docs(sisyphus-task): clarify resume usage with session_id and add when-to-use guidance

- Fix terminology: 'Task ID' → 'Session ID' in resume parameter docs
- Add clear 'WHEN TO USE resume' section with concrete scenarios
- Add example usage pattern in Sisyphus agent prompt
- Emphasize token savings and context preservation benefits

src/agents/sisyphus.ts

@@ -265,8 +265,18 @@ result = task(...)  // Never wait synchronously for explore/librarian
 3. When results needed: \`background_output(task_id="...")\`
 4. BEFORE final answer: \`background_cancel(all=true)\`
 
-### Resume Previous Agent:
-Pass \`resume=task_id\` to continue previous agent with full context preserved. Useful for follow-up questions or multi-turn exploration.
+### Resume Previous Agent (CRITICAL for efficiency):
+Pass \`resume=session_id\` to continue previous agent with FULL CONTEXT PRESERVED.
+
+**ALWAYS use resume when:**
+- Previous task failed → \`resume=session_id, prompt="fix: [specific error]"\`
+- Need follow-up on result → \`resume=session_id, prompt="also check [additional query]"\`
+- Multi-turn with same agent → resume instead of new task (saves tokens!)
+
+**Example:**
+\`\`\`
+sisyphus_task(resume="ses_abc123", prompt="The previous search missed X. Also look for Y.")
+\`\`\`
 
 ### Search Stop Conditions
 

src/tools/call-omo-agent/constants.ts

@@ -4,4 +4,4 @@ export const CALL_OMO_AGENT_DESCRIPTION = `Spawn explore/librarian agent. run_in
 
 Available: {agents}
 
-Pass \`resume=task_id\` to continue previous agent with full context. Prompts MUST be in English. Use \`background_output\` for async results.`
+Pass \`resume=session_id\` to continue previous agent with full context. Prompts MUST be in English. Use \`background_output\` for async results.`

src/tools/sisyphus-task/constants.ts

@@ -243,7 +243,12 @@ MUTUALLY EXCLUSIVE: Provide EITHER category OR agent, not both (unless resuming)
 - category: Use predefined category (${BUILTIN_CATEGORIES}) → Spawns Sisyphus-Junior with category config
 - agent: Use specific agent directly (e.g., "oracle", "explore")
 - background: true=async (returns task_id), false=sync (waits for result). Default: false. Use background=true ONLY for parallel exploration with 5+ independent queries.
-- resume: Task ID to resume - continues previous agent session with full context preserved
+- resume: Session ID to resume (from previous task output). Continues agent with FULL CONTEXT PRESERVED - saves tokens, maintains continuity.
 - skills: Array of skill names to prepend to prompt (e.g., ["playwright", "frontend-ui-ux"]). Skills will be resolved and their content prepended with a separator. Empty array = no prepending.
 
+**WHEN TO USE resume:**
+- Task failed/incomplete → resume with "fix: [specific issue]"
+- Need follow-up on previous result → resume with additional question
+- Multi-turn conversation with same agent → always resume instead of new task
+
 Prompts MUST be in English.`