Commit graph

13 commits

Author SHA1 Message Date
Bryan Helmkamp
b64352dccd
chore: plan 2026-05-06 07:15:18 -04:00
fabro-sh-0530[bot]
79f89165f6
Wire end-to-end steering for running agents (#209)
## Summary
This makes the advertised mid-run steering path real: users can send
append or interrupt steering messages through the API, CLI, and web UI,
and the worker delivers them to live API-mode agent sessions or buffers
them for the next session. The change adds the control protocol, session
interrupt machinery, workflow hub, server route/OpenAPI/client updates,
and UI feedback needed for the whole path.

### Plan Summary
- Add `SteerKind`/`run.steer` wire protocol and `POST /runs/{id}/steer`
- Deliver steers through subprocess JSONL or the in-process
`SteeringHub`
- Support append and interrupt behavior in agent sessions, with bounded
buffering and events
- Expose steering in the CLI/web UI and surface SSE toasts

## Flow

```mermaid
flowchart TB
  UI["CLI / Web UI"] --> API["POST /runs/{id}/steer"]
  API -->|"subprocess transport"| Control["Worker control JSONL"]
  API -->|"in-process transport"| Hub["SteeringHub"]
  Control --> Hub
  Hub -->|"active API sessions"| Session["SessionControlHandle"]
  Hub -->|"no active session"| Pending["Pending buffer"]
  Pending -->|"first future API session"| Session
  Session --> Agent["Session round loop"]
  Agent --> Events["RunEvent stream"]
  Events --> UI
```

## What changed and why

- Agent sessions now expose a lightweight `SessionControlHandle`, drain
steering at the top of each round, and use a replaceable round
cancellation token for interrupts. LLM waits are cancelled promptly,
while tool execution observes cancellation cooperatively so every
committed `tool_use` still gets a matching `tool_result`.
- `SteeringHub` owns active API session registration, broadcast
delivery, pending buffering, FIFO queue caps, and steering
lifecycle/drop events. A completion coordinator closes the
final-response race without introducing a workflow dependency into the
agent crate.
- The server route replaces the 501 stub, validates run state and
best-effort CLI-only steerability, and forwards through either
subprocess control JSONL or the in-process hub. OpenAPI and generated
clients now include the request type.
- The CLI and web UI can send append or interrupt steers. Run detail and
board views open the new composer, and shared SSE subscriptions now
support per-subscriber event callbacks so invalidation and steering
toasts can coexist on one EventSource.

## Review notes

- Steering actors stay on top-level `RunEvent.actor`; event props only
carry steering kind/drop metadata.
- Buffered steers replay as append messages to the first API session
that registers after an empty-active period. Per-stage targeting remains
out of scope.
- CLI-mode agent stages are still not steerable; the server returns a
best-effort 409 when all active agent stages are CLI-mode, while the
worker hub remains the authoritative safety net.
- No persistence or schema migration is required; active and pending
steering state is in memory.
- New tests focus on protocol round-trips, hub buffering/bounds, session
steering-loop behavior, SSE fanout, and basic server rejection paths.

⚒️ Generated with [Fabro](https://fabro.sh)

---------

Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 15:34:16 -04:00
Bryan Helmkamp
4b100d350d
chore: add plan 2026-05-04 16:09:12 -04:00
Bryan Helmkamp
92cfcbde71
chore: update plan 2026-05-04 12:55:19 -04:00
Bryan Helmkamp
e0594a86bd
chore: add plan 2026-05-04 11:12:40 -04:00
Bryan Helmkamp
be0b5829b9
chore: add plan 2026-05-04 11:12:40 -04:00
Bryan Helmkamp
5c60fe8182
chore: plans 2026-05-03 13:10:04 -04:00
Bryan Helmkamp
bfb6bdb25c
fix(cli): bound server readiness probes
Use HTTP health checks with short deadlines for managed server readiness and add finite control-plane request timeouts for CLI/server clients. Keep stream bodies uncapped so SSE attach flows can remain long-lived.
2026-05-02 20:13:18 -04:00
Bryan Helmkamp
ae5ccb5ce2
refactor(workflow): split event module by responsibility
Keep fabro_workflow::event as the public facade while moving event conversion, names, redaction, sink, emitter, stored-field helpers, and StageScope into focused modules. Co-locate the existing event tests with the moved code and update the events strategy docs for the new module layout.
2026-05-02 14:52:10 -04:00
Bryan Helmkamp
2f7aeba417
fix(workflow): preserve exec failure diagnostics
Add bounded redacted exec output tails to failure events while keeping tracing log-safe. Centralize tail projection on ExecResult and thread diagnostics through metadata, setup, devcontainer, and CLI install failures.
2026-05-01 08:45:50 -04:00
Bryan Helmkamp
7e62dae28b
chore: add plans 2026-04-30 15:04:44 -04:00
Bryan Helmkamp
fb51c1485b
docs(plans): add command output streaming and type unification plans
Stage the two 2026-04-30 plan documents: command output streaming with
CAS log storage, and the duplicate-type unification rollup.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 08:36:00 -04:00
Bryan Helmkamp
4a4f0f8548
feat(workflow): emit metadata snapshot events
Add typed metadata snapshot events around init, checkpoint, and finalize archive writes so run logs expose durable metadata timing and failures. Include snapshot accounting, CLI rendering with compatibility-notice suppression, and event documentation.
2026-04-29 19:31:13 -04:00