refactor(acp): reduce bridge to automation protocol
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# @deepseek-ai/dsh-command-goal
|
||||
|
||||
Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI and ACP execute it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions.
|
||||
Human-facing `/goal` control over [`ctx.goals`](../goal/README.md). The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI executes it without a model turn. The [human goal-command Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-human-goal-command.md) owns the UX and composition decisions.
|
||||
|
||||
## Command contract
|
||||
|
||||
@@ -30,7 +30,7 @@ The producer injects `commands` and `goals`. A custom app mounts their owners pl
|
||||
name: '@deepseek-ai/dsh-command-goal'
|
||||
```
|
||||
|
||||
The TUI and ACP demo apps enable the complete persisted-goal stack and this command by default; `goals: false` removes both. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation.
|
||||
The TUI app enables the complete persisted-goal stack and this command by default. The ACP automation app enables the domain and model tools without mounting the command registry; `goals: false` removes that stack. The UI-less `agent-spine-demo` requires an explicit `goals: {}` so headless one-shot callers do not silently change from one physical turn to a multi-round operation.
|
||||
|
||||
## Model Experience
|
||||
|
||||
@@ -50,7 +50,7 @@ Command discovery and direct output do not affect the cache. A mutation appends
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **Plain-text interaction only** — the generic command registry has no modal edit form or replacement-confirmation callback; inline edit and explicit clear keep destructive intent deterministic on both TUI and ACP.
|
||||
- **Plain-text interaction only** — the generic command registry has no modal edit form or replacement-confirmation callback; inline edit and explicit clear keep destructive intent deterministic across adapters.
|
||||
- **No per-command round-cap argument** — `defaultMaxGoalRounds` remains deployment config, while a direct human request may ask the model to edit `max_goal_rounds` through the separately authorized goal tool.
|
||||
- **No continuous status widget** — bare `/goal` is the portable observation surface; adapter-specific badges and reconnectable command output remain future UI work.
|
||||
- **TUI and ACP only** — the headless CLI and JSON-RPC adapters do not consume `ctx.commands`. Ordinary human prompts can still authorize the model-facing goal tools when those are composed.
|
||||
- **TUI only in the shipped apps** — the headless CLI, ACP automation, and JSON-RPC adapters do not consume `ctx.commands`. Ordinary prompts can still authorize model-facing goal tools when those are composed.
|
||||
|
||||
Reference in New Issue
Block a user