mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-09-19 00:03:30 +00:00
1959 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Bryan Helmkamp
|
f35dccecab
|
Finalize unfinished stages after run failure | ||
|
Bryan Helmkamp
|
c19cedaede
|
Link unconfigured providers to prefilled secret form
On /settings/models, unconfigured providers now offer "Add secret →" alongside "Get API key →", deep-linking to /settings/secrets/new with the expected vault secret name prefilled. Driven by a new `expected_secret_name` field on the Provider API, derived from the first vault credential in the catalog so the suggestion stays in sync with the catalog instead of being hardcoded on the frontend. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
fabro-sh-0530[bot]
|
04e169ef79
|
Add POST /api/v1/runs/delete batch delete endpoint (#382)
## Summary
Adds a fail-soft batch delete endpoint (`POST /api/v1/runs/delete`) that
mirrors the existing archive/unarchive batch pattern, processes 1–250
run IDs independently, and returns per-item outcomes with an aggregate
summary. Existing `DELETE /api/v1/runs/{id}` behavior is unchanged.
### Plan Summary
- **OpenAPI-first**: new
`BatchDeleteRunsRequest/Response/Result/Summary` schemas added to the
spec; Rust (`fabro-api`) and TypeScript (`fabro-api-client`) clients
regenerated.
- **Delete internals refactored**: `DeleteRunOutcome` gains `Deleted`
and `AlreadyAbsent` variants (replacing the old `NoContent`);
`delete_run_internal` and its helpers now return `Result<_, ApiError>`
instead of `Result<_, Response>`, enabling both the single-delete
handler and the new batch handler to reuse the same logic.
- **Batch handler**: `batch_delete_runs` in `lifecycle.rs` validates the
request (reusing the generalized `validate_batch_run_ids`), loops over
IDs, and assembles `BatchDeleteRunsResult` items mapping
`ApiError::status()` to outcome strings (`conflict`, `error`).
- **Web helper**: `deleteRuns` added to `run-actions.ts` alongside
`archiveRuns`/`unarchiveRuns`, with the same `as unknown as` cast needed
for the openapi-generator `Set<string>` quirk.
- **Tests**: six new server integration tests cover ordered results,
mixed outcomes without rollback, force deletion, sandbox preservation
handoff, pre-mutation validation rejection, and auth gating.
### Key design decisions
**`POST /runs/delete` not `DELETE /runs`** — JSON request bodies on
`DELETE` are poorly supported by proxies and HTTP clients; the existing
batch lifecycle endpoints already use JSON-body `POST` actions.
**`already_absent` counts as success** — consistent with single-delete
semantics where `204` means "deleted or already absent"; callers doing
cleanup don't need to special-case missing IDs.
**`force` is batch-wide** — callers needing mixed force behavior issue
separate requests; this keeps the request schema simple.
**`SandboxDeleteOutcome` internal enum** — introduced alongside
`DeleteRunOutcome` to cleanly separate the sandbox-layer result
(absent/cleaned/preserved) from the top-level outcome that callers see,
avoiding a leaky intermediate type.
### Fabro Details
<details>
<summary>Ran 8 stages in 41m 52s for $13.37</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 3s | – | 0 |
| preflight_lint | 2m 17s | – | 0 |
| implement | 15m 12s | $8.10 | 0 |
| simplify_opus | 8m 54s | $3.30 | 0 |
| simplify_gpt | 3m 54s | $1.97 | 0 |
| verify | 9m 0s | – | 0 |
| **Total** | **41m 52s** | **$13.37** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && { command -v rg >/dev/null 2>&1 || { echo 'rg is required for verify'; exit 127; }; } && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
Bryan Helmkamp
|
846d1e91af
|
Polish stage insights sidebar
- Track which MCP servers the agent invoked. New `invoked: bool` on `McpServerProjection` (OpenAPI + Rust type + generated TS client), set by the projector when an `AgentToolStarted` event has an `mcp__<server>__*` tool_name. UI shows `used/total` in the section header, replaces the tool count with `used` on invoked rows, and dims rows that weren't invoked. Sticky across status re-reads. - Quiet noisy context-window warnings. When the snapshot's total is provider-authoritative (ProviderApiScaledBreakdown or ResponseUsageScaledBreakdown), drop local-estimator warning codes from the snapshot — they imply the user-facing total is wrong when it isn't. Also dedupe by code so a 35-turn conversation with opaque reasoning blocks no longer surfaces 35 copies of the same warning. - Reword the legitimately-local warnings. "opaque provider context estimated from JSON" → "Some content couldn't be precisely tokenized; total is approximate." Same treatment for the media, provider-options, and whole-request local-estimate messages. - Rename the sidebar header from "INSIGHTS" to "AGENT" to better describe what it shows. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
deb8f27a27
|
Add stage insights sidebar to agent stage pages
Renders a second left sidebar on /runs/<id>/stages/<agent-stage> with todos, color-coded context-window usage and breakdown, skills, MCP servers, and permission level. Data comes from the existing StageProjection and the context-window endpoint added in #378; no API changes. Also set permission_level to Full on workflow agent SessionOptions — workflow agents run with no tool_access_policy and expose the full tool registry, so Full is the honest report and avoids "Unknown" rendering in the new sidebar. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
fabro-sh-0530[bot]
|
8ceb246b5a
|
feat: Add batch archive/unarchive API endpoints and update web bulk act… (#380)
## Summary
The web UI previously issued one archive/unarchive HTTP request per
selected run. This PR adds `POST /api/v1/runs/archive` and `POST
/api/v1/runs/unarchive` endpoints that process up to 250 runs in a
single fail-soft, non-transactional request, then wires the web
bulk-action toolbar and board column menu to use them.
### Plan Summary
- **OpenAPI contract** — four new schemas (`BatchRunLifecycleRequest`,
`BatchRunLifecycleResponse`, `BatchRunLifecycleResult`,
`BatchRunLifecycleSummary`) and two new paths; Rust and TypeScript
clients regenerated.
- **Server handlers** — `batch_archive_runs` / `batch_unarchive_runs`
behind `RequiredUser`; full request validation (empty, >250, duplicates,
unparseable IDs) before any mutation; per-item outcome mapping
(`archived`, `already_archived`, `unarchived`, `not_archived`,
`conflict`, `not_found`, `error`).
- **Frontend helpers** — `archiveRuns` / `unarchiveRuns` wrappers in
`run-actions.ts`; single-run helpers unchanged.
- **UI integration** — `BulkActionToolbar` and `ColumnActionsMenu`
replaced `Promise.allSettled` fan-out with one batch call; new
`summarizeBatchLifecycleAction` helper drives toast copy for
all-success, partial, and all-failure cases.
## Key Design Decisions
**Fail-soft `200` for valid batches.** A batch where some items fail is
still a successfully *processed* request; the per-item `ok` flag and
`summary` counts communicate individual outcomes without requiring the
caller to handle HTTP errors for partial failures. Request-level
problems (bad IDs, empty list) still return `400`.
**`RequiredUser` only.** Batch endpoints accept any-run mutations from a
request body, so a run-scoped worker token must not be accepted. This is
enforced at the handler level, separate from existing single-run
lifecycle routes.
**Request validation before any mutation.** Empty list, >250 IDs,
duplicate IDs, and unparseable IDs all return `400` before touching any
run — avoiding partial mutation surprises from invalid input.
**Idempotent outcomes are successes.** `already_archived` (archive of an
already-archived run) and `not_archived` (unarchive of a terminal
non-archived run) both set `ok=true`. This matches the existing
single-run semantics and avoids spurious failures in retry scenarios.
**`ask_fabro_readiness` hoisted out of the per-item loop.** Readiness
resolution involves LLM credential work; it's identical for every run in
the batch, so it's resolved once before the loop and shared via
`&AskFabroReadiness`.
**`uniqueItems: true` / `Set<string>` workaround.** The OpenAPI
generator maps `uniqueItems` arrays to `Set<T>` in TypeScript, but the
HTTP wire format is still a JSON array. The frontend helper casts
through `unknown` to send an array so Axios serializes correctly.
### Fabro Details
<details>
<summary>Ran 8 stages in 47m 48s for $23.53</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 4s | – | 0 |
| preflight_lint | 2m 16s | – | 0 |
| implement | 20m 17s | $15.09 | 0 |
| simplify_opus | 10m 27s | $6.18 | 0 |
| simplify_gpt | 3m 58s | $2.25 | 0 |
| verify | 8m 14s | – | 0 |
| **Total** | **47m 48s** | **$23.53** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && { command -v rg >/dev/null 2>&1 || { echo 'rg is required for verify'; exit 127; }; } && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
fabro-sh-0530[bot]
|
39fa73d5e2
|
Add context-window snapshot API for agent stages (#378)
## Summary
Adds a best-effort `GET
/api/v1/runs/{id}/stages/{stageId}/context-window` endpoint that exposes
model-visible input-token usage, broken down by category (system prompt,
tools, MCP tools, skills, memory, conversation, other). The endpoint
degrades gracefully: it returns a stored projection snapshot when the
stage is inactive, and `available: false` when no snapshot has ever been
observed rather than surfacing count gaps as HTTP errors.
### Plan Summary
- **Unit 1** – OpenAPI schemas (`StageContextWindow`,
`StageContextWindowProjection`, breakdown/enum types) and generated Rust
+ TypeScript clients, with `fabro-api` build-time type replacements
pointing at the hand-written `fabro-types` structs.
- **Unit 2** – `ToolSource` enum on `RegisteredTool` (Native / Mcp /
Skill) + `ToolDefinitionWithSource`; new `context_window.rs` builder in
`fabro-agent` that assembles a content-free category breakdown at
request-assembly time; `fabro-llm::token_count` narrow public helpers
(`estimate_message_tokens`, `estimate_tool_definition_tokens`,
`estimate_request_control_tokens`).
- **Unit 3** – `AgentEvent::ContextWindowSnapshot` carries a
`StageContextWindowProjection`; the session emits a local snapshot
immediately, then a provider-scaled replacement (or
response-usage-scaled replacement) asynchronously; fingerprinting
prevents double-counting the same request.
- **Unit 4** – Server endpoint (stubbed routing; full handler targets a
follow-up) returning the latest projected snapshot.
- **Unit 5** – `queryKeys.runs.stageContextWindow`,
`useRunStageContextWindow` hook, and SSE invalidation for
`agent.context_window.snapshot` and all stage-lifecycle events.
### Key design decisions
**Agent-side counting, not server-side.** The exact `fabro_llm::Request`
only exists inside the active agent session. Rather than moving raw
prompt/message content into server-managed state, the session counts the
request it already has and emits content-free projection events. The
HTTP endpoint just reads the latest durable snapshot.
