fix(prompts): prefer task_id in continuation guidance

src/agents/atlas/default-prompt-sections.ts

@@ -139,10 +139,10 @@ Count remaining **top-level task** checkboxes. Ignore nested verification/eviden
 [ ] Boulder: Read plan file, confirmed current progress
 \`\`\`
 
-**If verification fails**: Resume the SAME session with the ACTUAL error output:
+**If verification fails**: Resume the SAME task with the ACTUAL error output:
 \`\`\`typescript
 task(
-  session_id="ses_xyz789",
+  task_id="ses_xyz789",
   load_skills=[...],
   prompt="Verification failed: {actual error}. Fix."
 )
@@ -156,7 +156,7 @@ Every \`task()\` output includes a task_id. STORE IT.
 
 If task fails:
 1. Identify what went wrong
-2. **Resume the SAME session** - subagent has full context already:
+2. **Resume the SAME task** - subagent has full context already:
     \`\`\`typescript
     task(
       task_id="ses_xyz789",  // Task ID from failed task
@@ -187,7 +187,7 @@ Final-wave reviewers can finish in parallel before you update the plan file, so
 
 1. Execute all Final Wave tasks in parallel
 2. If ANY verdict is REJECT:
-   - Fix the issues (delegate via \`task()\` with \`session_id\`)
+   - Fix the issues (delegate via \`task()\` with \`task_id\`)
    - Re-run the rejecting reviewer
    - Repeat until ALL verdicts are APPROVE
 3. Mark \`pass-final-wave\` todo as \`completed\`

src/agents/atlas/gemini-prompt-sections.ts

@@ -154,7 +154,7 @@ Answer THREE questions:
 ALL three must be YES. "Probably" = NO. "I think so" = NO.
 
 - **All 3 YES** → Proceed.
-- **Any NO** → Reject: resume session with \`session_id\`, fix the specific issue.
+- **Any NO** → Reject: resume with \`task_id\`, fix the specific issue.
 
 **After gate passes:** Check boulder state:
 \`\`\`
@@ -185,7 +185,7 @@ Final-wave reviewers can finish in parallel before you update the plan file, so
 
 1. Execute all Final Wave tasks in parallel
 2. If ANY verdict is REJECT:
-   - Fix the issues (delegate via \`task()\` with \`session_id\`)
+   - Fix the issues (delegate via \`task()\` with \`task_id\`)
    - Re-run the rejecting reviewer
    - Repeat until ALL verdicts are APPROVE
 3. Mark \`pass-final-wave\` todo as \`completed\`
@@ -242,7 +242,7 @@ Subagents CLAIM "done" when:
 
 **Phase 3 is NOT optional for user-facing changes.**
 **Phase 4 gate: ALL three questions must be YES. "Unsure" = NO.**
-**On failure: Resume with \`session_id\` and the SPECIFIC failure.**
+**On failure: Resume with \`task_id\` and the SPECIFIC failure.**
 </verification_rules>`
 
 export const GEMINI_ATLAS_BOUNDARIES = `<boundaries>
@@ -272,7 +272,7 @@ export const GEMINI_ATLAS_CRITICAL_RULES = `<critical_rules>
 - Send prompts under 30 lines
 - Skip scanned-file lsp_diagnostics (use 'filePath=".", extension=".ts"' for TypeScript projects; directory scans are capped at 50 files)
 - Batch multiple tasks in one delegation
-- Start fresh session for failures (use session_id)
+- Start fresh session for failures (do NOT do this; use task_id)
 
 **ALWAYS**:
 - Include ALL 6 sections in delegation prompts
@@ -280,6 +280,6 @@ export const GEMINI_ATLAS_CRITICAL_RULES = `<critical_rules>
 - Run scanned-file QA after every delegation
 - Pass inherited wisdom to every subagent
 - Parallelize independent tasks
-- Store and reuse session_id for retries
+- Store and reuse task_id for retries
 - **USE TOOL CALLS for verification - not internal reasoning**
 </critical_rules>`

src/agents/atlas/gpt-prompt-sections.ts

@@ -158,7 +158,7 @@ Before moving to the next task, answer these THREE questions honestly:
 3. **Am I confident this doesn't break existing functionality?** (If no → run broader tests)
 
 - **All 3 YES** → Proceed: mark task complete, move to next.
-- **Any NO** → Reject: resume session with \`session_id\`, fix the specific issue.
+- **Any NO** → Reject: resume with \`task_id\`, fix the specific issue.
 - **Unsure on any** → Reject: "unsure" = "no". Investigate until you have a definitive answer.
 
