GitLab/Azure/Bitbucket PR"
 
+    - trigger: "SS or fuzzy match on select-session or resume-session"
+      exec: "{project-root}/_prr/core/tasks/select-session.md"
+      description: "[SS] Select Session: List past review sessions and resume one"
+
     - trigger: "HH or fuzzy match on help"
       exec: "{project-root}/_prr/core/tasks/help.md"
       description: "[HH] Help: Show review workflow guide and available commands"
 
     - trigger: "CL or fuzzy match on clear or clean or reset"
       exec: "{project-root}/_prr/core/tasks/clear.md"
-      description: "[CL] Clear: Remove context files and/or review reports from output folder"
+      description: "[CL] Clear: Delete one or more past review sessions"

package/src/core/tasks/clear.md

@@ -8,58 +8,41 @@
 
 Read `{project-root}/_prr/prr/config.yaml` to get `review_output` path.
 
-### 2. Scan Output Folder
+### 2. Scan Session Folders
 
-List all files currently in `{review_output}`:
+List all session folders in `{review_output}` (datetime-slug subdirectories):
 
 ```bash
-ls "{review_output}/"
+ls -d "{review_output}"/*/
 ```
 
-Group into three categories:
+Each session folder is named `{YYYY-MM-DD-HHmm}-{slug}` (e.g. `2026-03-02-1430-pr44-feature-auth`).
+Inside each folder are: `pr-context.yaml` (knowledge base) and review `.md` files.
 
-**Context files** (session state + knowledge bases):
-- `current-pr-context.yaml` — active session state (which PR is selected)
-- `pr-*-context.yaml` — per-PR knowledge bases built during context collection
-
-**Intermediate review files** (individual review output, used by [RR] and [PC]):
-- `general-review-*.md`
-- `security-review-*.md`
-- `performance-review-*.md`
-- `architecture-review-*.md`
-- `business-review-*.md`
-- `improve-code-*.md`
-- `pr-description-*.md`
-
-**Review reports** (final compiled reports):
-- `review-*.md` — final review reports generated by [RR]
+Also detect any legacy flat files still directly in `{review_output}/` (pre-session-folder format).
 
 ### 3. Display What Exists
 
-Show the user exactly what will be affected:
+Show the user a summary of each session:
 
 ```
 🗂️ PRR Output — {review_output}
 
-Context files ({n}):
-  • current-pr-context.yaml
-  • pr-feature-auth-...-context.yaml
-  • pr-feature-search-...-context.yaml
-  ... (list all pr-*.yaml)
-
-Intermediate review files ({k}):
-  • general-review-2026-02-21.md
-  • security-review-2026-02-21.md
-  • pr-description-2026-02-21.md
-  ... (list all intermediate review files)
-
-Review reports ({m}):
-  • review-feature-auth-indexeddb-migration-2026-02-21.md
-  • review-feature-add-search-functionality-2026-02-21.md
-  ... (list all review-*.md)
+Session folders ({n}):
+
+  📁 2026-03-02-1430-pr44-feature-auth/
+     Branch: feature/auth  |  PR #44  |  2026-03-02
+     Files: pr-context.yaml, pr-description.md,
+            general-review.md, security-review.md, final-review.md
+
+  📁 2026-03-01-0915-fix-null-pointer/
+     Branch: fix/null-pointer  |  no PR  |  2026-03-01
+     Files: general-review.md
+
+  ... (list all session folders)
 ```
 
-If output folder is already empty or doesn't exist:
+If no session folders exist:
 ```
 ✅ Nothing to clear — output folder is already empty.
 ```
@@ -72,49 +55,32 @@ Ask the user what to clear:
 ```
 What would you like to clear?
 
-  [1] All          — context files + intermediate review files + review reports
-  [2] Context only — clear session state and knowledge bases (keep reports)
-  [3] Reports only — clear intermediate review files + final review reports (keep context)
-  [4] Cancel       — do nothing
+  [1] All sessions      — delete all session folders
+  [2] Select sessions   — choose specific session(s) to delete
+  [3] Cancel            — do nothing
 ```
 
 Wait for user input.
 
-### 5. Execute Deletion
-
-**If [1] All:**
-```bash
-rm -f "{review_output}/current-pr-context.yaml"
-rm -f "{review_output}"/pr-*-context.yaml
-rm -f "{review_output}"/general-review-*.md
-rm -f "{review_output}"/security-review-*.md
-rm -f "{review_output}"/performance-review-*.md
-rm -f "{review_output}"/architecture-review-*.md
-rm -f "{review_output}"/business-review-*.md
-rm -f "{review_output}"/improve-code-*.md
-rm -f "{review_output}"/pr-description-*.md
-rm -f "{review_output}"/review-*.md
+**If [2] Select sessions:** List sessions numbered and ask:
+```
+Which session(s) to delete? (e.g. 1, 3 or 1-3)
 ```
+Wait for response.
+
+### 5. Execute Deletion
 
-**If [2] Context only:**
+**If [1] All sessions:**
 ```bash
-rm -f "{review_output}/current-pr-context.yaml"
-rm -f "{review_output}"/pr-*-context.yaml
+rm -rf "{review_output}"/*/
 ```
 
-**If [3] Reports only:**
+**If [2] Selected sessions:** For each chosen session folder:
 ```bash
-rm -f "{review_output}"/general-review-*.md
-rm -f "{review_output}"/security-review-*.md
-rm -f "{review_output}"/performance-review-*.md
-rm -f "{review_output}"/architecture-review-*.md
-rm -f "{review_output}"/business-review-*.md
-rm -f "{review_output}"/improve-code-*.md
-rm -f "{review_output}"/pr-description-*.md
-rm -f "{review_output}"/review-*.md
+rm -rf "{review_output}/{selected_session_folder}/"
 ```
 
-**If [4] Cancel:**
+**If [3] Cancel:**
 ```
 ❌ Cancelled — nothing was deleted.
 ```
@@ -122,15 +88,14 @@ Stop.
 
 ### 6. Confirm Deletion
 
-Verify files are gone and report:
+Verify folders are gone and report:
 