**Hybrid category ownership.** `fabro-agent` owns the category taxonomy
(it sees memory documents, skills, MCP registration, and session
history); `fabro-llm` exposes narrow estimation helpers. Neither crate
leaks the other's concerns.
**Provider count is async and non-blocking.** A spawned task calls
`Client::count_input_tokens(..., PreferProvider)` with a clone of the
request. It is cancelled via `close_token` when the session closes.
Failures produce a warning on the snapshot, not a stage error.
**`available: false` instead of 4xx for known-but-unobserved stages.**
The sidebar needs stable empty states; HTTP errors only mean the run or
stage doesn't exist.
```mermaid
flowchart TB
A[Session::build_request] --> B[build_local_snapshot\nLocalEstimate]
B --> C[emit ContextWindowSnapshot]
C --> D{provider count\nspawned task}
D -- success --> E[scaled_snapshot\nProviderApiScaledBreakdown]
D -- failure --> F[warning appended to local snapshot]
E --> G[emit ContextWindowSnapshot]
G --> H[run_state reducer\nupdates StageProjection.context_window]
F --> H
H --> I[GET context-window endpoint\nreturns projection]
```
**`ToolSource` on every `RegisteredTool`.** All 20+ `make_*_tool` call
sites are updated to set `ToolSource::Native`; MCP tools get
`ToolSource::Mcp { server_name }` at registration time;
`make_use_skill_tool` gets `ToolSource::Skill`. A parallel
`definitions_with_source_for_policy` method preserves existing
`definitions_for_policy` behaviour unchanged.
### Fabro Details
<details>
<summary>Ran 8 stages in 90m 57s for $70.01</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 1m 59s | – | 0 |
| preflight_lint | 2m 11s | – | 0 |
| implement | 45m 14s | $48.47 | 0 |
| simplify_opus | 25m 50s | $18.29 | 0 |
| simplify_gpt | 6m 12s | $3.25 | 0 |
| verify | 8m 59s | – | 0 |
| **Total** | **90m 57s** | **$70.01** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
3fb4b5bc1b
|
Add output_schema validation with same-context repair for agent and pro… (#374)
## Summary
Adds `output_schema` and `output_retries` node attributes that validate
structured LLM output and perform corrective repair turns inside the
same conversation context before failing the node. Also adds sortable
columns (Repo, Title, Workflow, Changes) to the runs list view and hides
the pager when the result set is small.
### Plan Summary
- **Task 1**: `Node::output_schema()` / `Node::output_retries()`
accessors in `fabro-types`, with `@`-prefix file-reference support in
static validation and file inlining.
- **Task 2**: New `handler/structured_output.rs` module —
`OutputSchemaKind` (Routing / JsonSchema), balanced JSON scanning,
validation, repair-message generation, `apply_validated_output`, and
`exhausted_failure_outcome`.
- **Task 3**: `extract_status_fields` moved to `structured_output.rs`;
agent routing fallback chain (response → `status.json` → last file
touched) preserved and delegated to `validate_agent_output_sources`.
- **Task 4/5**: `one_shot` (prompt) and `run` (agent) both loop over LLM
calls, appending the prior assistant response and a corrective user turn
on validation failure, up to `output_retries` times.
- **Task 6**: ACP backend rejects `output_schema` immediately with a
clear error before launching any process.
- **Task 7**: `outputs.mdx` and `dot-language.mdx` updated with
attribute docs, repair semantics, and `output.{node_id}` context key.
## What changed and why
```mermaid
TB
graph
A[Node attrs\noutput_schema / output_retries] --> B[structured_output.rs\nparse / validate / repair]
B --> C{OutputSchemaKind}
C -->|Routing| D[validate routing fields\n→ outcome routing]
C -->|JsonSchema| E[jsonschema validator\n→ context_updates.output.node_id]
B --> F[exhausted_failure_outcome\nterminal, non-retryable]
G[prompt handler\none_shot loop] --> B
H[agent handler\nrun loop + session.process_input] --> B
I[ACP backend] -->|output_schema present| J[Validation error\nno process launched]
```
**`output_schema="routing"`** tightens existing loose routing
extraction: malformed fields now fail validation and trigger a repair
turn rather than being silently ignored. The fallback priority (response
text → `status.json` → last file touched) is preserved but only for the
`NoJsonObject`/`NoRelevantJsonObject` error kinds that allow it.
**Custom schemas** (`@path` inlined to JSON Schema) validate the last
JSON object in the response against a precompiled
`jsonschema::Validator`. On success, the parsed value is stored at
`output.{node_id}` in `context_updates` for downstream nodes.
**Repair loop** — prompt nodes keep the prior assistant response in the
message list and append a corrective user message; agent API sessions
call `session.process_input` on the live session. Both paths aggregate
token usage across all turns. Exhausting `output_retries` returns a
terminal `OutputSchemaValidation` error (non-retryable, deterministic
failure category) that does not consume `max_retries`.
**ACP guardrail** rejects `output_schema` before spawning any
subprocess, with a clear `"output_schema is not supported with
backend=\"acp\" in this release"` message.
The `one_shot` refactor also extracted `complete_one_shot_request` and
`OneShotCompletion` to separate fallback-chain logic from the repair
loop, removing duplication.
### Fabro Details
<details>
<summary>Ran 9 stages in 74m 9s for $31.92</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 16s | – | 0 |
| preflight_lint | 2m 28s | – | 0 |
| implement | 24m 59s | $17.96 | 0 |
| simplify_opus | 16m 36s | $9.95 | 0 |
| simplify_gpt | 3m 20s | $1.75 | 0 |
| verify | 6m 29s | – | 0 |
| fixup | 17m 13s | $2.26 | 0 |
| **Total** | **74m 9s** | **$31.92** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Fabro <fabro@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
def37896cd
|
Expose PermissionLevel on StageProjection and add sortable run columns (#373)
## Summary
Two independent additions landed together: surfacing `PermissionLevel`
on `StageProjection` (the primary goal), and making four previously
unsortable run-list columns (`repo`, `title`, `workflow`, `changes`)
sortable.
## Permission Level on StageProjection
`PermissionLevel` (`read-only | read-write | full`) was already resolved
at session start inside `fabro-agent` but never reached the API. This
wires it through the existing `agent.session.activated` event rather
than introducing a new event.
The data flow:
```mermaid
graph TB
A[SessionOptions.permission_level] -->|set at CLI build_tool_approval| B[Session.permission_level]
B -->|read in api.rs| C[ActivationLeaseOptions.permission_level]
C -->|emitted as| D[Event::AgentSessionActivated.permission_level]
D -->|convert.rs| E[EventBody::AgentSessionActivated.permission_level]
E -->|run_state.rs apply_event| F[StageProjection.permission_level]
F -->|OpenAPI + TS client| G[API consumers]
```
Key decisions:
- **No new event or type.** `PermissionLevel` is reused from
`fabro_types::session` directly; `AgentSessionActivatedProps` gains one
optional field with `skip_serializing_if`, so older persisted events
deserialize cleanly to `None`.
- **`Option<PermissionLevel>` on `StageProjection`** follows the same
pattern as `provider_used` — agent stages populate it, non-agent stages
leave it `None`. No migration required.
- **`AgentSessionActivatedProps` is now a progenitor type replacement**
so the API crate and the canonical type stay in sync (verified by the
new `agent_session_activated_props_round_trip` test).
### Plan Summary
- `fabro-agent` `config.rs` / `session.rs` — store and expose
`permission_level` on `SessionOptions`
- `fabro-types` `run_event/agent.rs` — add field to
`AgentSessionActivatedProps`
- `fabro-types` `run_projection.rs` — add field to `StageProjection`
- `fabro-workflow` `api.rs` / `activation_lease.rs` / `convert.rs` /
`events.rs` — thread the value to the emission site
- `fabro-store` `run_state.rs` — fold into projection on
`AgentSessionActivated`, plus new unit test
- OpenAPI schema, `fabro-api` build.rs, TS client — all
regenerated/updated
## Sortable Run Columns
`repo`, `title`, `workflow`, and `changes` columns were rendered as
plain `<th>` elements with no sort affordance. They now use `SortHeader`
in the frontend, the server-side `RunsSortKey` enum gains the four
variants, and the OpenAPI `ListRunsSortEnum` and TS client enum are
extended to match.
Sort helpers (`run_repo_key`, `run_title_key`, `run_workflow_key`,
`run_changes_total`) normalize to lowercase strings / integer totals and
compose with the existing stable ULID tiebreak.
### Fabro Details
<details>
<summary>Ran 9 stages in 53m 42s for $18.48</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 14s | – | 0 |
| preflight_lint | 2m 29s | – | 0 |
| implement | 20m 37s | $11.87 | 0 |
| simplify_opus | 8m 0s | $3.61 | 0 |
| simplify_gpt | 5m 11s | $2.50 | 0 |
| verify | 4m 48s | – | 0 |
| fixup | 9m 56s | $0.50 | 0 |
| **Total** | **53m 42s** | **$18.48** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: fabro-bot <fabro-bot@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
c81fcc2a27
|
Auto-migrate legacy [run.sandbox] config files to named-environment syn… (#375)
## Summary
On startup, Fabro now detects confidently migratable pre-v1.0
`[run.sandbox]` config files and rewrites them in-place to the
`[run.environment]` + `[environments.default]` named-environment syntax.
The original file is preserved as a sibling
`*.legacy-sandbox-migration.bak` before any write. Unsupported or
ambiguous keys produce a targeted error listing exact key paths rather
than a generic TOML unknown-field failure.
### Plan Summary
- **New module** `legacy_sandbox_migration.rs` owns all detection,
rewriting, backup logic, and unsupported-key diagnostics — isolated so
it can be deleted before v1.0.
- **`load.rs` hook** catches parse failures on file loads and attempts
migration before re-raising the original error, leaving in-memory
`SettingsLayer` parsing strict and unchanged.
- **Field mappings** cover Daytona (snapshot, volumes, labels,
lifecycle, `auto_stop_interval`) and Docker (image, `memory_limit`,
`cpu_quota` divisible by 100 000, `skip_clone`).
- **Ambiguity guard** rejects files that already contain
`[run.environment]` or `[environments.default]` alongside
`[run.sandbox]`.
- **Docs** add a `<Warning>` block to `environments.mdx` and a new
`2026-05-23.mdx` changelog entry.
This PR also bundles two unrelated improvements that landed in the same
branch: additional sort keys (`repo`, `title`, `workflow`, `changes`)
for the runs list API and UI, and a test isolation fix in `user.rs` that
wraps path assertions in `with_var` to avoid `FABRO_HOME` leakage.
