prr-kit 1.2.3 → 1.4.0

package/src/prr/workflows/2-analyze/collect-pr-context/steps/step-03-manual-context-input.md

@@ -0,0 +1,102 @@
+---
+name: "step-03-manual-context-input"
+description: "Collect user instructions, requirements, and context for this review session"
+nextStepFile: "./step-04-build-knowledge-base.md"
+---
+
+# Step 3: User Instructions & Context
+
+## Goal
+Let the user guide the review — they can restrict scope, set focus areas, add mandatory requirements, or provide background context. Their input directly controls which reviews run and what each reviewer prioritizes.
+
+## Sequence of Instructions
+
+### 1. Show Collection Summary
+
+Print a brief summary of what was automatically collected so far:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+✅ Auto-collection complete.
+
+📊 Collected:
+   🗂️  Files changed:  {files_count}
+   🎯 Domains:         {domains_list}
+   🧩 Stacks:          {stacks_list or "none"}
+   📘 Primary docs:    {primary_docs_found}
+   ⚙️  Config files:   {config_files_found}
+   💬 Annotations:     {annotations_count}
+   🔌 External:        {mcp_and_rag_summary or "none"}
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+### 2. Prompt User
+
+Display EXACTLY:
+
+```
+💬 Any instructions for this review?
+   Press Enter to run a full standard review, or type your instructions below.
+
+   You can specify:
+     • Scope        "only security" / "security and architecture" / "skip performance"
+     • Focus        "focus on SQL injection and rate limiting"
+     • Requirements "all API endpoints must have auth middleware"
+     • Context      "hotfix — ignore refactoring suggestions"
+     • Mix freely   "security only, focus on JWT handling, context: auth rewrite in progress"
+```
+
+**HALT — wait for user response before continuing.**
+
+### 3. Parse Response
+
+**If user pressed Enter / left empty:**
+- Set `user_instructions.provided` = `false`
+- Set `user_instructions.review_scope` = `"all"`
+- Set all other fields to `null`
+
+**If user typed something**, parse the free-form text and extract:
+
+**`review_scope`** — which reviews to run:
+- Parse for scope signals: "only X", "just X", "X only", "skip X", "no X review", "X and Y"
+- Map to codes: `GR` (general), `SR` (security), `PR` (performance), `AR` (architecture), `BR` (business), `IC` (improve code)
+- Examples:
+  - "only security" → `[SR]`
+  - "security and architecture" → `[SR, AR]`
+  - "skip performance" → `[GR, SR, AR, BR]`
+  - "security, focus on JWT" → `[SR]` (scope signal found)
+  - "focus on SQL injection" (no scope signal) → `"all"` (focus only, all reviews still run)
+- If no scope restriction found → `"all"`
+
+**`focus_areas`** — specific things reviewers must prioritize (list of strings), or `null` if none mentioned.
+
+**`custom_requirements`** — mandatory checks user specified (list of strings), or `null`.
+
+**`context_notes`** — background info, trade-offs, constraints (list of strings), or `null`.
+
+**`raw`** — full original text from user.
+
+Set `user_instructions.provided` = `true`.
+
+### 4. Acknowledge
+
+**If user provided instructions**, print a confirmation of what was parsed:
+
+```
+✅ Instructions captured — driving all downstream review steps.
+
+   📋 Scope:         {scope_list joined with ", "  OR  "all reviews (standard)"}
+   🎯 Focus:         {focus_areas joined with ", "  OR  "standard coverage"}
+   ✅ Requirements:  {custom_requirements joined with ", "  OR  "none"}
+   📝 Context:       {context_notes joined with "; "  OR  "none"}
+```
+
+**If user left empty:**
+
+```
+▶️  Full standard review — all reviewers, standard focus.
+```
+
+### 5. Load Next Step
+
+Add `step-03-manual-context-input` to `stepsCompleted`. Load: `{nextStepFile}`

package/src/prr/workflows/2-analyze/collect-pr-context/steps/{step-03-build-knowledge-base.md → step-04-build-knowledge-base.md}

@@ -1,9 +1,9 @@
 ---
-name: "step-03-build-knowledge-base"
+name: "step-04-build-knowledge-base"
 description: "Build structured PR-specific knowledge base for reviewers"
 ---
 
-# Step 3: Build PR-Specific Knowledge Base
+# Step 4: Build PR-Specific Knowledge Base
 
