mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-23 20:34:49 -06:00
Patrick Buckley
7d6b31e18a
* fix(coord): close gaps an operator's harness shakedown surfaced
Operator-driven shakedown of the coordinator tool surface flagged
five issues; this commit addresses all of them plus the review
findings against the initial fix.
1. Cancelled-mid-stream partial assistant content now carries a
"[generation cancelled before completion]" marker. Without it,
``inspect_workstream`` / ``wait_for_workstream`` callers and the
next coord-LLM turn read the truncated text as a complete answer.
``_cancelled_partial_msg`` no longer ships ``_provider_content``
(Anthropic would otherwise read that lane verbatim and bypass the
marker; partial tool_use blocks could also leak through).
2. ``spawn_workstream`` / ``spawn_batch`` no longer surface the
routing-proxy ``status`` field (always HTTP 200 on the success
path). The tool description claimed it was "lifecycle state at
creation"; code that did ``if result["status"] == "idle"``
silently never matched. Lifecycle state lives on the workstream
row — ``inspect_workstream`` is the read. Tool JSON descriptions
plus docs/coordinator-skills.md and docs/bulk-endpoints.md
examples updated to match.
3. ``inspect_workstream`` not-found error string is bare ("workstream
not found"); the structured ``ws_id`` field carries the queried
id. Pre-fix the error STRING echoed the id back at the caller
who just sent it — redundant and out of step with the rest of the
surface. Cross-tenant + missing rows still return the same shape,
preserving the existence-leak guarantee.
4. ``tasks(...)`` is now rejected when called in a parallel tool
batch. The prior shape relied on a docstring warning ("a list
paralleled with writes can reflect pre-write state") that put
cognitive overhead on every model invocation; turning the silent
footgun into an explicit error means the model only thinks about
the rule the moment it actually breaks it. Warning dropped from
the tasks tool description. ``_PARALLEL_INCOMPATIBLE_TOOLS``
constant in session.py is the extension point for any future
tool with the same read-after-write hazard.
Plus the multi-stage code review's findings against the initial
fix (q-1 / q-2 docs drift, q-3 idiom, q-4 keys-assertion, q-5
duplicate guard) — all addressed in the same pass.
Tests: 4752 pass, +6 net since the pre-fix baseline. Ruff + mypy
clean. Three new tests pin the parallel-batch-rejection behaviour
on tasks (rejected when batched, runs alone, sibling tools
unaffected); existing cancel + spawn + inspect tests updated to
match the new shape.
* fix(coord): close two copilot review gaps on PR 444
Copilot review on PR 444 flagged two follow-ups:
1. Empty-content cancel divergence — when ``GenerationCancelled``
races BEFORE the first content token, the prior shape skipped
``save_message`` and only appended an empty-content msg in
memory. In-memory and storage diverged: a rehydrate would see
nothing in storage but the session would carry an empty
assistant turn. Both branches now persist; on the empty-content
shape the marker becomes the entire message
("[generation cancelled before completion]") so storage matches
the in-memory history.
2. Test stub cleanup — three new tests injected ``ui.approve_tools``
via ad-hoc ``lambda + type: ignore[attr-defined]``. Replaced
with a permissive ``approve_tools`` method on ``_StubUI`` so the
stub matches the SessionUI surface the dispatcher actually
reads. Tests that exercise approval pathways can still override
per-instance.
Tests: 4752 pass. Ruff + mypy clean.
33 lines
2.5 KiB
JSON
33 lines
2.5 KiB
JSON
{
|
|
"name": "spawn_workstream",
|
|
"description": "Create a new child workstream, optionally dispatching an initial message. Kick off a focused sub-task on a different skill / model / node while the coordinator stays in charge. The child runs independently — drive it with send_to_workstream / inspect_workstream / close_workstream. Returns `{ws_id, name, node_id, routing_strategy}`. `routing_strategy` is `rendezvous` (default placement on the live-node set), `target_node` (your hint was honored), or `resume` (rebound to a still-alive prior owner on rehydrate). The returned `node_id` is the spawn-time binding; subsequent ops re-route via rendezvous over the live-node set, so a node join or drop after spawn can shift the active owner. Conversation state lives in storage (the new owner rehydrates lazily). Don't cache `node_id` for long-running callbacks — re-read with inspect_workstream. Lifecycle state (idle / running / etc.) is not in this response — read it via inspect_workstream.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"initial_message": {
|
|
"type": "string",
|
|
"description": "First user message to dispatch to the new workstream. If empty, the workstream is created idle and waits for send_to_workstream."
|
|
},
|
|
"skill": {
|
|
"type": "string",
|
|
"description": "Optional skill name to apply to the new workstream (overrides default skills, may select a model)."
|
|
},
|
|
"name": {
|
|
"type": "string",
|
|
"description": "Optional display name for the new workstream. Auto-generated when empty."
|
|
},
|
|
"model": {
|
|
"type": "string",
|
|
"description": "Optional model alias from the registry. Omit to use the coordinator's default model (or the one the skill prescribes)."
|
|
},
|
|
"target_node": {
|
|
"type": "string",
|
|
"description": "Optional node_id hint. When provided, the routing proxy pins the workstream to that node by generating a ws_id that rendezvous-hashes onto it. Otherwise rendezvous picks deterministically from the live-node set. CAVEAT: pinning is a hard constraint — if the named node has dropped out of the 120s service-registry heartbeat window between your `list_nodes` call and this spawn, the spawn fails with \"No available node for routing\" rather than falling back. Omit `target_node` if you can tolerate landing on any node; pin only when the workload truly requires that specific node's capabilities/region/tenancy."
|
|
}
|
|
},
|
|
"required": []
|
|
},
|
|
"coordinator": true,
|
|
"primary_key": "initial_message"
|
|
}
|