### Migration flow
```mermaid
flowchart TB
A[load_settings_path] --> B{parse SettingsLayer}
B -- ok --> G[resolve paths / return]
B -- err --> C{migrate_settings_path}
C -- no legacy sandbox --> D[return original parse error]
C -- has new env config --> E[error: ambiguous, manual fix required]
C -- unsupported keys --> F[error: list unsupported keys]
C -- success --> H[write .bak, rewrite file, warn]
H --> I[parse migrated SettingsLayer]
I --> G
```
### Fabro Details
<details>
<summary>Ran 0 stages in 53m 26s for $16.82</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| **Total** | **53m 26s** | **$16.82** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Fabro <fabro@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
Bryan Helmkamp
|
54a23707d9
|
Add event append race regression test (#379)
## Summary
Adds a black-box server API regression test for the per-run event append
race observed as projection cache sequence gaps and non-contiguous event
streams.
The test creates a run through the public API, simulates a server
restart with a fresh AppState over the same backing object store, then
concurrently appends events through `POST /api/v1/runs/{id}/events`. The
expected contract is that all appends succeed and the resulting event
sequence is durable and contiguous.
## Test Plan
- `cargo nextest run -p fabro-server --features test-support --test it
concurrent_event_appends_after_restart_keep_projection_cache_contiguous`
Expected current result: fails RED, demonstrating the existing race.
Example observed failure showed duplicate/missing seqs such as `[1, 2,
3, 3, 4, 4, ...]` instead of a contiguous sequence through 66.
|
||
|
Bryan Helmkamp
|
1c2abbb2f5
|
Configure implement-plan sandbox tooling (#377)
Fixes implement-plan runs failing at verify time when cloned sandboxes lack Git identity, and prevents the verify forbidden-pattern scan from being silently skipped when `rg` is unavailable. ## Changes - Install `ripgrep` in the Fabro Daytona image and bump the snapshot ref to `fabro-v12` so Daytona rebuilds it. - Configure repository-local Git `user.name` and `user.email` from `run.git.author` during workflow initialization before lifecycle setup commands or workflow stages run. - Make the implement-plan verify stage fail explicitly if `rg` is missing. ## Validation - `cargo test -p fabro-workflow configure_sandbox_git_identity_uses_run_author --quiet` - `cargo +nightly-2026-04-14 fmt --check --all` - `cargo +nightly-2026-04-14 clippy -p fabro-workflow --all-targets -- -D warnings` - `cargo run -p fabro-cli -- validate .fabro/workflows/implement-plan/workflow.fabro` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) |
||
|
Bryan Helmkamp
|
eda9e8855e
|
Make runs list Repo, Title, Workflow, and Changes columns server-side sortable
Extend the RunsSort enum and sort_runs() with case-insensitive ordering for repo, title, and workflow names, and total line changes (additions + deletions) for changes. Swap the corresponding `<th>` cells in the runs list view to `<SortHeader>` so every column can toggle asc/desc. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
fabro-sh-0530[bot]
|
dbe3e3966d
|
Migrate sandbox config to named environments; add InterviewOption metad… (#372)
## Summary
Two related changes land together: the sandbox configuration surface is
replaced with a named-environment model, and `InterviewOption` gains
`description` and `preview` fields needed for the mid-stage agent
interview tools described in the plan.
## What changed
### Named environments (was `[run.sandbox]`)
`[run.sandbox]` and its provider-specific sub-tables
(`[run.sandbox.daytona]`, `[run.sandbox.docker]`) are replaced by a
two-level model:
- **`[environments.<slug>]`** — reusable catalog entries with a unified
shape: `provider`, `image`, `resources`, `network`, `lifecycle`,
`labels`, `volumes`, `env`.
- **`[run.environment] id = "<slug>"`** — selects which environment a
run uses.
- **`[run.environment.<field>]`** — sparse run-level overrides applied
on top of the selected environment.
The OpenAPI schema drops `RunSandboxSettings`, `DaytonaSettings`,
`DaytonaSnapshotSettings`, `DaytonaNetworkLayer`, and `DockerSettings`
in favour of `EnvironmentSettings`, `RunEnvironmentSettings`, and the
new sub-schemas (`EnvironmentImageSettings`,
`EnvironmentResourcesSettings`, `EnvironmentNetworkSettings`,
`EnvironmentLifecycleSettings`, `EnvironmentVolumeSettings`). The
`--sandbox` CLI flag becomes `--environment`.
All docs, example configs, `.fabro/project.toml`, and the
automation-detail / run-settings UI panels are updated to the new shape.
The run-settings page renames "Sandbox" → "Environment" and reads from
the new field paths.
### `InterviewOption` metadata fields
`description` and `preview` are added to the canonical `InterviewOption`
type (OpenAPI, helpers.ts, interview-dock, human-qa renderer). Both are
treated as untrusted model-authored text — stored and displayed as plain
strings, never rendered as HTML. The `interview-dock` test asserts that
raw HTML in `preview` is not rendered. Option `description` is shown as
secondary text under the label in choice and multi-select buttons.
### `StageModelUsage` projection
`provider_used` on `RunStageInfo` and stage projections is promoted from
a freeform object to a typed `StageModelUsage` schema (with `mode`,
`provider`, `model`, `reasoning_effort`, `speed`). The
`extractStageModel` event-scraping helper is replaced by
`formatStageModelUsageLabel` and `stageModelUsageTitle`, which work
directly from the projection field. The `Stage` interface gains
`providerUsed` and the `EventsToolbar` consumes it.
### Other schema additions
`ReasoningEffort` enum, `small_default` on model info,
`SubAgentProjection`/`SkillsProjection`/`McpServerProjection` inline in
stage projections, and `TodoListProjection` moved from the run-state
top-level `todos_by_list` map into per-stage `todos`.
### Plan summary
- Replace `[run.sandbox]` config with `[environments.<slug>]` +
`[run.environment]` selection across config, OpenAPI, UI, and docs.
- Extend `InterviewOption` with `description` and `preview`; render
`description` in choice/multi-select buttons.
- Promote `provider_used` to a typed `StageModelUsage` schema; drop
event-scraping in favour of the projection field.
- Add `ReasoningEffort`, `small_default`, subagent/skills/MCP
stage-projection schemas to OpenAPI.
### Fabro Details
<details>
<summary>Ran 9 stages in 93m 2s for $48.56</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 4s | – | 0 |
| preflight_lint | 2m 16s | – | 0 |
| implement | 39m 28s | $35.95 | 0 |
| simplify_opus | 22m 6s | $8.66 | 0 |
| simplify_gpt | 7m 18s | $1.66 | 0 |
| verify | 6m 33s | – | 0 |
| fixup | 12m 34s | $2.29 | 0 |
| **Total** | **93m 2s** | **$48.56** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (11 nodes and 14
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="git fetch origin main 2>&1 && git merge --no-edit --no-stat origin/main 2>&1 && cargo +nightly-2026-04-14 fmt --all 2>&1 && cargo dev docs refresh 2>&1 && cargo +nightly-2026-04-14 fmt --check --all 2>&1 && ! rg -n 'AuthMode::Disabled|RunAuthMethod|RunSubjectProvenance|\bActorRef\b|\bActorKind\b|AuthenticatedSubject|AuthenticatedService|AuthorizeRunScoped|AuthorizeRunBlob|AuthorizeStageArtifact|AuthorizeCommandLog|auth_method\s*==\s*\"disabled\"' lib/crates apps lib/packages docs/public/api-reference/fabro-api.yaml 2>&1 && cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --workspace --status-level slow --profile ci 2>&1 && cargo dev docs check 2>&1 && bun install --frozen-lockfile 2>&1 && (cd apps/fabro-web && bun run typecheck) 2>&1 && (cd apps/fabro-web && bun run test) 2>&1 && (cd lib/packages/fabro-api-client && bun run typecheck) 2>&1 && cargo dev build -- -p fabro-cli --release 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all format, clippy, Rust test, docs, TypeScript typecheck/test, and build failures.", max_visits=3]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> exit [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Fabro <fabro@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
f73f2a53f3
|
Replace queued with pending/runnable and add approval flow (web + API s… (#371)
## Summary
Replaces the single `queued` pre-execution state with explicit `pending`
and `runnable` states, and wires approve/deny actions for
parent-generated child runs that require human approval before they can
execute. This diff covers the web UI and OpenAPI spec layers of that
change.
## What changed
**Run status model**
- `queued` is removed from all TypeScript types, display maps, column
routing, and tests.
- `pending` (awaiting approval) and `runnable` (eligible for the
scheduler) replace it as distinct board columns and `RunStatus` variants
with their own labels and colors (`runnable` gets cyan; `pending` stays
muted).
**Approval actions**
- New `approveRun` / `denyRun` API calls in `run-actions.ts` invoke the
new `POST /runs/{id}/approve` and `POST /runs/{id}/deny` endpoints.
- `canApprove` predicate requires both `status.kind === "pending"` and
`lifecycle.approval?.state === "pending"` — a run whose status is
pending but has no approval record does not expose the action.
- `useApproveRun` / `useDenyRun` mutations in `mutations.ts` follow the
same pattern as `useCancelRun`.
- `ActionsMenu` in `run-detail.tsx` gains Approve (lifecycle group) and
Deny (destructive group) menu items.
**Board and event plumbing**
- `columnForStatus` now routes `pending → pending column` and `runnable
→ runnable column`; `submitted` stays in the pending column.
- `BOARD_STATUS_EVENTS` and `RUN_SUMMARY_EVENTS` replace `run.queued`
with `run.start_requested`, `run.pending`, `run.approved`, `run.denied`,
and `run.runnable`.
- The `pending` column is hidden when empty (same behaviour the old
`queued` column had).
**Waterfall phases (`run-phases.ts`)**
- `queued` phase is removed; `pending` and `runnable` phases are added
in order.
- The submitted phase closes at `run.start_requested` rather than
`run.queued`.
- Each phase derives its timestamps from its own event rather than a
single `firstTs` lookup, making multi-phase pre-execution timelines
accurate.
**OpenAPI spec**
- `POST /api/v1/runs/{id}/approve` and `POST /api/v1/runs/{id}/deny`
endpoints added with 200/404/409 responses.
- `startRun` description updated to describe the pending/runnable
branching behaviour.
- `cancelRun` description updated to reference `pending`/`runnable`
instead of `queued`.
### Plan Summary
- **Task 3** (OpenAPI schema additions for approve/deny endpoints) —
complete in this diff.
- **Task 6** (Web UI surfaces: board columns, run-detail actions,
waterfall phases, event subscriptions) — complete in this diff.
- **Task 7** (doc cleanup: references to `queued` replaced in plans,
brainstorms, and QA docs) — complete in this diff.
