sapient/oh-my-openagent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2328 from mrosnerr/fix/background-result-collection-wait-behavior

Browse Source 
fix(agents): prevent orchestrator from rushing ahead of background agents
This commit is contained in:
YeonGyu-Kim
2026-03-09 13:23:14 +09:00
committed by GitHub
parent 53337ad68f f1f682c3ab
commit 9e07f1d32b
4 changed files with 16 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/agents/dynamic-agent-prompt-builder.ts
View File

@@ -116,7 +116,7 @@ export function buildExploreSection(agents: AvailableAgent[]): string {
return `### Explore Agent = Contextual Grep
Use it as a **peer tool**, not a fallback. Fire liberally.
Use it as a **peer tool**, not a fallback. Fire liberally for discovery, not for files you already know.
**Use Direct Tools when:**
${avoidWhen.map((w) => `- ${w}`).join("\n")}

11
src/agents/sisyphus.ts
View File

@@ -225,18 +225,17 @@ task(subagent_type="explore", run_in_background=true, load_skills=[], descriptio
// Reference Grep (external)
task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT auth and need current security best practices to choose token storage (httpOnly cookies vs localStorage) and set expiration policy. Find: OWASP auth guidelines, recommended token lifetimes, refresh token rotation strategies, common JWT vulnerabilities. Skip 'what is JWT' tutorials — production security guidance only.")
task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express auth middleware and need production-quality patterns to structure my middleware chain. Find how established Express apps (1000+ stars) handle: middleware ordering, token refresh, role-based access control, auth error propagation. Skip basic tutorials — I need battle-tested patterns with proper error handling.")
// Continue working immediately. System notifies on completion — collect with background_output then.
// WRONG: Sequential or blocking
result = task(..., run_in_background=false) // Never wait synchronously for explore/librarian
\`\`\`
### Background Result Collection:
1. Launch parallel agents \u2192 receive task_ids
2. Continue immediate work
3. System sends \`<system-reminder>\` on each task completion — then call \`background_output(task_id="...")\`
4. Need results not yet ready? **End your response.** The notification will trigger your next turn.
5. Cleanup: Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
2. If you have DIFFERENT independent work \u2192 do it now
3. Otherwise \u2192 **END YOUR RESPONSE.**
4. System sends \`<system-reminder>\` on completion \u2192 triggers your next turn
5. Collect via \`background_output(task_id="...")\`
6. Cleanup: Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
### Search Stop Conditions

9
src/agents/sisyphus/default.ts
View File

@@ -327,10 +327,11 @@ result = task(..., run_in_background=false) // Never wait synchronously for exp
### Background Result Collection:
1. Launch parallel agents → receive task_ids
2. Continue immediate work
3. System sends \`<system-reminder>\` on each task completion — then call \`background_output(task_id="...")\`
4. Need results not yet ready? **End your response.** The notification will trigger your next turn.
5. Cleanup: Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
2. If you have DIFFERENT independent work → do it now
3. Otherwise → **END YOUR RESPONSE.**
4. System sends \`<system-reminder>\` on completion → triggers your next turn
5. Collect via \`background_output(task_id="...")\`
6. Cleanup: Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
### Search Stop Conditions

9
src/agents/sisyphus/gpt-5-4.ts
View File

@@ -246,10 +246,11 @@ Each agent prompt should include:
Background result collection:
1. Launch parallel agents → receive task_ids
2. Continue immediate work
3. System sends \`<system-reminder>\` on completion → call \`background_output(task_id="...")\`
4. If results aren't ready: end your response. The notification triggers your next turn.
5. Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
2. If you have DIFFERENT independent work → do it now
3. Otherwise → **END YOUR RESPONSE.**
4. System sends \`<system-reminder>\` on completion → triggers your next turn
5. Collect via \`background_output(task_id="...")\`
6. Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
Stop searching when: you have enough context, same info repeating, 2 iterations with no new data, or direct answer found.
</explore>`;