 ## Goal
 Transform collected data into structured knowledge base optimized for reviewers.
@@ -32,6 +32,20 @@ pr_metadata:
   files_changed: {n}
   collected_at: {ISO timestamp}
 
+# ⚠️  IMPORTANT — Human-provided instructions from the user.
+# All reviewers MUST read this section before starting any review.
+# review_scope controls which reviews run. focus_areas, custom_requirements, and context_notes
+# are highest-priority guidance — align all findings against them.
+user_instructions:
+  # Populated only when the user provided input in step-03-manual-context-input.
+  # If provided: true — treat this content as the highest-priority context in this file.
+  provided: {true|false}
+  review_scope: {"all" | [SR] | [SR, AR] | ...}   # "all" = run all reviews; list = only those codes
+  focus_areas: {list of strings, or null}           # specific things every reviewer must prioritize
+  custom_requirements: {list of strings, or null}   # mandatory checks the user specified
+  context_notes: {list of strings, or null}         # background info, trade-offs, constraints
+  raw: {original text from user, or null}           # verbatim input
+
 files_analysis:
   changed_files:
     - path: src/stores/todoStore.js
@@ -235,6 +249,7 @@ external_context:
 
 review_priorities:
   # Guide reviewers on what to focus on
+  # ⚠️  If user_instructions.provided is true — reviewers MUST check findings against user_instructions first.
   critical:
     - "Verify no v-html with user input (security requirement)"
     - "Check ESLint error-level rules compliance"
@@ -250,6 +265,10 @@ review_priorities:
     - "Optional optimizations"
 