### Fabro Details
<details>
<summary>Ran 9 stages in 127m 37s for $104.98</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 2m 15s | – | 0 |
| preflight_lint | 2m 29s | – | 0 |
| implement | 92m 10s | $91.53 | 0 |
| simplify_opus | 18m 35s | $10.65 | 0 |
| simplify_gpt | 7m 36s | $2.81 | 0 |
| verify | 3m 42s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **127m 37s** | **$104.98** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: fabro <fabro@anthropic.com>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
Bryan Helmkamp
|
fd63f4b523
|
feat(api): expose run size buckets (#369)
## Summary Adds a stable `Run.size` API field so clients can bucket workflow runs by current best-effort billed usage without introducing a separate cost-estimation system. The field uses the `RunSize` enum and serializes as uppercase `XS`, `S`, `M`, `L`, or `XL`. ## Changes - Derives run size from terminal billed totals when available, otherwise from the existing projected stage usage while a run is still active. - Exposes `size` on `Run` in the OpenAPI contract and regenerated TypeScript client. - Preserves existing `Run.billing` behavior so live/provisional usage only affects `size`, not the nullable billing summary. ## Verification - `cargo nextest run -p fabro-types run_size` - `cargo nextest run -p fabro-store summary_size_tracks_current_projected_usage_before_terminal_conclusion` - `cargo nextest run -p fabro-api run_summary_json_matches_openapi_shape` - `cargo +nightly-2026-04-14 fmt --check --all` - `cd apps/fabro-web && bun run typecheck` - `git diff --check` - `cargo build --workspace` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) |
||
|
Bryan Helmkamp
|
1cd5d89316
|
Runs list view: table layout, server-side sort/pagination, redesigned toolbar (#367)
## Summary Overhauls the `/runs` list view and consolidates the two runs endpoints that backed it. **API** - Removes `GET /api/v1/boards/runs`, `PaginatedBoardRunList`, and `BoardColumnDefinition`. The board view is now a pure frontend rendering. - `GET /api/v1/runs` gains `status` (repeatable `BoardColumn`), `sort` (`created_at | updated_at | status | elapsed`, default `created_at`), and `direction` (`asc | desc`, default `desc`). - `BoardColumn` enum gains `removing`; default behavior hides Removing-status runs, opt in with `?status=removing`. - `PaginationMeta` gains an optional `total: int64`; `list_runs` fills it in (free — it already filters all runs in memory before paging). **List view UI** - Renders as a real `<table>` with column headings instead of horizontal cards. - Sortable Status, Elapsed, Created, and Updated headers — click to toggle direction, click another to switch sort key (resets to desc). URL params drive `sort`/`direction`/`page`/`size`. - New pager footer with rows-per-page selector (10/25/50/100), `Page X of Y`, and first/prev/next/last icon buttons. - Toolbar redesigned into left (search + filter buttons for Time/Repo/Workflow + archived toggle) and right (column picker + view toggle) sections. Filter buttons use Headless UI `Menu` popovers; the column picker uses Headless UI `Listbox` with `multiple` for multi-select. Hidden columns persist via `?hide=...`. **Tests** - 589 server tests pass, including new coverage for status filter (single + repeated), Removing opt-in, sort × direction with `id desc` tiebreak, and status-bucket sorting. - Frontend tests updated for the matcher-based cache invalidation and the new `buildBoardColumns` signature; 435 pass (3 pre-existing `RunDetail full-height` failures unrelated to this change). ## Test plan - [ ] `cargo build --workspace` - [ ] `cargo nextest run -p fabro-server` - [ ] `cd lib/packages/fabro-api-client && bun run generate` — no diff (already regenerated and committed) - [ ] `cd apps/fabro-web && bun run typecheck && bun test` - [ ] Manual: visit `/runs` — board view still renders all columns in canonical order, Removing runs hidden, archived toggle works. - [ ] Manual: visit `/runs?view=list` — table renders with sortable headers; clicking a header updates URL; pager advances; changing rows-per-page resets to page 1; column picker hides/shows columns and round-trips via `?hide=`. - [ ] Manual: `curl '/api/v1/boards/runs'` → 404; `curl '/api/v1/runs?status=removing'` returns only removing runs; `curl '/api/v1/runs?sort=status&direction=asc'` returns runs grouped by status bucket. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
fabro-sh-0530[bot]
|
7d8506cb7c
|
feat: add manual retry for failed and dead runs (#362)
## Summary
Adds a **Retry** action that creates a fresh run from a failed or dead
run's captured durable definition. The new run gets a new ID, records
`retried_from: <source_run_id>`, and is immediately queued. The source
run is left entirely unchanged.
### Plan Summary
- `retried_from: Option<RunId>` added to `RunCreatedProps`,
`RunProjection`, and `Run` (API surface); defaults to `null` for
backward compat with legacy events.
- `POST /api/v1/runs/{id}/retry` → `201` with the new run; eligible
source states are `failed` (except `reason=cancelled`) and `dead`.
- New `retry_run` workflow operation (modeled after `fork`) creates a
new run store, appends `run.created` with `retried_from` set, then
`run.submitted`. No checkpoints, sandbox state, PR links, questions, or
conclusions are copied.
- `start_run` handler refactored into a reusable `queue_run_start(state,
id, resume)` helper so retry can queue the new run through the same
path.
- Web: `canRetry` predicate, `useRetryRun` mutation, **Retry** menu item
in `ActionsMenu`, "Retried from" link in `RunSummaryPanelView`, and
navigation to the new run on success (deduplicated via
`lastProcessed.retry`).
- OpenAPI spec updated; generated Rust and TypeScript client types
regenerated.
## Key design decisions
**No runtime state is copied.** Only the durable definition fields
(`graph`, `settings`, `labels`, `git`, `manifest_blob`,
`definition_blob`, `fork_source_ref`, `parent_id`, `title`) are
forwarded to the new `RunCreated` event. Checkpoints, sandbox, billing,
PR links, and pending controls are left in the source run.
**`queue_run_start` extraction.** `start_run` was restructured to
extract a `queue_run_start(state, id, resume) -> Result<(), ApiError>`
helper, so the retry handler can reuse the exact same queueing path
without duplicating logic.
**`lastProcessed.retry` deduplication.** The UI effect that fires on
`retryMutation.data` checks `state.lastProcessed.retry === result`
before navigating, so React StrictMode double-invocation or re-renders
won't push duplicate navigations.
**Demo mode guard.** `canRetry` is gated by `!demoMode` at the call site
so the button is hidden in demo mode and never navigates to a missing
demo run.
### Fabro Details
<details>
<summary>Ran 9 stages in 65m 2s for $51.70</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 1m 53s | – | 0 |
| preflight_lint | 2m 8s | – | 0 |
| implement | 36m 51s | $36.06 | 0 |
| simplify_opus | 16m 22s | $14.46 | 0 |
| simplify_gpt | 3m 10s | $1.18 | 0 |
| verify | 3m 39s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **65m 2s** | **$51.70** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
0f36304d2c
|
Add small_default model role and async generated run titles (#368)
## Summary
Introduces a `small_default` catalog role for identifying each
provider's small/cheap utility model, and uses that model to
asynchronously generate human-readable run titles when the caller
doesn't supply one explicitly.
### Plan Summary
- **Catalog**: Add `small_default: Option<bool>` to
`ModelCatalogSettings` and `small_default: bool` to the `Model` type.
Mark built-in small defaults: `claude-haiku-4-5` (Anthropic),
`gpt-5.4-mini` (OpenAI), `gemini-3.1-flash-lite-preview` (Gemini).
Validate that each provider has at most one small default; zero is
allowed with fallback to the provider's regular default.
- **Helpers**: Add `small_default_for_provider` and
`small_default_for_configured_ids` on `Catalog`, mirroring the existing
`default_for_provider` / `default_for_configured_ids` /
`probe_for_provider` pattern.
- **Title generation**: New `run_title_generation` module in
`fabro-server` builds a prompt from workflow identity, goal, and raw run
inputs, calls `generate_object` with `max_tokens(64)` and a 10 s
timeout, normalizes output (trim, reject blank/control, truncate to 100
chars), and falls back to the deterministic title on any failure.
- **Server integration**: In the create-run handler, if no explicit
`RunManifest.title` was supplied and at least one LLM provider is ready,
spawn a detached task that generates a title and appends
`run.title.updated` — but only if the title hasn't been changed by a
concurrent user PATCH.
## What changed and why
**`small_default` vs `default`** — the existing `default` role drives
normal model selection for workflow execution and must not be disturbed.
`small_default` is a separate, additive role for lightweight metadata
work. The two roles are intentionally independent so teams can promote a
newer large model to `default` without accidentally routing title
generation there.
**Best-effort, async title enrichment** — run creation is kept
synchronous and reliable. The title task is fire-and-forget: LLM errors,
timeouts, and validation failures all silently leave the deterministic
title in place. The stale-title guard (`current.title !=
deterministic_title`) prevents the async task from clobbering a
concurrent user edit via `PATCH /runs/{id}`.
**No redaction** — per the design goal, raw input values are forwarded
to the model. This is noted explicitly in the prompt and in the module
docs.
**Prompt size bounding** — each of the three prompt sections (workflow
identity, run inputs, workflow summary) is independently capped at 4 000
characters with a `...[truncated]` marker so pathological inputs can't
produce enormous requests.
## Public interface changes
- `Model` gains `small_default: bool` in the Rust type, OpenAPI schema,
and generated TypeScript client.
- `MAX_RUN_TITLE_CHARS` is now `pub` in `fabro-types` so the
title-generation module can reuse the same limit.
- Config docs (`models.mdx`, `litellm.mdx`) document `small_default =
true` alongside `default` and `probe`.
### Fabro Details
<details>
<summary>Ran 9 stages in 61m 23s for $32.17</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 1m 52s | – | 0 |
| preflight_lint | 2m 5s | – | 0 |
| implement | 29m 16s | $23.26 | 0 |
| simplify_opus | 17m 15s | $6.28 | 0 |
| simplify_gpt | 7m 1s | $2.63 | 0 |
| verify | 3m 7s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **61m 23s** | **$32.17** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
caba862a33
|
Show live timing for in-flight runs via read-time overlay (#361)
## Summary
`Run.timing` was only populated for terminal runs, so the duration chip
and popover were hidden for every queued, running, or blocked run. This
change derives a best-effort `RunTiming` at cache read time for
started-but-not-terminal runs, making the duration chip appear and tick
for in-flight runs everywhere the UI consumes `summary.timing`.
### Plan Summary
- Add `RunProjection::live_run_timing(now)` in `fabro-types`: wall time
from `start.start_time → now`; active time summed from completed stages'
`StageTiming`.
- Add `apply_read_overlays(entry, now)` in `projection_cache.rs`: called
after mutex release on cloned entries; only fills `timing` when it is
`None` (terminal runs are unaffected).
- Thread `now: DateTime<Utc>` through `get_summary` / `list` /
`list_cached_runs` / `list_runs` / `list_runs_with_projection` in
`slate/mod.rs` and `projection_cache.rs`.
