fix(prompt): simplify pickup follow-through

[salman1993]

Why

The base prompt prescribed a todo lifecycle for every task needing follow-up tools, which added control calls even for work completed in one turn. This keeps the important behavioral contract—continue after publishing pickup—without prescribing the mechanism.

What

• Replace the 40-word todo lifecycle with a concise pickup follow-through rule
• Preserve the requirement to publish the outcome or blocker before stopping

Risk Assessment

Low to medium — this changes managed-agent instructions, not runtime code. The terminal benchmark covers single-turn task completion but does not cover restart, compaction, or long-lived multi-turn recovery.

References

• Builds on the prompt simplification in Remove Startup Recovery section in base prompt #6161
• Benchmark setup: GPT 5.6 Terra at high effort; the same 11-task Terminal-Bench 2.1 slate; four concurrent trials; 4 CPU and 8 GiB per trial; 3× timeout

Prompt	Pass	Active-h	Median active	Tool calls
PR 6161 baseline	22/22	0.3438	0.91 min	216
Benchmarked 14-word rule	22/22	0.2926	0.75 min	198

The benchmarked rule used 14.9% less active time, 16.9% lower median active time, and 8.3% fewer tool calls. Across the screen and confirmation runs it passed 33/33 trials with every completion report present; results are directional because model and tool behavior is stochastic.

---

Update Aug 18, 10:47 EDT: Expanded the completion outcomes following review feedback.

• The follow-through rule now covers a verified result, blocker, or key decision or information that needs to be surfaced.
• The benchmark was not rerun; the table reflects the prior 14-word formulation. This is a completion-taxonomy clarification, not a return to a prescribed todo mechanism.

Generated with Codex

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4e9b1da0e6

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Preserve the todo guard after publishing pickup

For managed buzz-agent sessions, when the model publishes a pickup and later emits end_turn before sending the result or blocker—the failure the _Stop lifecycle hook is intended to catch—this replacement no longer requires any open todo, so buzz-dev-mcp returns no objection and the harness accepts the early stop. The same empty state leaves _PostCompact with no durable work marker to re-inject after a context handoff. Long-running tasks can therefore strand the user with only the pickup message; retain the open todo until completion or provide an equivalent mechanically enforced marker, and exercise this multi-round workflow rather than relying only on the single-turn benchmark.

AGENTS.md reference: AGENTS.md:L20-L24

Useful? React with 👍 / 👎.