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

fix(tool-goal): let the model deliver a wrap-up message after a goal-round complete/blocked

Browse Source 
A goal round reporting complete or blocked used to conclude the turn at
the tool result, so the model never spoke after the call and sessions
ended on a bare update_goal card. The terminal update now defers one
plugin-sourced <goal_complete>/<goal_blocked> instruction onto its
result asking for a grounded closing message without further tool
calls; the turn then ends through the ordinary no-tool-calls stop.
Direct-human mutations stay uninstructed. Wording chosen by A/B
sampling on deepseek-v4-pro; one extra request per goal lifecycle.

New keyless ACP snapshot goal-wrapup drives the shipped app through
create -> round one -> autonomous complete and pins the injection, the
same-turn closing message, and the completed turn end.
This commit is contained in:
ZiyaZhang
2026-08-02 05:58:45 -07:00
parent 04d43e3b19
commit 666ef95f81
19 changed files with 334 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/goal/tool-goal/README.md
View File

@@ -14,7 +14,7 @@ All calls are exclusive, so a model-ordered batch observes earlier mutations and
All three canonical values match the compact JSON already rendered to Native callers: `{ goal: null }` or `{ goal: { id, revision, objective, phase, roundsStarted, maxGoalRounds, blockedReason? }, activation }`. Programmatic consumers therefore receive the same domain structure without parsing the rendered JSON.
An autonomous goal round that successfully reports `complete` or `blocked` marks that tool execution with `concludeTurn()` so the physical turn stops after the step. Direct-human mutations never contribute this stop: the assistant may acknowledge the change and concurrent human steering remains available to the loop.
An autonomous goal round that successfully reports `complete` or `blocked` defers one wrap-up context onto that tool result: an injected instruction telling the model to write a final closing message to the user and call no more tools, after which the turn ends through the ordinary no-tool-calls stop. Direct-human mutations receive no instruction: the assistant may acknowledge the change and concurrent human steering remains available to the loop.
## Authority
@@ -61,11 +61,11 @@ Prefix-stable while the plugin scope, configured threshold, and guidance text ar
#### What the model sees
The generated [`get_goal`, `create_goal`, and `update_goal` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-goal). Successful results are compact JSON. Mutation results are followed by the goal domain's raw `<goal_state>` snapshot after the tool batch. `activation` in a result is a live observation and never becomes replay authority.
The generated [`get_goal`, `create_goal`, and `update_goal` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-goal). Successful results are compact JSON. Mutation results are followed by the goal domain's raw `<goal_state>` snapshot after the tool batch. `activation` in a result is a live observation and never becomes replay authority. A goal-round `complete` or `blocked` result additionally injects one `<goal_complete>`/`<goal_blocked>` wrap-up instruction that asks for a grounded closing message to the user without further tool calls.
#### Token effect
Fixed schema cost plus one compact result per call. Mutations also retain the domain snapshot until compaction.
Fixed schema cost plus one compact result per call. Mutations also retain the domain snapshot until compaction. A goal-round terminal update adds the injected wrap-up instruction and one further model request for the closing message — once per goal lifecycle, not per round.
#### KV Cache effect