- Propagate `Utc::now()` at all HTTP handler and background-task call
sites in `fabro-server` and `fabro-workflow`.
- Add unit tests covering the three key cases: not-yet-started (returns
`None`), in-flight with completed stages, and a terminal run whose live
derivation matches `Conclusion.timing`.
### Key design decisions
**Overlay happens outside the cache mutex on a cloned copy.** The cached
`CachedRunProjection.summary.timing` is never mutated; only the cloned
value returned to callers gets the overlay. This means `get_cached_run`
(raw cache access, no `now`) still returns `None` for in-flight timing —
confirmed by the new integration test
`cached_summary_overlays_live_timing_without_mutating_cached_snapshot`.
**Known limitation — active time steps, not ticks.** `StageProjection`
records inference/tool time only at stage completion, so
`active_time_ms` reflects the sum of *completed* stages and jumps
forward when a stage finishes. `wall_time_ms` advances continuously.
This is intentional and documented in the code comment; live per-stage
inference tracking is out of scope.
**`build_summary` and `Conclusion.timing` are untouched.** All five
internal readers that want "timing as of conclusion" continue to use
`Conclusion.timing` directly; no test churn from the existing call
sites.
### Fabro Details
<details>
<summary>Ran 9 stages in 38m 28s for $10.35</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 2m 4s | – | 0 |
| preflight_lint | 2m 20s | – | 0 |
| implement | 11m 27s | $6.21 | 0 |
| simplify_opus | 13m 12s | $2.48 | 0 |
| simplify_gpt | 4m 20s | $1.66 | 0 |
| verify | 4m 9s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **38m 28s** | **$10.35** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
f81c5b96b1
|
Move agent state (todos, subagents, skills, MCP) onto StageProjection (#364)
## Summary
The `GET /runs/{id}` response now carries per-stage agent state — todos,
subagents, skills, and MCP server status — directly on each
`StageProjection`, unblocking the agent-stage sidebar without any new
endpoints.
## What changed and why
**`RunProjection.todos_by_list` removed.** The run-level map was the
only home for todos, but every list was already 1:1 with a stage (keyed
by `openai_plan:<session>` or `anthropic_tasks:<root_session>`). Moving
todos onto `StageProjection.todos: Option<TodoListProjection>`
eliminates the awkward cross-stage indirection with no loss of
expressiveness.
**Four new fields on `StageProjection`** (`todos`, `subagents`,
`skills`, `mcp_servers`) plus five new projection-side types
(`SubAgentProjection`, `SubAgentStatus`, `SkillsProjection`,
`ActivatedSkill`, `McpServerProjection`, `McpServerStatus`). All
colocated in `run_projection.rs`; no new modules. Four existing
event-payload types are reused directly (`TodoListProjection`,
`AgentSkillSummary`, `AgentSkillActivationSource`,
`AgentMcpToolSummary`) via `with_replacement(...)` in
`fabro-api/build.rs` so progenitor doesn't generate parallel `ApiFoo`
aliases.
**Reducer rerouting** (`run_state.rs`): `TodoCreated/Updated/Deleted`
now resolve the owning stage via the existing
`stage_at_stored_or_current_visit` helper and mutate `stage.todos`
directly. Eight new event arms handle
`AgentSubSpawned/Completed/Failed/Closed`,
`AgentSkillsDiscovered/Activated`, and `AgentMcpReady/Failed` using the
same `stage_at_stored_or_visit` pattern already used for other agent
events.
**Design decisions called out in the plan:**
- `SkillActivated` appends every activation (event-sourced replay
semantics); the UI can collapse if needed.
- `upsert_mcp_server` replaces by `server_name`, so a server that
recovers after a failure shows its final state.
- `SubAgentStatus` and `McpServerStatus` are projection-side enums,
intentionally distinct from the runtime per-process status types in
`fabro-agent`.
**OpenAPI + TS client** updated in lockstep: new schemas added,
`todos_by_list` removed from `RunProjection`, `bun run generate`
regenerated 20+ new model files.
### Plan Summary
- Extend `StageProjection` with `todos`, `subagents`, `skills`,
`mcp_servers` + supporting types in `run_projection.rs`
- Remove `RunProjection.todos_by_list` (no cross-stage use case)
- Reroute todo reducer handlers; add 8 new event arms for
subagent/skill/MCP events
- Wire reused types through `fabro-api/build.rs` `with_replacement`;
regenerate TS client
- Update all existing todo reducer tests to read from `stage.todos`; add
new test modules for subagent, skill, and MCP event families
- Update stale comment in `run-events.ts`
### Fabro Details
<details>
<summary>Ran 9 stages in 38m 52s for $13.29</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 6s | – | 0 |
| preflight_lint | 2m 16s | – | 0 |
| implement | 16m 8s | $7.80 | 0 |
| simplify_opus | 10m 34s | $3.91 | 0 |
| simplify_gpt | 3m 23s | $1.58 | 0 |
| verify | 3m 51s | – | 0 |
| fmt | 2s | – | 0 |
| **Total** | **38m 52s** | **$13.29** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
7e6052bec3
|
Surface reasoning_effort + speed in stage badge end-to-end (#363)
## Summary
The run page stage badge showed only the model name. This PR plumbs
`reasoning_effort` and `speed` from the LLM call site all the way
through the event stream, store projection, API, and UI so the badge now
renders `gpt-5.5 · high`.
### Plan Summary
- **Event props** — `AgentSessionActivatedProps` and `StagePromptProps`
gain `reasoning_effort: Option<ReasoningEffort>` and `speed:
Option<Speed>` with `serde(default, skip_serializing_if)` for
back-compat.
- **Typed projection** — `provider_used: Option<serde_json::Value>` is
replaced by `Option<StageModelUsage>`, a proper struct in `fabro-types`
with factory methods (`from_prompt_props`,
`from_agent_session_activated`). The freeform JSON bag is gone.
- **Emission sites** — `ActivationLeaseOptions` carries the new fields;
`emit_stage_prompt()` (new shared helper) resolves
`EffectiveRequestControls` via the backend and stamps them on
`Event::Prompt`. `AgentHandler` and `PromptHandler` both call this
helper instead of building the event inline.
- **ACP path** — `AgentAcpStarted` no longer writes `provider_used`; the
canonical source is the later `AgentSessionActivated` event, which is
already emitted for ACP steering sessions. Runs without a hub
legitimately leave `provider_used` unset.
- **OpenAPI** — new `StageModelUsage` and `ReasoningEffort` schemas
replace the `object | null` bag; `build.rs` maps both to the canonical
Rust types; a new `stage_model_usage_round_trip` integration test
enforces the parity requirement.
- **UI** — `extractStageModel` (event-scanning heuristic) is deleted;
replaced by `formatStageModelUsageLabel` and `stageModelUsageTitle` that
read directly off `selectedStage.providerUsed`. `parseFanInOutcome` now
sources the reducer model from `stage.prompt` instead of
`prompt.completed`.
### Key design decisions
**No type sprawl**: `fabro_model::ReasoningEffort` and `Speed` are
reused verbatim via `with_replacement` in `build.rs` — no parallel
enums.
**ACP behavior change**: previously `AgentAcpStarted` wrote a bespoke
`provider_used` blob and a later `AgentSessionActivated` would be
ignored for ACP sessions. Now `AgentSessionActivated` is the single
write path for all modes; ACP runs that never activate a steering hub
correctly leave `provider_used = null`. The integration test (`acp.rs`)
is updated to assert the new shape, and the unit test is renamed
`agent_acp_started_alone_leaves_stage_provider_used_unset` to document
intent.
**`emit_stage_prompt` helper**: both `AgentHandler` and the existing
prompt path share one function to avoid the two call sites drifting
apart again.
### Fabro Details
<details>
<summary>Ran 9 stages in 98m 44s for $65.70</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 2m 15s | – | 0 |
| preflight_lint | 2m 30s | – | 0 |
| implement | 42m 19s | $26.85 | 0 |
| simplify_opus | 38m 3s | $35.17 | 0 |
| simplify_gpt | 9m 20s | $3.68 | 0 |
| verify | 3m 38s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **98m 44s** | **$65.70** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
Co-authored-by: Bryan Helmkamp <bhelmkamp@users.noreply.github.com>
|
||
|
fabro-sh-0530[bot]
|
651eae6b34
|
Add Slack run lifecycle notifications via [run.notifications] (#365)
## Summary
Extends the Slack integration to post `run.started`, `run.completed`,
and `run.failed` notifications, configured per-run or per-workflow
through `[run.notifications]` rather than server config. Interview
behavior is unchanged and keeps its own state.
### What changed and why
**`SlackService` is now started whenever Slack credentials are
present**, regardless of whether `default_channel` is set. Previously,
the service required `default_channel` to initialize, which blocked
lifecycle notifications for users who have no interview default.
`default_channel` is now `Option<String>` and is only consulted in the
`InterviewStarted` path.
**`handle_event` receives the full `EventEnvelope` and `AppState`**
instead of just the `RunEvent`. Lifecycle handling needs to read the
cached run projection (for `[run.notifications]` routes) and scan prior
events (for PR details and the `run.started` event name), both of which
require `AppState`.
**Lifecycle path in `handle_event`** (`RunStarted` / `RunCompleted` /
`RunFailed`):
1. Reads the run projection to find enabled Slack routes whose `events`
list contains the current event name.
2. For terminal events, scans prior run events to recover
`PullRequestCreated` details and the `run.started` event name.
3. Resolves each route's channel (supporting `{{ env.VAR }}`
interpolation); warns and skips on missing/empty/unresolved channels
without affecting other routes.
4. Posts once per matching route concurrently via `join_all`; post
failures are logged, never propagated.
**`fabro-slack/src/blocks.rs`** adds `run_lifecycle_blocks` and helpers
separate from the interview builders:
- `RunLifecycleKind` uses `strum::IntoStaticStr` for the title string.
- All untrusted fields go through `escape_slack_controls` +
`truncate_to_limit`.
- `compact_duration` formats milliseconds into human-readable strings
(`1.2s`, `1m 5s`, `2h 30m`, …).
- PR line includes number, optional URL link, and optional HTML-escaped
title.
**`SlackClient::with_api_base_and_http`** is added as a test constructor
so server tests can point the client at a `MockServer` without going
through the normal builder path.
### Design decisions
- Lifecycle notifications are fire-and-forget and never touch
`posted_messages` or `thread_registry`, keeping interview and
notification state fully separate.
- `default_channel` is only used for interviews; lifecycle channel
always comes from `[run.notifications.<name>.slack].channel`. This
matches the goal of not promoting per-run config into server config.
- PR title is sourced only from prior `PullRequestCreated` events — no
GitHub API call is made at notification time. If only a
`PullRequestLink` is available in the projection, number and URL are
included but title is omitted.
