Add a new recap type 'fix' for when an issue identified in code review is fixed

src/mcp/CLAUDE.md

@@ -18,7 +18,7 @@ Exposes issue/PR operations to agents. Provider-agnostic — routes to GitHub, L
 
 ### recap-server.ts
 
-Manages the recap system — structured knowledge capture (decisions, insights, risks, artifacts) displayed in the VS Code sidebar.
+Manages the recap system — structured knowledge capture (decisions, insights, risks, fixes, artifacts) displayed in the VS Code sidebar.
 
 **Tools:** `set_goal`, `set_complexity`, `add_entry`, `add_artifact`, `get_recap`, `set_loom_state`, `get_loom_state`
 

src/mcp/recap-server.test.ts

@@ -91,6 +91,22 @@ describe('recap-server add_entry deduplication', () => {
 				content: 'Found existing helper function',
 			})
 		})
+
+		it('should create a new fix entry and return skipped: false', async () => {
+			const result = await addEntryWithDeduplication(
+				readRecapMock,
+				writeRecapMock,
+				'fix',
+				'Fixed null check in auth handler per review feedback'
+			)
+			expect(result.skipped).toBe(false)
+			expect(result.id).toBe('test-uuid-123')
+			expect(mockRecapFile.entries).toHaveLength(1)
+			expect(mockRecapFile.entries?.[0]).toMatchObject({
+				type: 'fix',
+				content: 'Fixed null check in auth handler per review feedback',
+			})
+		})
 	})
 
 	describe('when adding an entry with duplicate type and content', () => {

src/mcp/recap-server.ts

@@ -1,7 +1,7 @@
 /**
  * Loom Recap MCP Server
  *
- * Captures session context (goal, decisions, insights, risks, assumptions)
+ * Captures session context (goal, decisions, insights, risks, fixes, assumptions)
  * for the VS Code Loom Context Panel.
  *
  * Environment variables:
@@ -234,7 +234,7 @@ server.registerTool(
 			'Append an entry to the recap. If an entry with the same type and content already exists, it will be skipped.',
 		inputSchema: {
 			type: z
-				.enum(['decision', 'insight', 'risk', 'assumption', 'other'])
+				.enum(['decision', 'insight', 'risk', 'assumption', 'fix', 'other'])
 				.describe('Entry type'),
 			content: z.string().describe('Entry content'),
 			worktreePath: z.string().optional().describe('Optional worktree path to scope recap to a specific loom'),
@@ -360,7 +360,7 @@ server.registerTool(
 				z.object({
 					id: z.string(),
 					timestamp: z.string(),
-					type: z.enum(['decision', 'insight', 'risk', 'assumption', 'other']),
+					type: z.enum(['decision', 'insight', 'risk', 'assumption', 'fix', 'other']),
 					content: z.string(),
 				})
 			),

src/mcp/recap-types.ts

@@ -3,11 +3,11 @@
  *
  * The Recap MCP captures session context that scrolls away during Claude sessions:
  * - Goal: The original problem statement
- * - Entries: Decisions, insights, risks, assumptions discovered during the session
+ * - Entries: Decisions, insights, risks, assumptions, fixes discovered during the session
  */
 
 /** Entry types for recap entries */
-export type RecapEntryType = 'decision' | 'insight' | 'risk' | 'assumption' | 'other'
+export type RecapEntryType = 'decision' | 'insight' | 'risk' | 'assumption' | 'fix' | 'other'
 
 /** Artifact types for tracking created items */
 export type RecapArtifactType = 'comment' | 'issue' | 'pr'

src/utils/mcp.ts

@@ -199,7 +199,7 @@ export async function writeRecapFile(filePath: string, recap: Record<string, unk
 /**
  * Generate MCP configuration for recap server
  *
- * The recap server captures session context (goal, decisions, insights, risks, assumptions)
+ * The recap server captures session context (goal, decisions, insights, risks, fixes, assumptions)
  * for the VS Code Loom Context Panel.
  *
  * @param loomPath - Absolute path to the loom workspace

templates/agents/iloom-issue-implementer.md

@@ -43,6 +43,8 @@ After creating or updating any issue comment, use the Recap MCP tools:
 
 This enables the recap panel to show quick-reference links to artifacts created during the session.
 
