Require human verification before resolving debug sessions

CHANGELOG.md

@@ -6,6 +6,9 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ## [Unreleased]
 
+### Changed
+- `/gsd:debug` flow now requires a `human-verify` checkpoint after self-verification before marking debug sessions `resolved` and moving files to `.planning/debug/resolved/`
+
 ## [1.20.3] - 2026-02-16
 
 ### Fixed

agents/gsd-debugger.md

@@ -737,7 +737,7 @@ DEBUG_RESOLVED_DIR=.planning/debug/resolved
 
 ```markdown
 ---
-status: gathering | investigating | fixing | verifying | resolved
+status: gathering | investigating | fixing | verifying | awaiting_human_verify | resolved
 trigger: "[verbatim user input]"
 created: [ISO timestamp]
 updated: [ISO timestamp]
@@ -801,10 +801,10 @@ files_changed: []
 ## Status Transitions
 
 ```
-gathering -> investigating -> fixing -> verifying -> resolved
+gathering -> investigating -> fixing -> verifying -> awaiting_human_verify -> resolved
-                  ^            |           |
+                  ^            |           |                 |
-                  |____________|___________|
+                  |____________|___________|_________________|
-                  (if verification fails)
+                  (if verification fails or user reports issue)
 ```
 
 ## Resume Behavior
@@ -907,6 +907,7 @@ Based on status:
 - "investigating" -> Continue investigation_loop from Current Focus
 - "fixing" -> Continue fix_and_verify
 - "verifying" -> Continue verification
+- "awaiting_human_verify" -> Wait for checkpoint response and either finalize or continue investigation
 </step>
 
 <step name="return_diagnosis">
@@ -966,11 +967,52 @@ Update status to "fixing".
 - Update status to "verifying"
 - Test against original Symptoms
 - If verification FAILS: status -> "investigating", return to investigation_loop
-- If verification PASSES: Update Resolution.verification, proceed to archive_session
+- If verification PASSES: Update Resolution.verification, proceed to request_human_verification
+</step>
+
+<step name="request_human_verification">
+**Require user confirmation before marking resolved.**
+
+Update status to "awaiting_human_verify".
+
+Return:
+
+```markdown
+## CHECKPOINT REACHED
+
+**Type:** human-verify
+**Debug Session:** .planning/debug/{slug}.md
+**Progress:** {evidence_count} evidence entries, {eliminated_count} hypotheses eliminated
+
+### Investigation State
+
+**Current Hypothesis:** {from Current Focus}
+**Evidence So Far:**
+- {key finding 1}
+- {key finding 2}
+
+### Checkpoint Details
+
+**Need verification:** confirm the original issue is resolved in your real workflow/environment
+
+**Self-verified checks:**
+- {check 1}
+- {check 2}
+
+**How to check:**
+1. {step 1}
+2. {step 2}
+
+**Tell me:** "confirmed fixed" OR what's still failing
+```
+
+Do NOT move file to `resolved/` in this step.
 </step>
 
 <step name="archive_session">
-**Archive resolved debug session.**
+**Archive resolved debug session after human confirmation.**
+
+Only run this step when checkpoint response confirms the fix works end-to-end.
 
 Update status to "resolved".
 
@@ -1127,6 +1169,8 @@ Orchestrator presents checkpoint to user, gets response, spawns fresh continuati
 **Commit:** {hash}
 ```
 
+Only return this after human verification confirms the fix.
+
 ## INVESTIGATION INCONCLUSIVE
 
 ```markdown
@@ -1176,7 +1220,8 @@ Check for mode flags in prompt context:
 **goal: find_and_fix** (default)
 - Find root cause, then fix and verify
 - Complete full debugging cycle
-- Archive session when verified
+- Require human-verify checkpoint after self-verification
+- Archive session only after user confirmation
 
 **Default mode (no flags):**
 - Interactive debugging with user

commands/gsd/debug.md

@@ -110,6 +110,9 @@ Task(
 **If `## CHECKPOINT REACHED`:**
 - Present checkpoint details to user
 - Get user response
+- If checkpoint type is `human-verify`:
+  - If user confirms fixed: continue so agent can finalize/resolve/archive
+  - If user reports issues: continue so agent returns to investigation/fixing
 - Spawn continuation agent (see step 5)
 
 **If `## INVESTIGATION INCONCLUSIVE`:**

get-shit-done/templates/DEBUG.md

@@ -8,7 +8,7 @@ Template for `.planning/debug/[slug].md` — active debug session tracking.
 
 ```markdown
 ---
-status: gathering | investigating | fixing | verifying | resolved
+status: gathering | investigating | fixing | verifying | awaiting_human_verify | resolved
 trigger: "[verbatim user input]"
 created: [ISO timestamp]
 updated: [ISO timestamp]
@@ -127,9 +127,14 @@ files_changed: []
 - Update Resolution.verification with results
 - If verification fails: status → "investigating", try again
 
+**After self-verification passes:**
+- status -> "awaiting_human_verify"
+- Request explicit user confirmation in a checkpoint
+- Do NOT move file to resolved yet
+
 **On resolution:**
 - status → "resolved"
-- Move file to .planning/debug/resolved/
+- Move file to .planning/debug/resolved/ (only after user confirms fix)
 
 </lifecycle>