- Workflow label resolution follows a priority chain: workflow name →
workflow slug → graph name → `run.started` event name → raw event name.
### Plan Summary
- Make `SlackService` start without `default_channel`; gate interview
path on `default_channel` presence.
- Add `handle_lifecycle_event` that filters routes, loads prior events,
builds blocks, resolves channels, and fans out posts.
- Add `run_lifecycle_blocks` Block Kit builder with escaping,
truncation, and `compact_duration`.
- Add server integration tests covering: started/completed/failed
posting, route filtering, missing/unresolved channel skipping, PR
details from prior events, and interview/lifecycle state isolation.
- Update public docs for Slack integration and run configuration.
### Fabro Details
<details>
<summary>Ran 9 stages in 53m 38s for $22.76</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 1m 58s | – | 0 |
| preflight_lint | 2m 11s | – | 0 |
| implement | 23m 3s | $14.18 | 0 |
| simplify_opus | 16m 37s | $6.36 | 0 |
| simplify_gpt | 5m 30s | $2.23 | 0 |
| verify | 3m 31s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **53m 38s** | **$22.76** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bhelmkamp@users.noreply.github.com>
|
||
|
fabro-sh-0530[bot]
|
7f84ac5e3f
|
Replace run-scoped sandbox config with named environments (#360)
## Summary
Replaces the `[run.sandbox]` configuration surface with a named,
provider-explicit environment catalog. Runs now select an environment by
slug (`[run.environment] id = "..."`) rather than configuring a sandbox
inline. Fabro resolves the catalog through normal settings precedence,
applies sparse run-level overrides, and creates a concrete sandbox from
the resolved environment.
This is a clean break — no `[run.sandbox]` compatibility layer.
### Plan Summary
- **New config shape:** Top-level `[environments.<slug>]` catalog valid
in `settings.toml`, `.fabro/project.toml`, and `workflow.toml`. Runs
reference a slug via `[run.environment] id = "..."` with optional sparse
overrides under `[run.environment.*]`.
- **Unified environment fields:** `provider`, `image` (ref +
dockerfile), `resources` (cpu/memory/disk), `network` (mode + allow
CIDRs), `lifecycle` (preserve/stop_on_terminal/auto_stop), `labels`,
`volumes`, `env` — replacing the previous split between `[run.sandbox]`,
`[run.sandbox.docker]`, `[run.sandbox.daytona]`, and
`[run.sandbox.daytona.snapshot]`.
- **OpenAPI schema update:** `RunSandboxSettings`, `DockerSettings`,
`DaytonaSettings`, and `DaytonaNetworkLayer` replaced with
`RunEnvironmentSettings`, `EnvironmentSettings`, `EnvironmentProvider`,
`EnvironmentImageSettings`, `EnvironmentResourcesSettings`,
`EnvironmentNetworkSettings`, `EnvironmentLifecycleSettings`, and
`EnvironmentVolumeSettings`.
- **CLI flag rename:** `--sandbox <provider>` → `--environment <slug>`
on `run`, `create`, `preflight`, and `server start/restart`.
- **Provider capability model:** Hard errors for security properties a
provider cannot enforce (local with blocked/CIDR networking; docker with
CIDR allow-lists). Warnings for unsupported resource limits, volumes,
labels, auto-stop, and Docker Dockerfiles.
- **Docs and internal code updated** throughout: `.fabro/project.toml`,
workflow configs, all public docs, CLI args, manifest builders, and the
runner's GitHub credentials check.
### Provider mapping
| Environment field | Local | Docker | Daytona |
|---|---|---|---|
| `image.ref` | Ignored | Docker image | Snapshot name |
| `image.dockerfile` | Ignored | Warning; ignored | Snapshot Dockerfile
(requires `image.ref`) |
| `resources.cpu/memory/disk` | Warning; ignored | cpu_quota / memory
limit / warning | Snapshot sizing |
| `network.mode = block` | **Error** | `network_mode = none` | Daytona
block |
| `network.mode = cidr_allow_list` | **Error** | **Error** | Daytona
CIDR allow-list |
| `labels` | Warning; ignored | Warning; ignored | Daytona labels |
| `volumes` | Warning; ignored | Warning; ignored | Daytona volume
mounts |
| `lifecycle.auto_stop` | Warning; ignored | Warning; ignored | Daytona
auto-stop interval |
| `env` | Process env overlay | Container env | Sandbox env |
### Fabro Details
<details>
<summary>Ran 11 stages in 217m 39s for $129.86</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 4m 7s | – | 0 |
| preflight_lint | 4m 9s | – | 0 |
| fix_lints | 3m 46s | $1.06 | 0 |
| implement | 76m 6s | $57.39 | 0 |
| simplify_opus | 71m 50s | $38.17 | 0 |
| simplify_gpt | 8m 27s | $2.24 | 0 |
| verify | 6m 10s | – | 0 |
| fixup | 42m 1s | $31.00 | 0 |
| fmt | 3s | – | 0 |
| **Total** | **217m 39s** | **$129.86** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
Co-authored-by: Bryan Helmkamp <bhelmkamp@users.noreply.github.com>
|
||
|
fabro-sh-0530[bot]
|
c987766641
|
agent: use API usage baseline for compaction context estimate (#366)
## Summary
Replaces the whole-history `chars / 4` compaction trigger with a Claude
Code-style hot-path estimator: find the latest assistant turn with real
provider-reported `usage.total_tokens()`, use that as the baseline, and
add local char estimates only for turns appended after it. This makes
compaction sensitive to actual provider-reported context usage
(including cache read/write and reasoning tokens) without adding any
provider token-count API calls.
### Plan Summary
- **New estimator** (`estimate_active_context_usage`): returns a
`ContextEstimate` with both a token count and an `ContextEstimateMethod`
enum tag (`ApiUsagePlusLocalDelta` or `LocalEstimate`).
- **`check_context_usage`** now returns `Option<ContextEstimate>`
instead of `bool`, and includes `estimate_method` in warning `details`.
The caller passes the estimate directly into `compact_context`, avoiding
a double-compute.
- **`compact_context`** signature drops `system_prompt` (no longer
needed) and takes the pre-computed `ContextEstimate`. The
`CompactionStarted` event is now emitted *after* the `turns.len() <=
preserve_count` no-op guard, so a no-op can never emit `Started` without
`Completed`.
- **`History::compact`** invalidates preserved assistant `usage` (resets
to `TokenCounts::default()`) so a preserved turn's pre-compaction
provider baseline never becomes the next estimate's anchor. Content,
tool calls, provider parts, and response IDs are untouched.
- **`session.compact_if_needed`** restructured to early-return on `None`
from `check_context_usage` or on compaction disabled, simplifying the
nesting.
## Key design decisions
**Why invalidate preserved assistant usage?** After compaction the prior
turns are gone, so a stored `total_tokens` from before compaction would
overstate the new context. The authoritative billing record is in
emitted run events, not in mutable runtime history.
**Why return `Option<ContextEstimate>` from `check_context_usage`?**
Avoids recomputing the estimate in `compact_context`. It also makes the
call-site idiom (`let Some(estimate) = ... else { return; }`) an
explicit gate, which is cleaner than a separate bool-then-compact
pattern.
**Why `strum::IntoStaticStr` on the method enum?** Lets the variant
serialize to a `&'static str` for the JSON `details` field without a
manual `match` or adding `serde` derives.
### Fabro Details
<details>
<summary>Ran 9 stages in 30m 54s for $7.93</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 2s | – | 0 |
| preflight_compile | 1m 52s | – | 0 |
| preflight_lint | 2m 6s | – | 0 |
| implement | 8m 11s | $3.47 | 0 |
| simplify_opus | 11m 7s | $3.53 | 0 |
| simplify_gpt | 2m 39s | $0.93 | 0 |
| verify | 4m 4s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **30m 54s** | **$7.93** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD.", model="gpt-55", reasoning_effort="xhigh"]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
Bryan Helmkamp
|
8f36772af3
|
feat(llm): add input token counting (#359)
## Summary Adds an optional `fabro-llm` API for counting model-visible input tokens without creating a completion, with provider-native counting where available and deterministic local estimates when exact counting is unavailable or intentionally avoided. ## Details - Adds `Client::count_input_tokens` plus `InputTokenCountPreference` modes for provider-preferred, provider-required, and estimate-only behavior. - Implements provider count endpoints for Anthropic, Gemini, and OpenAI while filtering request bodies to count-supported fields. - Adds strict fallback semantics so local estimates do not hide bad credentials, invalid requests, unsupported models, context-length/content-filter failures, or other deterministic provider errors. - Adds a deterministic local estimator with explicit warning codes for local estimates, media heuristics, opaque provider context, and provider options. - Documents privacy implications: provider-native counting sends the provider-serialized model-visible request to the upstream count endpoint, while `EstimateOnly` keeps counting local. ## Verification - `cargo nextest run -p fabro-llm` - 385 passed, 10 skipped - `cargo +nightly-2026-04-14 fmt --check --all` - `cargo +nightly-2026-04-14 clippy -p fabro-llm --all-targets -- -D warnings` - `cargo build --workspace` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 (context unknown, thinking not disclosed) via [Codex](https://openai.com/codex) |
||
|
Bryan Helmkamp
|
29e2750a00
|
feat(agent): add Anthropic TaskGet and task reminders
Some checks are pending
Rust / Format (push) Waiting to run
Rust / Clippy (push) Waiting to run
Rust / Generated Docs (push) Waiting to run
Rust / Test (Linux) (push) Waiting to run
Rust / Test (macOS) (push) Waiting to run
TypeScript / Typecheck (push) Waiting to run
TypeScript / Test (push) Waiting to run
TypeScript / Build (push) Waiting to run
Expose TaskGet for Claude-style task inspection, refresh Anthropic prompt and tool guidance, and remind long-running sessions to use task tracking when those tools are available. |
||
|
Bryan Helmkamp
|
eb4891b1b0
|
refactor(agent): simplify reviewed changes
Use raw sandbox reads for memory and skills, keep line-numbered reads focused on display, and share retry-delay handling across agent and LLM code. Trim task tool descriptions, bound multi-file read concurrency, restore Docker's text read path, and add the reviewed implementation plan docs. |
||
|
Bryan Helmkamp
|
d1cc47324d
|
fix(agent): use raw sandbox reads for edits
Separate raw file reads from the line-numbered display API so apply_patch and edit_file operate on unformatted UTF-8 content. Keep read_file/read_many_files model-facing output numbered and cover regressions for prefix corruption. |
||
|
Bryan Helmkamp
|
96fff07a84
|
fix(agent): retry retryable mid-stream LLM failures
Replay retryable stream failures from the last committed turn state, clear partial visible output before retry or terminal failure, and map Anthropic stream error events into structured provider errors. |
||
|
Bryan Helmkamp
|
a308734e9b
|
feat(agent): align Anthropic task prompt guidance
Modularize the Anthropic system prompt into Claude-style sections and expand TaskCreate, TaskUpdate, and TaskList descriptions with task-management guidance adapted to Fabro's tool surface. |
||
|
fabro-sh-0530[bot]
|
bf7ce485e1
|
feat(fabro-types): promote transcript primitives and extend agent event… (#357)
## Summary
This is the foundational step of the unified agent transcript
implementation: it establishes one canonical set of replay types in
`fabro-types` and threads them into the existing `agent.message`,
`agent.tool.started`, and `agent.tool.completed` event shapes — without
breaking any existing producers or consumers.