 reviewer_guidance:
+  # ⚠️  If user_instructions.provided is true:
+  #     PREPEND each reviewer's list with user_instructions.focus_areas (if any)
+  #     APPEND each reviewer's list with user_instructions.custom_requirements prefixed "MANDATORY: "
+  #     Example: if focus_areas = ["JWT handling"], add "FOCUS: JWT handling" as first item
   general_review:
     - "Check for ESLint rule violations (no-var, prefer-const)"
     - "Verify component naming follows standards"
@@ -275,28 +294,21 @@ context_sources:
   config_files: [.eslintrc.js, .prettierrc]
   standards_docs: [CONTRIBUTING.md, ARCHITECTURE.md]
   inline_annotations: yes
+  user_instructions: {true|false}  # true if user provided input in step-03
   mcp_tools: []                   # list of MCP tools actually used
   rag_systems: []                 # list of RAG systems queried
   url_sources: []                 # list of plain URLs fetched
 ```
 
-### 3. Determine Output Filename
+### 3. Output Filename
 
-```javascript
-if (pr_number_available) {
-  filename = `pr-${pr_number}-context.yaml`
-} else {
-  // Use sanitized branch name
-  const safeBranchName = branch_name.replace(/[^a-zA-Z0-9-]/g, '-')
-  filename = `pr-${safeBranchName}-context.yaml`
-}
-```
+Always: `pr-context.yaml` — the session folder already identifies the PR uniquely.
 
 ### 4. Write Knowledge Base to File
 
-Write to: `{review_output}/{filename}`
+Write to: `{session_output}/pr-context.yaml`
 
-Example: `_prr-output/pr-123-context.yaml`
+Example: `_prr-output/reviews/2026-03-02-1430-pr123-feature-auth/pr-context.yaml`
 
 ### 5. Report Completion
 
@@ -309,6 +321,9 @@ Example: `_prr-output/pr-123-context.yaml`
    • ESLint rules: {n}
    • Guidelines: {m}
    • Inline annotations: {k}
+   • User instructions: ⚠️ YES — scope: {scope}, focus: {focus_count} areas, requirements: {req_count}
+     OR
+   • User instructions: none — full standard review
    • MCP tools used: {mcp_list or "none"}
    • RAG patterns: {rag_count}
    • Issue context: {issue_key or "none"}
@@ -321,16 +336,11 @@ Example: `_prr-output/pr-123-context.yaml`
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
 
-### 6. Store Context Path
-
-Update PR context file to include knowledge base path:
+### 6. Store Knowledge Base Path in Working Context
 
-```yaml
-# {review_output}/current-pr-context.yaml
-pr_knowledge_base: "{review_output}/{filename}"
-```
+Store `pr_knowledge_base` = `{session_output}/pr-context.yaml` in working context.
 
-This allows review workflows to find the knowledge base.
+Review workflows (GR, SR, PR, AR, BR) find the knowledge base via working context or directly at `{session_output}/pr-context.yaml`.
 
 ### 7. Workflow Complete
 

package/src/prr/workflows/2-analyze/collect-pr-context/workflow.md

@@ -3,7 +3,7 @@ name: collect-pr-context
 description: "Collect fresh, PR-specific context from multiple sources after describing the PR"
 main_config: "{project-root}/_prr/prr/config.yaml"
 nextStep: "./steps/step-01-analyze-files.md"
-output_file: "{review_output}/pr-{pr_number}-context.yaml"
+output_file: "{session_output}/pr-context.yaml"
 ---
 
 # Collect PR-Specific Context Workflow
@@ -105,18 +105,17 @@ If a stack has no matching data file, skip it silently and proceed with general
 
 ## WORKFLOW ARCHITECTURE
 
-3-step process:
+4-step process:
 1. **Analyze files** changed in PR — extract metadata, domains, and **detect technology stacks**
 2. **Collect context** from all sources: primary docs, config files, standards docs, inline annotations, **stack-specific rules**, MCP tools, RAG systems
-3. **Build PR-specific knowledge base** — structured YAML with all context, stack rules, and reviewer guidance
+3. **Manual context input** — prompt the user for any additional context (business rationale, focus areas, known trade-offs). **Always runs — user must respond before continuing.** If the user provides input, it is marked **⚠️ IMPORTANT** and reviewers treat it as highest-priority context
+4. **Build PR-specific knowledge base** — structured YAML with all context, stack rules, manual context, and reviewer guidance
 
 ## INITIALIZATION
 
 Load config from `{main_config}`.
 
-Check if PR number is available:
-- If available: use `pr-{pr_number}-context.yaml`
-- If not: use `pr-{branch_name}-context.yaml`
+Output filename is always `pr-context.yaml` — the session folder already identifies the PR uniquely.
 
 ## EXECUTION
 

package/src/prr/workflows/2-analyze/describe-pr/steps/step-01-load-context.md

@@ -14,11 +14,11 @@ Load the PR context file and the actual code diff for analysis.
 
 ### 1. Load PR Context
 
-Read `{review_output}/current-pr-context.yaml`.
+Use `session_output`, `target_branch`, `base_branch`, `pr_number` from working context.
 
-If file not found:
+If not set:
 ```
-❌ No PR selected yet. Please run [SP] Select PR first.
+❌ No active session. Run [SS] Select Session to resume a past session, or [SP] Select PR to start a new one.
 ```
 Stop workflow.
 

package/src/prr/workflows/2-analyze/describe-pr/steps/step-04-output.md

@@ -1,7 +1,7 @@
 ---
 name: "step-04-output"
 description: "Write PR description to file and display summary"
-outputFile: "{review_output}/pr-description-{date}.md"
+outputFile: "{session_output}/pr-description.md"
 templateFile: "../templates/pr-description.template.md"
 ---
 
@@ -24,14 +24,13 @@ Using the template at `{templateFile}`, generate the PR description with:
 
 ### 2. Write to File
 
-Write to `{outputFile}` (replace {date} with actual date: YYYY-MM-DD).
+Write to `{outputFile}`.
 
-### 3. Update PR Context
+### 3. Update Working Context
 
-Update `{review_output}/current-pr-context.yaml`:
-- Add `description_generated: true`
-- Add `pr_type: "{classified_type}"`
-- Add `risk_level: "{risk_level}"`
+Store in working context:
+- `pr_type` = `{classified_type}`
+- `risk_level` = `{risk_level}`
 
 ### 4. Display Summary
 

package/src/prr/workflows/2-analyze/describe-pr/workflow.md

