Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

feat(todo): allow several in_progress todos at once

Browse Source 
Remove the single-in_progress cap from todo_write execute validation and
the durable-log invariant so a task list can mirror genuinely parallel
work (concurrent subagents, background commands). Update the tool
description to instruct marking every actively worked task in_progress,
refresh the tool catalog and keyless snapshot expected outputs, and
record the decision in a new Agent Note superseding the original cap.
This commit is contained in:
Chinesezjc
2026-07-26 02:50:47 +08:00
parent 6f50208ea3
commit 876065a97d
44 changed files with 150 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md
+2 -2
View File
@@ -6,7 +6,7 @@ English | [中文](2026-06-29-todo-write-tool.zh.md)
## Problem
The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active task unambiguous (at most one active, exactly one while work remains), and it gives an interactive host a live progress checklist. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing.
The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active work unambiguous, and it gives an interactive host a live progress checklist. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing.
## Decision
@@ -34,7 +34,7 @@ Each list belongs to the calling agent session, and non-agent calls are rejected
### Validation: the cheap middle
The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content` and more than one `in_progress` task. claude-code leaves single-in-progress to the prompt; oh-my-pi enforces it in code. We take the middle: enforce the cheap invariants that make a plan *coherent* (no blank tasks, no dupes, at most one active), but leave ordering and the discipline of keeping the list current to the model via the tool description. A rejected write returns an `isError` result so the model self-corrects.
The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content`: enforce the cheap invariants that make a plan *coherent* (no blank tasks, no dupes), but leave ordering, active-task discipline, and keeping the list current to the model via the tool description. A rejected write returns an `isError` result so the model self-corrects. The original design also capped the list at one `in_progress` task; that cap was removed for parallel work — the [parallel in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) owns that decision.
## Why no cordis-catalog entry / no `@mode`