## What changed
**New `fabro-types::transcript` module** owns `ContentPart`,
`ImageData`, `AudioData`, `DocumentData`, `ThinkingData`, `ToolCall`,
`ToolResult`, `MessageKind`, `MessageSource`, `PairMessageRef`,
`TranscriptMessage`, and `MessageId`. These were previously defined in
`fabro-llm::types`; they now live at the canonical layer.
**`fabro-llm::types`** drops its local definitions and re-exports from
`fabro-types` so every existing `fabro_llm::types::*` import keeps
compiling without change.
**`AgentMessageProps`** gains an optional `message:
Option<TranscriptMessage>` field; `AgentToolStartedProps` gains
`tool_call`, `turn_id`, and `parent_message_id`;
`AgentToolCompletedProps` gains `tool_result` and `turn_id`. All new
fields use `#[serde(default, skip_serializing_if = "Option::is_none")]`
so existing stored events deserialize cleanly.
**All current event emitters** (`fabro-workflow/event/convert.rs`, demo
fixtures, test helpers) are updated to set the new fields to `None` —
this is a mechanical compatibility update; actual enrichment comes in
later tasks.
### Design decisions worth noting
- `MessageKind` captures LLM role semantics (system / user / reasoning /
agent); `MessageSource` captures audit provenance (steer, pair,
loop_detection, …). They are intentionally kept separate so a steering
message can be `kind=user, source=steer` without collapsing the
distinction.
- `TranscriptMessage` is named with the `Transcript` prefix specifically
to avoid import ambiguity with `fabro_agent::Message` and
`fabro_llm::types::Message`.
- `ProviderAnswer` and `ProviderReasoning` are included as
`MessageSource` variants so committed model outputs carry a first-class
audit label distinct from user-originated inputs.
- The new fields are additive-only; no narrow legacy fields were
removed. Consumer migration is a separate step.
### Fabro Details
<details>
<summary>Ran 9 stages in 47m 27s for $12.79</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 6s | – | 0 |
| preflight_lint | 2m 21s | – | 0 |
| implement | 20m 6s | $8.53 | 0 |
| simplify_opus | 13m 36s | $2.68 | 0 |
| simplify_gpt | 4m 17s | $1.58 | 0 |
| verify | 4m 7s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **47m 27s** | **$12.79** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
fabro-sh-0530[bot]
|
a2e2cbc7ed
|
Add agent context observability events (memory, skills, MCP tools) (#356)
## Summary
Adds three new durable run events — `agent.memory.loaded`,
`agent.skills.discovered`, and `agent.skill.activated` — and enriches
`agent.mcp.ready` with names-only tool summaries. Consumers can now
reconstruct what memory, skills, and MCP tools were active for any agent
run by reading the event stream, without needing to inspect session
state.
### Plan Summary
- **`fabro-types`**: New prop structs (`AgentMemoryLoadedProps`,
`AgentSkillsDiscoveredProps`, `AgentSkillActivatedProps`,
`AgentMcpToolSummary`) and three new `EventBody` variants with canonical
dot-name serialization. `AgentMcpReadyProps.tools` uses
`#[serde(default, skip_serializing_if = "Vec::is_empty")]` for backwards
compatibility.
- **`fabro-agent/memory.rs`**: `discover_memory` now returns
`Vec<MemoryDocument>` carrying path, byte counts, and truncation flag
alongside content. The content itself is never put in any event payload.
- **`fabro-agent/types.rs`**: Adds `MemoryLoaded`, `SkillsDiscovered`,
`SkillActivated`, and enriched `McpServerReady` internal variants.
Removes `SkillExpanded` (replaced by `SkillActivated { source: Slash
}`). New variants are **not** classified as streaming noise, so they
persist.
- **`fabro-agent/session.rs`**: Emits `MemoryLoaded` before skills init,
`SkillsDiscovered` after skill discovery, and enriches `McpServerReady`
with summaries from `McpConnectionManager::tool_summaries_for_server`.
Slash expansion now emits `SkillActivated { source: Slash }` instead of
`SkillExpanded`.
- **`fabro-agent/skills.rs`**: `make_use_skill_tool` emits
`SkillActivated { source: Tool }` on successful lookup only.
- **`fabro-mcp/connection_manager.rs`**: New `tool_summaries_for_server`
returns sorted `(qualified_name, original_name)` pairs without leaking
descriptions or schemas.
- **`fabro-workflow/event/convert.rs` + `names.rs`**: Converts all new
agent events to their typed `fabro-types` props, including `visit`
injection. Removes dead `SkillExpanded` arm.
- **`docs/internal/events.md`**: Documents all new event shapes with
full property tables; notes that `agent.skill.expanded` is replaced.
### Key design decisions
- Both `MemoryLoaded` and `SkillsDiscovered` are emitted even when the
result is empty. This lets consumers distinguish "no memory/skills
found" from "event not yet reported."
- Memory file **contents are never included** in any event payload —
only `path`, `byte_count`, `loaded_bytes`, and `truncated`.
- `agent.mcp.ready` `tools` field is omitted from JSON when empty
(`skip_serializing_if`), preserving wire compatibility with existing
stored events.
- `SkillActivated` is persisted (not filtered as streaming noise),
unlike the former internal-only `SkillExpanded`.
### Fabro Details
<details>
<summary>Ran 9 stages in 57m 15s for $27.15</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 17s | – | 0 |
| preflight_lint | 2m 30s | – | 0 |
| implement | 21m 18s | $16.27 | 0 |
| simplify_opus | 15m 21s | $6.52 | 0 |
| simplify_gpt | 10m 33s | $4.35 | 0 |
| verify | 4m 24s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **57m 15s** | **$27.15** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
fabro-sh-0530[bot]
|
0754f1ca4a
|
Add fabro_run_get read-only run inspection tool (#358)
## Summary
Adds a new `fabro_run_get` MCP tool that returns a run's summary,
resolved ID, projection, and pending questions without any mutation
capability. This separates read-only inspection from operational
control, allowing Ask Fabro sessions to inspect runs safely without
access to write operations.
## What changed and why
**New tool (`fabro-tool/src/get.rs`):** `FabroRunGetParams` /
`ValidatedRunGet` / `RunGetResult` follow the same
validation-and-dispatch pattern as other run tools. The implementation
resolves a selector, then fans out to three read-only API calls
(retrieve run, get state, list questions) and assembles them into a
single structured result.
**Tool registry and dispatch:** `FABRO_RUN_GET_TOOL_NAME` is exported
from `common.rs` and `lib.rs`, added to `TOOL_DEFINITIONS`, wired into
the MCP stdio server (`fabro-mcp-server/src/server.rs`), and dispatched
in the LLM agent executor (`fabro-workflow/src/handler/llm/api.rs`).
**Ask Fabro access policy (`fabro-server/.../sessions.rs`):** The
session now registers and allows only `fabro_run_events` +
`fabro_run_get` via the new `ASK_FABRO_RUN_TOOL_NAMES` constant.
`fabro_run_interact` is explicitly moved to the denied set, closing off
mutation from that session type. The policy match arm is refactored from
a hardcoded `|`-chain to a slice `contains` check so the constant is the
single source of truth.
**Docs:** `mcp.mdx` now lists `fabro_run_get` as the inspection tool and
redescribes `fabro_run_interact` as control-oriented.
**Backward compatibility:** `fabro_run_interact` (including `get` and
`get_questions` actions) is unchanged and still fully operational for
contexts that allow it.
### Plan Summary
- New `get.rs` module in `fabro-tool` with validation, async fetch, and
unit tests
- Constants + schema registration in `common.rs` / `lib.rs`
- MCP server and LLM dispatch branches added for
`FABRO_RUN_GET_TOOL_NAME`
- Ask Fabro session swaps `FABRO_RUN_INTERACT_TOOL_NAME` →
`FABRO_RUN_GET_TOOL_NAME` in registry and policy
- MCP integration tests: tool count constant, schema assertions, two new
end-to-end tests
(`mcp_get_resolves_selector_and_returns_summary_projection_and_questions`,
`mcp_get_rejects_blank_run_id_before_auth_or_network`)
- Public MCP docs updated
### Fabro Details
<details>
<summary>Ran 9 stages in 43m 30s for $13.42</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 2s | – | 0 |
| preflight_lint | 2m 14s | – | 0 |
| implement | 19m 43s | $8.85 | 0 |
| simplify_opus | 5m 52s | $1.45 | 0 |
| simplify_gpt | 10m 16s | $3.12 | 0 |
| verify | 2m 53s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **43m 30s** | **$13.42** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
fabro-sh-0530[bot]
|
94c657b92e
|
feat: add run.checkpoint.skip_git_hooks to bypass Git commit hooks (#355)
## Summary
Adds an opt-in `skip_git_hooks` boolean to `[run.checkpoint]` that
causes Fabro-managed run-branch checkpoint commits to pass `--no-verify`
to `git commit`, bypassing local hooks such as `pre-commit` and
`commit-msg`. Defaults to `false`. Metadata-branch snapshots and Fabro
`[[run.hooks]]` are unaffected.
```toml
[run.checkpoint]
skip_git_hooks = true
```
### Plan Summary
- `RunCheckpointSettings` (dense, in `fabro-types`) gains
`skip_git_hooks: bool` with `#[serde(default)]`.
- `RunCheckpointLayer` (sparse, in `fabro-config`) gains
`skip_git_hooks: Option<bool>` so layered config can distinguish unset
from explicit `false`.
- `RunCheckpointLayer::combine` is refactored from a wholesale-replace
to field-level merging: `exclude_globs` keeps its existing replace-wins
semantics; `skip_git_hooks` uses `.or()` (highest-priority layer that
sets it wins).
- `resolve_checkpoint` resolves `None → false`.
- `git_checkpoint` / `checked_git_checkpoint` in `sandbox_git.rs` accept
a new `skip_git_hooks: bool` and append `--no-verify` when true.
- `parallel_branch_commit_cmd` (new helper in `handler/parallel.rs`)
replaces the inline format string and accepts the same flag.