@@ -20,8 +20,8 @@ nextStep: "./steps/step-01-load-context.md"
 ## INITIALIZATION
 
 Load config from `{main_config}`.
-Load PR context from `{review_output}/current-pr-context.yaml`.
-If context file does not exist, instruct user to run [SP] Select PR first.
+Use `session_output`, `target_branch`, `base_branch`, `pr_number` from working context.
+If not set: prompt user to run [SS] Select Session (to resume a past session) or [SP] Select PR (to start a new one).
 
 ## EXECUTION
 

package/src/prr/workflows/3-review/architecture-review/checklist.md

@@ -22,5 +22,4 @@ validation-target: "Architecture review output file"
 - [ ] ❓ QUESTION findings include: specific question + list of potentially affected files outside the diff
 
 ## Output
-- [ ] Findings written to `{review_output}/architecture-review-{date}.md`
-- [ ] PR context updated with `architecture-review` in completed list
+- [ ] Findings written to `{session_output}/architecture-review.md`

package/src/prr/workflows/3-review/architecture-review/workflow.yaml

@@ -1,5 +1,5 @@
 name: architecture-review
-description: "Architecture-focused review: SOLID principles, layering, coupling, codebase consistency"
+description: "Architecture-focused review: SOLID principles, layering, coupling, codebase consistency, etc. — adapted to your architecture"
 author: "PR Review Kit"
 
 config_source: "{project-root}/_prr/prr/config.yaml"
@@ -7,11 +7,12 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/3-review/architecture-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/architecture-review-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/architecture-review.md"

package/src/prr/workflows/3-review/business-review/checklist.md

@@ -23,5 +23,4 @@ validation-target: "Business review output file"
 - [ ] Post-ship monitoring noted: what to watch after deploy
 
 ## Output
-- [ ] Findings written to `{review_output}/business-review-{date}.md`
-- [ ] PR context updated with `business-review` in completed list
+- [ ] Findings written to `{session_output}/business-review.md`

package/src/prr/workflows/3-review/business-review/instructions.xml

@@ -127,6 +127,8 @@ PR type: {pr_type} | Prior reviews loaded: {completed_reviews}
       MINIMAL  = additive feature, no regressions, low risk changes
     </risk-matrix>
 
+    <action>Apply any business-specific guidance from knowledge_base.reviewer_guidance.business_review and knowledge_base.relevant_guidelines to generate additional business checks beyond the default categories above. If no project-specific business guidance exists, skip silently.</action>
+
     <action>Structure the output by category, ordered by severity within each section:
       - Feature Completeness gaps (🔴 first, then 🟡, 🟢, ❓)
       - User Impact issues

package/src/prr/workflows/3-review/business-review/workflow.yaml

@@ -1,5 +1,5 @@
 name: business-review
-description: "Business impact review: user impact, business risk, feature completeness, data safety, observability"
+description: "Business impact review: user impact, business risk, feature completeness, data safety, observability — adapted to your project"
 author: "PR Review Kit"
 
 config_source: "{project-root}/_prr/prr/config.yaml"
@@ -7,11 +7,12 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/3-review/business-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/business-review-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/business-review.md"

package/src/prr/workflows/3-review/general-review/checklist.md

@@ -22,6 +22,5 @@ validation-target: "General review output file"
 - [ ] Side effect findings include: the affected location OUTSIDE the diff (not just the changed file)
 
 ## Output
-- [ ] Findings written to `{review_output}/general-review-{date}.md`
-- [ ] PR context updated with `general-review` in completed list
+- [ ] Findings written to `{session_output}/general-review.md`
 - [ ] At least one positive observation included (balanced review)

package/src/prr/workflows/3-review/general-review/instructions.xml

@@ -89,6 +89,13 @@ For side effect findings, include the AFFECTED LOCATION (the file outside the di
     </output-format>
   </step>
 
+  <step n="5b" goal="Stack-specific and project-specific code quality checks">
+    <action>Apply all code quality and common bug rules from knowledge_base.stack_context.rules for each detected stack</action>
+    <action>Apply code quality guidelines from knowledge_base.relevant_guidelines</action>
+    <action>Apply guidance from knowledge_base.reviewer_guidance.general_review</action>
+    <note>Generate additional checks specific to this project's technology and domain that go beyond the default categories above. If knowledge_base contains no stack-specific code quality rules, skip this step silently.</note>
+  </step>
+
   <step n="6" goal="Compile and write findings">
     <action>Group all findings by severity: 🔴 Blockers first, then 🟡 Warnings, then 🟢 Suggestions, then ❓ Questions</action>
     <action>Add positive observations: acknowledge good practices found</action>

package/src/prr/workflows/3-review/general-review/workflow.yaml

@@ -1,5 +1,5 @@
 name: general-review
-description: "General code quality review: logic, naming, readability, error handling, DRY, test coverage"
+description: "General code quality review: logic, naming, readability, error handling, DRY, test coverage, etc. — adapted to your stack"
 author: "PR Review Kit"
 
 config_source: "{project-root}/_prr/prr/config.yaml"
@@ -7,11 +7,12 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/3-review/general-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/general-review-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/general-review.md"

package/src/prr/workflows/3-review/performance-review/checklist.md

@@ -20,5 +20,4 @@ validation-target: "Performance review output file"
 - [ ] ❓ QUESTION findings include: specific concern + context needed to assess severity (e.g., "Is this in a hot path?", "What is the expected data volume?")
 