+**Do NOT log `fix` recap entries** — the orchestrator tracks which review findings were addressed.
+
 {{#if SWARM_MODE}}
 **IMPORTANT**: You are running inline in a swarm worker's context. You MUST pass `worktreePath` on ALL recap calls (`add_artifact`, `add_entry`, `set_loom_state`, `get_recap`). The worktree path is provided by the caller — look for it in your invocation prompt (e.g., "Your worktree path is ..."). Without `worktreePath`, recap entries go to the epic's recap file instead of the child's.
 {{/if}}

templates/prompts/issue-prompt.txt

@@ -64,11 +64,12 @@ The recap panel is visible to the user in VS Code. They don't care about your in
 2. **Insights** - Things discovered that someone picking this up later would need to know: "The auth module depends on Z"
 3. **Risks** - Things that could go wrong: "This assumes X, will break if Y"
 4. **Assumptions** - Bets you're making: "Assuming backwards compat not needed"
+5. **Fixes** - Code review findings you addressed: "Fixed null check in auth handler per review feedback"
 
 Use these Recap MCP tools:
 - `recap.set_complexity` - Call when complexity is confirmed at ROUTING DECISION POINT (trivial/simple/complex)
 - `recap.get_recap` - Call before adding entries to check what's already captured
-- `recap.add_entry` - Call with type (decision/insight/risk/assumption) and concise content
+- `recap.add_entry` - Call with type (decision/insight/risk/assumption/fix) and concise content
 - `recap.add_artifact` - After creating/updating comments, issues, or PRs, log them with type, primaryUrl, and description. Duplicates with the same primaryUrl will be replaced.
 
 **NEVER log:**
@@ -405,7 +406,7 @@ Always prepend: `"Your working directory is <worktree-path>. cd there before doi
 7a. Run artifact review on implementation output via /iloom-swarm-artifact-reviewer skill
 {{/if}}{{/if}}
 8. Set state to `code_review` (pass `worktreePath: "<your-worktree-path>"`), run code review via /iloom-swarm-code-reviewer skill
-9. If critical/high issues found, auto-fix and optionally re-review
+9. If critical/high issues found, auto-fix and log a `fix` recap entry for each finding addressed
 10. Stage and commit all changes: `git add -A && git commit -m "feat(issue-<issue-number>): [descriptive summary of changes]"` — the commit message must summarize what was implemented (not just "fixes #NNN")
 11. Set state to `done` (pass `worktreePath: "<your-worktree-path>"`), report structured result to orchestrator
 {{else}}
@@ -1255,9 +1256,11 @@ This section is about reviewing code changes for quality, security, and complian
 3. If critical, high, or medium priority issues found:
 {{#if ONE_SHOT_MODE}}
    - Automatically implement the recommended fixes for critical, high, and medium priority issues without asking
+   - After fixing each issue, log a `fix` recap entry describing what was resolved (e.g., `recap.add_entry({ type: "fix", content: "Fixed missing null check in auth handler" })`)
 {{else}}
    - Ask the user: "Issues found. Do you want to proceed anyway, or address these first?"
    - Wait for user response before continuing
+   - After fixing each issue, log a `fix` recap entry describing what was resolved (e.g., `recap.add_entry({ type: "fix", content: "Fixed missing null check in auth handler" })`)
 {{/if}}
 {{/if}}
 
@@ -1413,7 +1416,7 @@ When the user requests help, **YOU MUST USE subagents** to preserve your context
 
 After handling each request, summarize what was done and confirm you're still available.
 
-Use `recap.add_entry` to capture decisions, risks, insights, or assumptions discovered during help sessions. Do not log status updates or task completions.
+Use `recap.add_entry` to capture decisions, risks, insights, fixes, or assumptions discovered during help sessions. Do not log status updates or task completions.
 
 ### Epic Decomposition
 

templates/prompts/pr-prompt.txt

@@ -37,12 +37,13 @@ The recap panel is visible to the user in VS Code. They don't care about your in
 2. **Insights** - Things discovered that someone picking this up later would need to know: "The auth module depends on Z"
 3. **Risks** - Things that could go wrong: "This assumes X, will break if Y"
 4. **Assumptions** - Bets you're making: "Assuming backwards compat not needed"
+5. **Fixes** - Code review findings you addressed: "Fixed null check in auth handler per review feedback"
 
 Use these Recap MCP tools:
 - `recap.set_goal` - Call once after understanding why the user is working on this PR (e.g., "Review PR for security concerns", "Fix failing tests")
 - `recap.set_complexity` - Call when task complexity is assessed (trivial/simple/complex)
 - `recap.get_recap` - Call before adding entries to check what's already captured
-- `recap.add_entry` - Call with type (decision/insight/risk/assumption) and concise content
+- `recap.add_entry` - Call with type (decision/insight/risk/assumption/fix) and concise content
 - `recap.add_artifact` - After creating/updating comments, issues, or PRs, log them with type, primaryUrl, and description. Duplicates with the same primaryUrl will be replaced.
 
 **NEVER log:**
@@ -199,7 +200,7 @@ When the user requests help, **prefer subagents** to preserve your context windo
 
 After handling each request, summarize what was done and confirm you're still available.
 
-Use `recap.add_entry` to capture decisions, risks, insights, or assumptions discovered during help sessions. Do not log status updates or task completions.
+Use `recap.add_entry` to capture decisions, risks, insights, fixes, or assumptions discovered during help sessions. Do not log status updates or task completions.
 
