ewilliams28/turnstone
1
0
Fork 0
mirror of https://github.com/turnstonelabs/turnstone.git synced 2026-08-25 21:34:47 -06:00
Code Issues Packages Projects Releases Wiki Activity

refactor(tools): remove man, math, and plan_agent built-in tools

Browse Source 
`man` and `math` duplicated capabilities already reachable through
`bash`; `plan_agent` is better expressed as a `task_agent` running a
planning skill, and carried a large amount of special-case machinery
(plan-review gate, refinement loop, per-kind model routing). Removing
all three shrinks the tool surface and cuts per-call token cost.

Also removed, as dead-once-the-tools-are-gone:
- the `math` sandbox executor (`turnstone.core.sandbox`) and its
  `[sandbox]` extra; the eval analyst now runs bash-only
- the read-only `AGENT_TOOLS` sub-agent tool set and the `agent`
  tool-metadata key (`task_agent`/`TASK_AGENT_TOOLS` retained)
- the plan-review protocol end to end: the `on_plan_review` UI hook,
  `resolve_plan`, `POST /v1/api/plan` + `POST /v1/api/route/plan`,
  the `plan_review`/`plan_resolved` SSE events, and their Python SDK /
  TypeScript SDK / OpenAPI / frontend / Discord+Slack bindings
- the `model.plan_alias` / `model.plan_effort` settings and the
  registry `plan_model` / `plan_effort` routing fields

TOOLS 31->28, TASK_AGENT_TOOLS 13->11; COORDINATOR_TOOLS unchanged.

BREAKING CHANGE: removes the `man`, `math`, `plan_agent` tools, the
plan-review SSE/HTTP/SDK surface, and the plan_* model-routing settings
from the experimental 1.6 line.
This commit is contained in:
Patrick Buckley
2026-05-31 19:26:47 -07:00
parent 15b3aad815
commit 110d44b07e
106 changed files with 471 additions and 4393 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/api-reference.md
-37
View File
@@ -455,13 +455,6 @@ Each item in `items` (shared by `tool_info` and `approve_request`):
| `cache_creation_tokens` | int | Tokens written to prompt cache (Anthropic) |
| `cache_read_tokens` | int | Tokens served from prompt cache (Anthropic + OpenAI) |
**`plan_review`** -- the model is proposing a plan and wants feedback. The
client must respond via `POST /v1/api/plan`.
```json
{"type": "plan_review", "content": "Step 1: ...\nStep 2: ..."}
```
**`info`** -- an informational message (e.g. command output).
```json
@@ -779,36 +772,6 @@ automatically approved without prompting.
---
### `POST /v1/api/plan`
Responds to a plan review dialog. The SSE stream must have previously sent a
`plan_review` event for the given workstream.
**Request body:**
```json
{"feedback": "", "ws_id": "abc123"}
```
| Field | Type | Required | Description |
|------------|--------|----------|---------------------------------------------------------|
| `feedback` | string | yes | Feedback text; empty string means approval |
| `ws_id` | string | yes | Target workstream ID |
To approve the plan, send an empty string for `feedback`. To reject or request
changes, send a non-empty feedback string (e.g. `"reject"` or specific
revision instructions).
**Response:**
```json
{"status": "ok"}
```
**Error:** `404` with `{"error": "Unknown workstream"}` if `ws_id` is invalid.
---
### `POST /v1/api/command`
Executes a slash command in the given workstream.