 ## Output
-- [ ] Findings written to `{review_output}/performance-review-{date}.md`
-- [ ] PR context updated with `performance-review` in completed list
+- [ ] Findings written to `{session_output}/performance-review.md`

package/src/prr/workflows/3-review/performance-review/workflow.yaml

@@ -1,5 +1,5 @@
 name: performance-review
-description: "Performance-focused code review: N+1 queries, memory leaks, async patterns, bundle size, caching"
+description: "Performance-focused code review: N+1 queries, memory leaks, async patterns, bundle size, caching, etc. — adapted to your stack"
 author: "PR Review Kit"
 
 config_source: "{project-root}/_prr/prr/config.yaml"
@@ -7,11 +7,12 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/3-review/performance-review"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/performance-review-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/performance-review.md"

package/src/prr/workflows/3-review/security-review/checklist.md

@@ -22,5 +22,4 @@ validation-target: "Security review output file"
 - [ ] ❓ QUESTION findings include: specific concern + exact question to ask author (e.g., "Was this auth check intentionally removed?")
 
 ## Output
-- [ ] Findings written to `{review_output}/security-review-{date}.md`
-- [ ] PR context updated with `security-review` in completed list
+- [ ] Findings written to `{session_output}/security-review.md`

package/src/prr/workflows/3-review/security-review/workflow.yaml

@@ -1,5 +1,5 @@
 name: security-review
-description: "Security-focused code review: OWASP top 10, injection, auth, secrets, dependencies"
+description: "Security-focused code review: OWASP top 10, injection, auth, secrets, dependencies, etc. — adapted to your project"
 author: "PR Review Kit"
 
 config_source: "{project-root}/_prr/prr/config.yaml"
@@ -7,6 +7,7 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/3-review/security-review"
@@ -14,5 +15,5 @@ instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 owasp_data: "{installed_path}/data/owasp-checklist.csv"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/security-review-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/security-review.md"

package/src/prr/workflows/4-improve/improve-code/checklist.md

@@ -13,6 +13,5 @@ validation-target: "Improve code output file"
 - [ ] Suggestions are correct — the AFTER code actually works
 
 ## Output
-- [ ] All suggestions written to `{review_output}/improve-code-{date}.md`
+- [ ] All suggestions written to `{session_output}/improve-code.md`
 - [ ] Suggestions grouped by category (Bugs | Quality | Performance | Best Practices)
-- [ ] PR context updated with `improve-code` in completed list

package/src/prr/workflows/4-improve/improve-code/workflow.yaml

@@ -7,11 +7,12 @@ user_name: "{config_source}:user_name"
 communication_language: "{config_source}:communication_language"
 target_repo: "{config_source}:target_repo"
 review_output: "{config_source}:review_output"
+session_output: "working-context:session_output || latest-session-folder-in:{review_output}"
 date: system-generated
 
 installed_path: "{project-root}/_prr/prr/workflows/4-improve/improve-code"
 instructions: "{installed_path}/instructions.xml"
 validation: "{installed_path}/checklist.md"
 
-pr_context: "{review_output}/current-pr-context.yaml"
-output_file: "{review_output}/improve-code-{date}.md"
+pr_context: "working-context:target_branch,base_branch,pr_number,pr_knowledge_base"
+output_file: "{session_output}/improve-code.md"

package/src/prr/workflows/5-ask/ask-code/steps/step-01-load-context.md

@@ -10,9 +10,9 @@ nextStepFile: "./step-02-answer.md"
 
 ### 1. Load PR Context
 
-Read `{review_output}/current-pr-context.yaml`.
+Use `session_output`, `target_branch`, `base_branch` from working context.
 
-If not found, prompt user to run [SP] Select PR first.
+If not set, prompt user to run [SS] Select Session or [SP] Select PR first.
 
 ### 2. Load the Diff
 

package/src/prr/workflows/6-report/generate-report/steps/step-01-collect.md

@@ -8,19 +8,23 @@ nextStepFile: "./step-02-organize.md"
 
 ## Sequence of Instructions
 
-### 1. Load PR Context
+### 1. Detect Completed Reviews
 
-Read `{review_output}/current-pr-context.yaml` to get list of completed reviews.
+Check which review files exist in `{session_output}/`:
+
+```bash
+ls "{session_output}/"
+```
 
 ### 2. Collect Review Output Files
 
-For each completed review in `review.completed` list, read the corresponding output file:
-- `general-review` → `{review_output}/general-review-*.md` (latest)
-- `security-review` → `{review_output}/security-review-*.md` (latest)
-- `performance-review` → `{review_output}/performance-review-*.md` (latest)
-- `architecture-review` → `{review_output}/architecture-review-*.md` (latest)
-- `business-review` → `{review_output}/business-review-*.md` (latest)
-- `improve-code` → `{review_output}/improve-code-*.md` (latest)
+For each review file that exists, read it:
+- `general-review` → `{session_output}/general-review.md`
+- `security-review` → `{session_output}/security-review.md`
+- `performance-review` → `{session_output}/performance-review.md`
+- `architecture-review` → `{session_output}/architecture-review.md`
+- `business-review` → `{session_output}/business-review.md`
+- `improve-code` → `{session_output}/improve-code.md`
 
 ### 3. Parse All Findings
 

package/src/prr/workflows/6-report/generate-report/steps/step-03-write.md

@@ -1,7 +1,7 @@
 ---
 name: "step-03-write"
 description: "Write the final review report to file"
-outputFile: "{review_output}/review-{target_branch_slug}-{date}.md"
+outputFile: "{session_output}/final-review.md"
 templateFile: "../templates/review-report.template.md"
 ---
 
@@ -27,7 +27,7 @@ The report includes:
 ```
 ✅ Review Report Generated!
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-📄 File: {review_output}/review-{target_branch_slug}-{date}.md
+📄 File: {session_output}/final-review.md
 