 ### Epic Decomposition
 

templates/prompts/regular-prompt.txt

@@ -37,12 +37,13 @@ The recap panel is visible to the user in VS Code. They don't care about your in
 2. **Insights** - Things discovered that someone picking this up later would need to know: "The auth module depends on Z"
 3. **Risks** - Things that could go wrong: "This assumes X, will break if Y"
 4. **Assumptions** - Bets you're making: "Assuming backwards compat not needed"
+5. **Fixes** - Code review findings you addressed: "Fixed null check in auth handler per review feedback"
 
 Use these Recap MCP tools:
 - `recap.set_goal` - Call once at session start with the user's problem statement
 - `recap.set_complexity` - Call when complexity is confirmed at ROUTING DECISION POINT (trivial/simple/complex)
 - `recap.get_recap` - Call before adding entries to check what's already captured
-- `recap.add_entry` - Call with type (decision/insight/risk/assumption) and concise content
+- `recap.add_entry` - Call with type (decision/insight/risk/assumption/fix) and concise content
 - `recap.add_artifact` - After creating/updating comments, issues, or PRs, log them with type, primaryUrl, and description. Duplicates with the same primaryUrl will be replaced.
 
 **NEVER log:**
@@ -800,7 +801,7 @@ When the user requests help, **prefer subagents** to preserve your context windo
 
 After handling each request, summarize what was done and confirm you're still available.
 
-Use `recap.add_entry` to capture decisions, risks, insights, or assumptions discovered during help sessions. Do not log status updates or task completions.
+Use `recap.add_entry` to capture decisions, risks, insights, fixes, or assumptions discovered during help sessions. Do not log status updates or task completions.
 
 ### Epic Decomposition
 

templates/prompts/session-summary-prompt.txt

@@ -32,6 +32,7 @@ You are generating a summary of THIS conversation - the development session you
 - **Insights**: Discoveries that future developers need to know
 - **Risks**: Things that could go wrong
 - **Assumptions**: Bets being made about the implementation
+- **Fixes**: Code review issues that were identified and resolved
 
 When there are conflicts between the recap and conversation transcript, give weight to the most recent timestamp.
 
@@ -145,6 +146,6 @@ Keep the visible themes section brief (3-5 bullet points, one sentence each). Th
 ## VALIDATION CHECKLIST - FAILING THIS LIST MEANS FAILING THE TASK:
 * Did you ouput ONLY the markdown with no commentary before or after?
 {{#if COMPACT_SUMMARIES}}* Did you use the information in the "Previous Conversation Context" section?{{/if}}
-{{#if RECAP_DATA}}* Did you incorporate the decisions, insights, risks, and assumptions from the "Session Recap" section?{{/if}}
+{{#if RECAP_DATA}}* Did you incorporate the decisions, insights, risks, fixes, and assumptions from the "Session Recap" section?{{/if}}
 * Did you avoid process noise? (No mentions of: workflow phases, complexity classifications, git commands, test/build results, or descriptions of what you DID vs what was LEARNED)
 

templates/prompts/swarm-orchestrator-prompt.txt

@@ -23,7 +23,7 @@ You are a **coordinator**, not an executor. Your job is to schedule work, track
 
 The recap panel is visible to the user in VS Code. Use these Recap MCP tools to capture knowledge:
 
-- `recap.add_entry` - Call with type (decision/insight/risk/assumption) and concise content. **Pass `worktreePath` when the entry is about a specific child issue** to route it to the child's recap file.
+- `recap.add_entry` - Call with type (decision/insight/risk/assumption/fix) and concise content. **Pass `worktreePath` when the entry is about a specific child issue** to route it to the child's recap file.
 - `recap.get_recap` - Call before adding entries to check what's already captured. **Pass `worktreePath` to read a specific child's recap.**
 - `recap.add_artifact` - After creating/updating comments, issues, or PRs, log them with type, primaryUrl, and description. Duplicates with the same primaryUrl will be replaced. **Pass `worktreePath` when the artifact belongs to a child issue.**
 - `recap.set_loom_state` - Update the loom state (in_progress, done, failed, etc.)
@@ -542,7 +542,7 @@ IMPORTANT: Only fix the specific issues identified in the review findings. Do NO
 ````
 
 **Handle the subagent result:**
-- If the fix agent succeeds: log "Post-swarm review: N findings addressed, fix committed."
+- If the fix agent succeeds: log a `fix` recap entry for each finding addressed (e.g., `recap.add_entry({ type: "fix", content: "Fixed missing null check in auth handler" })`). Then log "Post-swarm review: N findings addressed, fix committed."
 - If the fix agent fails: log the failure and continue. Auto-fix failure is non-blocking.
 
 **Single pass only.** Do NOT re-review after fixing. This prevents infinite review-fix loops.