 **After gate passes:** Check boulder state:
@@ -190,7 +190,7 @@ Final-wave reviewers can finish in parallel before you update the plan file, so
 
 1. Execute all Final Wave tasks in parallel
 2. If ANY verdict is REJECT:
-   - Fix the issues (delegate via \`task()\` with \`session_id\`)
+   - Fix the issues (delegate via \`task()\` with \`task_id\`)
    - Re-run the rejecting reviewer
    - Repeat until ALL verdicts are APPROVE
 3. Mark \`pass-final-wave\` todo as \`completed\`
@@ -248,7 +248,7 @@ Your job is to CATCH THEM. Assume every claim is false until YOU personally veri
 
 **Phase 4 gate:** ALL three questions must be YES to proceed. "Unsure" = NO. Investigate until certain.
 
-**On failure at any phase:** Resume with \`session_id\` and the SPECIFIC failure. Do not start fresh.
+**On failure at any phase:** Resume with \`task_id\` and the SPECIFIC failure. Do not start fresh.
 </verification_rules>`
 
 export const GPT_ATLAS_BOUNDARIES = `<boundaries>
@@ -276,7 +276,7 @@ export const GPT_ATLAS_CRITICAL_RULES = `<critical_rules>
 - Send prompts under 30 lines
 - Skip scanned-file lsp_diagnostics (use 'filePath=".", extension=".ts"' for TypeScript projects; directory scans are capped at 50 files)
 - Batch multiple tasks in one delegation
-- Start fresh session for failures (use session_id)
+- Start fresh session for failures (do NOT do this; use task_id)
 
 **ALWAYS**:
 - Include ALL 6 sections in delegation prompts
@@ -284,5 +284,5 @@ export const GPT_ATLAS_CRITICAL_RULES = `<critical_rules>
 - Run scanned-file QA after every delegation
 - Pass inherited wisdom to every subagent
 - Parallelize independent tasks
-- Store and reuse session_id for retries
+- Store and reuse task_id for retries
 </critical_rules>`

src/agents/hephaestus/gpt-5-3-codex.ts

@@ -407,7 +407,7 @@ After delegation, ALWAYS verify: works as expected? follows codebase pattern? MU
 
 ### Session Continuity
 
-Every \`task()\` output includes a session_id. **USE IT for follow-ups.**
+Every \`task()\` output includes a task_id. **USE IT for follow-ups.**
 
 - **Task failed/incomplete** - \`task_id="{id}", prompt="Fix: {error}"\`
 - **Follow-up on result** - \`task_id="{id}", prompt="Also: {question}"\`

src/hooks/atlas/index.test.ts

@@ -520,7 +520,7 @@ session_id: ses_standalone_def
       cleanupMessageStorage(sessionID)
     })
 
-     test("should include session_id and checkbox instructions in reminder", async () => {
+     test("should include task_id and checkbox instructions in reminder", async () => {
        // given - boulder state, Atlas caller
        const sessionID = "session-resume-test"
        setupMessageStorage(sessionID, "atlas")

src/hooks/atlas/system-reminder-templates.ts

@@ -98,7 +98,7 @@ Answer honestly:
 ALL three must be YES. "Probably" = NO. "I think so" = NO. Investigate until CERTAIN.
 
 - **All 3 YES** - Proceed: mark task complete, move to next.
-- **Any NO** - Reject: resume session with \`session_id\`, fix the specific issue.
+- **Any NO** - Reject: resume with \`task_id\`, fix the specific issue.
 - **Unsure** - Reject: "unsure" = "no". Investigate until you have a definitive answer.
 
 **DO NOT proceed to the next task until all 4 phases are complete and the gate passes.**`

src/hooks/compaction-context-injector/compaction-context-prompt.ts

@@ -49,8 +49,8 @@ This section is CRITICAL for reviewer agents (momus, oracle) to maintain continu
 
 ## 8. Delegated Agent Sessions
 - List ALL background agent tasks spawned during this session
-- For each: agent name, category, status, description, and **session_id**
+- For each: agent name, category, status, description, and **task_id**
-- **RESUME, DON'T RESTART.** Each listed session retains full context. After compaction, use \`session_id\` to continue existing agent sessions instead of spawning new ones. This saves tokens, preserves learned context, and prevents duplicate work.
+- **RESUME, DON'T RESTART.** Each listed delegated task retains full context. After compaction, use \`task_id\` to continue existing delegated work instead of spawning new tasks. This saves tokens, preserves learned context, and prevents duplicate work.
 
 This context is critical for maintaining continuity after compaction.
 `

src/hooks/compaction-context-injector/index.test.ts

@@ -107,7 +107,7 @@ describe("createCompactionContextInjector", () => {
       //#then
       expect(prompt).toContain("Delegated Agent Sessions")
       expect(prompt).toContain("RESUME, DON'T RESTART")
-      expect(prompt).toContain("session_id")
+      expect(prompt).toContain("task_id")
     })
 
     it("injects actual task history when backgroundManager and sessionID provided", async () => {