 Summary:
   🔴 Blockers: {blocker_count}

package/src/prr/workflows/6-report/generate-report/workflow.md

@@ -19,7 +19,8 @@ nextStep: "./steps/step-01-collect.md"
 ## INITIALIZATION
 
 Load config from `{main_config}`.
-Load PR context from `{review_output}/current-pr-context.yaml`.
+Use `session_output` from working context.
+If not set: prompt user to run [SS] Select Session or [SP] Select PR first.
 
 ## EXECUTION
 

package/src/prr/workflows/6-report/post-comments/steps/step-01-format.md

@@ -10,9 +10,9 @@ nextStepFile: "./step-02-post.md"
 
 ### 1. Check Prerequisites
 
-Verify `{review_output}/current-pr-context.yaml` exists and contains:
-- `pr_number` — if missing, show: `❌ No PR number found. Run [SP] Select PR first.`
-- `target_branch`, `base_branch`
+Verify working context contains:
+- `pr_number` — if missing, show: `❌ No PR number found. Run [SS] Select Session or [SP] Select PR first.`
+- `target_branch`, `base_branch`, `session_output`
 
 Verify platform CLI is available:
 
@@ -54,8 +54,7 @@ Store as `{commit_sha}`.
 
 ### 3. Load Review Report
 
-Find the latest report in `{review_output}/review-*.md`.
-Sort by modification time, take the most recent.
+Read the report at `{session_output}/final-review.md`.
 
 ### 4. Parse All Findings
 

package/src/prr/workflows/6-report/post-comments/workflow.md

@@ -37,10 +37,11 @@ Depends on `{active_platform}`:
 ## INITIALIZATION
 
 Load config from `{main_config}`.
-Load PR context from `{review_output}/current-pr-context.yaml`.
+Use `session_output`, `target_branch`, `base_branch`, `pr_number`, `active_platform` from working context.
+If `session_output` not set: prompt user to run [SS] Select Session or [SP] Select PR first.
 Use `{active_platform}` (or detect from `{platform}` config).
 
-Set `{temp_dir}` = `{review_output}/temp`.
+Set `{temp_dir}` = `{session_output}/temp`.
 Create it if it doesn't exist:
 ```bash
 mkdir -p "{temp_dir}"