Files
shockbot/mcp
Colin McDonnell cf94773bf0 modes: make task-list authoring the explicit first step in every mode checklist (#665)
* modes: make task-list authoring the explicit first step in every mode checklist

The system prompt already instructs the agent to author an internal task list
at the start of every run (action/utils/instructions.ts:291), but the rule
lives several hundred tokens above the agent's first decision point and
references the mode's checklist before the agent has it. Compliance is
roughly coin-flip across opus runs — PR #610 dead-air for 9m20s was the
extreme case; my own #664 e2e runs split 1-for-1 on `todowrite` compliance.

Putting the directive *inside* the checklist that `select_mode` returns
co-locates instruction with referent at the moment the agent decides what to
do next. Same vocabulary as the existing rule (`task list`, agent-agnostic;
the harness already maps to `todowrite`/`TodoWrite` per-agent in
agents/opencode.ts and agents/claude.ts). The directive is deliberately
non-prescriptive about list contents — the agent authors items based on the
work it's about to do, not from a hand-shaped template.

Touches all 8 built-in modes and the PlanEdit override:

- Build / AddressReviews / Review / IncrementalReview / Plan / Fix /
  ResolveConflicts / Task: inserts `1. **task list**: create your task list
  for this run as your first action.` and renumbers existing steps.
- action/mcp/selectMode.ts: same insertion in the PlanEdit override checklist.
- All internal step cross-references shifted +1 (`step 5` → `step 6`,
  `skip steps 3–4` → `skip steps 4–5`, etc.) across Review,
  IncrementalReview, and ResolveConflicts modes. One code-comment reference
  in IncrementalReview's preamble updated to match.

Complements #664 (live progress streaming): streaming guarantees the user
sees *something* regardless of compliance; this PR raises the ceiling on
what they see when the agent does comply (clean numbered checklist tracking
through the run instead of just the latest assistant message).

488 action tests pass; typecheck, lint, format all clean.

* postRun: fix stale 'step 7' reference missed during +1 renumbering
2026-05-11 21:57:11 +00:00
..
2025-11-21 14:08:36 -05:00
2026-01-23 06:28:22 +00:00
2026-01-16 18:43:09 +00:00
2026-01-16 18:43:09 +00:00
2026-03-12 05:22:51 +00:00