 ```
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ✅ Clear complete
 
 Deleted:
-  🗑️  Context files: {n_ctx} file(s) removed
-  🗑️  Review reports: {n_rpt} file(s) removed
+  🗑️  Sessions removed: {n} folder(s)
 
 Output folder: {review_output}
 Status: clean

package/src/core/tasks/help.md

@@ -12,12 +12,13 @@ Use `/prr-help` anytime for guidance on what to do.
 **Per PR — Manual mode (step by step):**
 1. **[SP] Select PR** — Fetch latest, list branches/PRs, choose what to review
 2. **[DP] Describe PR** — Auto-generate PR type, summary, file-by-file walkthrough
-   ↳ *Context collected automatically — fresh, PR-specific, no setup needed*
-3. **[GR/SR/PR/AR/BR] Review** — Run one or more specialized reviews
-4. **[IC] Improve Code** — Get concrete code suggestions with inline fixes
-5. **[AK] Ask** — Ask specific questions about the code changes
-6. **[RR] Generate Report** — Compile all findings into a Markdown report
-7. **[PC] Post Comments** — Post inline review comments to GitHub / GitLab / Azure DevOps / Bitbucket
+3. **[CC] Collect Context** — Build a PR-specific knowledge base from your project docs, configs, stack rules, and external tools (Jira, Confluence, Figma). Run this before any review for best results.
+4. **[GR/SR/PR/AR/BR] Review** — Run one or more specialized reviews
+5. **[PM] Party Mode** 🎉 — All reviewers discuss the PR together in one collaborative session
+6. **[IC] Improve Code** — Get concrete code suggestions with inline fixes
+7. **[AK] Ask** — Ask specific questions about the code changes
+8. **[RR] Generate Report** — Compile all findings into a Markdown report
+9. **[PC] Post Comments** — Post inline review comments to GitHub / GitLab / Azure DevOps / Bitbucket
 
 ### Available Reviews
 
@@ -36,4 +37,6 @@ Use `/prr-help` anytime for guidance on what to do.
 
 ### Utilities
 
-- **[CL] Clear** — Remove context files and/or review reports from output folder. Useful when starting fresh or cleaning up after a session. Choose: All / Context only / Reports only.
+- **[SS] Select Session** — List past review sessions and resume one. Use this at the start of a new conversation to pick up where you left off.
+- **[HH] Help** — Show this guide.
+- **[CL] Clear** — Delete one or more past review session folders. Choose specific sessions or clear all.

package/src/core/tasks/select-session.md

@@ -0,0 +1,94 @@
+# Select Session
+
+**Goal:** List all past PR review sessions and let the user resume one by restoring `session_output` into working context.
+
+## EXECUTION
+
+### 1. Load Config
+
+Read `{project-root}/_prr/prr/config.yaml` to get `review_output` path.
+
+### 2. Scan Session Folders
+
+List all session folders in `{review_output}`:
+
+```bash
+ls -d "{review_output}"/*/
+```
+
+For each session folder, read its contents to build a summary:
+
+```bash
+ls "{review_output}/{session_folder}/"
+```
+
+From the files present, determine:
+- **Branch / PR** — from folder name (e.g. `2026-03-02-1430-pr44-feature-auth` → PR #44, branch `feature/auth`)
+- **Date / Time** — from folder name prefix (`2026-03-02-1430`)
+- **Reviews done** — which `*-review.md` files exist
+- **Has final report** — `final-review.md` exists
+- **Has description** — `pr-description.md` exists
+
+### 3. Display Sessions
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📂 Review Sessions — {review_output}
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+  [1] 2026-03-02 14:30 — PR #44  feature/auth-login
+      Reviews: DP ✓  GR ✓  SR ✓  RR ✓
+      Report:  final-review.md ✓
+
+  [2] 2026-03-01 09:15 — fix/null-pointer-checkout
+      Reviews: DP ✓  GR ✓
+      Report:  —
+
+  [3] 2026-02-28 17:00 — PR #41  chore/upgrade-deps
+      Reviews: DP ✓  GR ✓  AR ✓  RR ✓
+      Report:  final-review.md ✓
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+If no sessions exist:
+```
+✅ No sessions found in {review_output}.
+   Run [SP] Select PR or [QR] Quick Review to start a new session.
+```
+Then stop.
+
+### 4. Ask User to Select
+
+```
+Select a session to resume (enter number):
+```
+
+**HALT — wait for user response.**
+
+### 5. Restore Session
+
+Set `session_output` = full path of the selected session folder.
+
+Load PR metadata from working context sources available in the session folder:
+- Parse `session_output` folder name to extract: `datetime_prefix`, `pr_number` (if `prN-` prefix), `branch_slug`
+- Read `pr-context.yaml` if it exists — extract `pr_metadata.pr_number`, `pr_metadata.branch`, `pr_metadata.base_branch`
+- Derive `target_branch` and `base_branch` from knowledge base or folder name
+
+**Store in working context:**
+- `session_output` = selected folder path
+- `target_branch`, `base_branch`, `pr_number` = from above
+
+Display:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+✅ Session restored
+
+📁 {session_output}
+   Branch: {target_branch} → {base_branch}
+   PR #:   {pr_number}  (if applicable)
+
+Reviews completed: {list or "none"}
+Ready to continue — run any command from the menu.
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```