- `GitState` carries `checkpoint_skip_git_hooks`;
`RunOptions::checkpoint_skip_git_hooks()` exposes it; `execute.rs` and
`git.rs` thread it through.
- OpenAPI schema, TypeScript API client, and docs are updated.
### Key design decisions
**Field-level merging in `combine`**: the previous
`RunCheckpointLayer::combine` replaced the whole struct when
`self.exclude_globs` was non-empty. The refactor keeps that same replace
rule for `exclude_globs` while adding independent `Option::or` merging
for `skip_git_hooks`, so the two fields don't interfere.
**`--no-verify` only on run-branch commits**: the flag is injected only
in the two Git commit paths Fabro controls for run-branch checkpoints.
Metadata-branch snapshots use `git2` and never fire local hooks
regardless of this setting.
### Fabro Details
<details>
<summary>Ran 9 stages in 48m 3s for $13.91</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 3s | – | 0 |
| preflight_compile | 2m 4s | – | 0 |
| preflight_lint | 2m 15s | – | 0 |
| implement | 24m 13s | $10.38 | 0 |
| simplify_opus | 10m 31s | $1.59 | 0 |
| simplify_gpt | 5m 8s | $1.93 | 0 |
| verify | 3m 4s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **48m 3s** | **$13.91** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
|
||
|
Bryan Helmkamp
|
df6f62db6a
|
test(agent): pass root session id in tool execution tests
Update stale test-only call sites after execute_and_emit_one_tool gained an explicit root_session_id argument. |
||
|
Bryan Helmkamp
|
511371bd9a
|
feat(mcp): support goal files in run create
Allow fabro_run_create object specs to pass goal_file, reject goal and goal_file together, and preserve file-sourced goal semantics when building run manifests. |
||
|
Bryan Helmkamp
|
c2d950da38
|
feat: orient Ask Fabro turns with run snapshots | ||
|
Bryan Helmkamp
|
4df9e483ac
|
Merge remote-tracking branch 'origin/main' into ask-fabro-welcome-prompts | ||
|
fabro-sh-0530[bot]
|
a42634cc54
|
Add event-sourced todo tools for OpenAI and Anthropic profiles (#353)
## Summary
Adds a shared todo/task engine behind two model-native tool surfaces,
with all mutations persisted as individual run events and replayed into
`RunProjection`.
### Plan Summary
- **New domain types** in `fabro-types`: `TodoStatus`, `TodoListKind`,
`TodoProjection`, `TodoListProjection`, and `todos_by_list` on
`RunProjection`.
- **New run events**: `todo.created`, `todo.updated`, `todo.deleted` —
mapped through Fabro's typed event pipeline and replayed by
`RunProjectionReducer`.
- **`TodoRuntime`** (`fabro-agent`): thread-safe in-memory projection
shared across tool closures within a profile instance; each mutation
emits the corresponding agent event.
- **`update_plan`** registered only in `OpenAiProfile`: reconciles
incoming steps by exact `step` text (sha256-derived ID), emitting
create/update/delete events to match the submitted plan.
- **`TaskCreate` / `TaskUpdate` / `TaskList`** registered only in
`AnthropicProfile`: numeric task IDs per list, metadata merge with
`null`-key deletion, `status: "deleted"` routes to `todo.deleted`.
- **Session identity threading**: `ToolContext` gains `session_id`,
`root_session_id`, `tool_call_id`, and `agent_event_emitter`;
`execute_tool_calls` threads these through to `execute_one_tool`;
`Session` tracks `root_session_id` and `spawn_agent` inherits it for
subagents.
- **Scoping**: OpenAI todos scope to `openai_plan:<session_id>`
(per-session); Anthropic todos scope to
`anthropic_tasks:<root_session_id>` (shared across subagents).
- **Web invalidation**: `todo.*` events invalidate `getRunState` and the
run events list; tested in `run-events.test.tsx`.
```mermaid
graph TB
subgraph OpenAI
UP[update_plan] -->|diff by step text| TR[TodoRuntime]
end
subgraph Anthropic
TC[TaskCreate] --> TR
TU[TaskUpdate] --> TR
TL[TaskList] -->|read-only snapshot| TR
end
TR -->|emit todo.created/updated/deleted| SE[SessionBoundEmitter]
SE --> EV[AgentEvent stream]
EV --> RP[RunProjection\ntodos_by_list]
```
### Key design decisions
- **Step identity by text, not position** (`update_plan`): a
sha256-derived ID from `list_id + step` means reordering without
renaming emits an update rather than a delete+create. Duplicate step
strings are rejected with a model-visible error because text is the
identity.
- **No plan-replace event**: the engine emits only individual mutation
events; bulk replacement is expressed as a set of create/update/delete
events produced by diffing the incoming plan against the projection
snapshot.
- **`TodoRuntime` per profile instance**: tools inside a single profile
share one runtime. OpenAI subagents each have their own `session_id` so
their plans are isolated; Anthropic subagents inherit `root_session_id`
so tasks are shared — matching upstream Codex/Claude behavior.
- **`AgentEventEmitter` trait on `ToolContext`**: a narrow interface
that lets tools publish typed events without taking a dependency on the
full `Emitter`. `SessionBoundEmitter` wraps `Emitter` and stamps
`session_id` + `tool_call_id` on each event.
### Fabro Details
<details>
<summary>Ran 9 stages in 93m 23s for $56.46</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 6s | – | 0 |
| preflight_lint | 2m 20s | – | 0 |
| implement | 41m 30s | $38.21 | 0 |
| simplify_opus | 29m 2s | $11.78 | 0 |
| simplify_gpt | 14m 24s | $6.46 | 0 |
| verify | 3m 2s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **93m 23s** | **$56.46** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
Bryan Helmkamp
|
1930791802
|
feat(agent): gate tools by effective access policy
Expose only policy-allowed tool schemas to the model and block hidden tool calls before executor lookup. Give Ask Fabro a run-scoped read-only policy and prompt so it only advertises tools it can actually use. |
||
|
Bryan Helmkamp
|
d52f3726fc
|
fix: hide Ask Fabro reasoning deltas | ||
|
Bryan Helmkamp
|
4190e13a20
|
Collapsible run stage sidebar (#352)
## What Makes the run-detail stage sidebar (shown on the Overview and Stages tabs) collapsible with a slide animation. - A toggle button slides the panel between full width (`w-56`) and an icon-only rail (`w-12`), animating `width` over 300ms with the same easing as the Ask Fabro panel. - When collapsed, **stage status icons stay visible** — green check / red X / spinning teal for running — so run progress is still scannable at a glance. Workflow links (Graph Source, Run Logs, etc.) collapse to icons too so they remain reachable. - Labels and durations become `sr-only` with `title` tooltips for hover. - The open/closed choice persists to `localStorage` (`fabro:stage-sidebar-collapsed`), carrying across the Overview and Stages tabs and reloads. ## Layout - The collapse toggle is inline with the `STAGES` heading row (or `WORKFLOW` when a run has no stages yet), so it doesn't push the stage list down. - The stage sidebar's top padding on the Stages tab was reduced (`pt-6` → `pt-3`) so the heading aligns with the adjacent content column and sits closer to the tab nav. ## Notes Self-contained in `StageSidebar` — `run-overview.tsx` and `run-stages.tsx` render it inside flex layouts that already track its width, so the slide works in both with no parent changes (aside from the padding tweak). Verified: `tsc` typecheck passes; `stage-sidebar` lib tests pass (10/10). 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: fabro-sh-0530[bot] <281434857+fabro-sh-0530[bot]@users.noreply.github.com> Co-authored-by: Fabro <noreply@fabro.sh> |
||
|
fabro-sh-0530[bot]
|
199cf0822e
|
feat: gate Fabro run tools by worker JWT scope (#351)
Fabro run tools are now gated behind an explicit per-run opt-in so workflow agents only receive those capabilities when the run requests them. ## What changed - **`fabro_tools` setting** (`run.agent.fabro_tools`, default `false`) is resolved through the existing TOML config layer stack. - **Worker JWT scope** adds `agent:run_tools` only when the resolved setting is `true`; default worker tokens carry only `run:worker`. - **Worker tool registration** derives from the worker JWT scope claim. The CLI worker locally decodes the token payload and registers `FabroRunToolServices` only when the scope includes both `run:worker` and `agent:run_tools`. - **Server-side authorization remains authoritative**. The worker-side decode is only a local tool-registration gate; the server still validates token signature and scopes before accepting run-tool API calls. > **Behavior change:** existing runs that relied on Fabro run tools being always available must add `[run.agent] fabro_tools = true` to their workflow config. ## Verification ```sh cargo +nightly-2026-04-14 fmt --all cargo test -p fabro-cli fabro_run_tools_enabled_token_requires_run_tools_scope cargo test -p fabro-server worker_command_ cargo test -p fabro-static cargo +nightly-2026-04-14 clippy -p fabro-cli -p fabro-server -p fabro-static --all-targets -- -D warnings git diff --check ``` --------- Co-authored-by: Fabro <noreply@fabro.sh> Co-authored-by: Bryan Helmkamp <bryan@brynary.com> |
||
|
Bryan Helmkamp
|
5d188dbe18
|
feat(agent): make OpenAI apply_patch Codex-compatible (#350)
## Summary OpenAI-profile agents now receive `apply_patch` as a Codex-compatible freeform custom tool instead of a JSON function with a `patch` field. The model sends raw patch text validated by the vendored Lark grammar, and Fabro round-trips OpenAI custom tool calls/results through the Responses API. ## What Changed - Added `fabro-llm` support for function and custom tool definitions while preserving existing JSON function behavior for normal tools. - Translated OpenAI custom tool calls, custom tool outputs, and streaming `response.custom_tool_call_input.delta` events into Fabro tool calls with raw arguments. - Ported the Codex apply-patch grammar and adapted Codex-style patch parsing/application semantics to Fabro's `Sandbox` trait, including strict envelopes, fuzzy context matching, move/delete/add/update behavior, trailing-newline normalization, and Codex-style summaries/errors. - Updated OpenAI agent prompt/tool registration so `apply_patch` is freeform, and skipped JSON-schema validation/repair for custom tool calls only. - Updated file tracking to read Codex-style `A`/`M` result lines from successful patch output. ## Verification - `cargo nextest run -p fabro-llm -p fabro-agent` - `cargo +nightly-2026-04-14 fmt --check --all` - `cargo +nightly-2026-04-14 clippy --no-deps -p fabro-llm -p fabro-agent --all-targets -- -D warnings` - `git diff --check` Note: the full non-`--no-deps` clippy command still surfaces an unrelated existing `fabro-sandbox` `large_enum_variant` warning in `lib/crates/fabro-sandbox/src/sandbox_spec.rs`. --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) |
||
|
fabro-sh-0530[bot]
|
95b45b5960
|
feat: wire Ask Fabro sidebar to real session API with run-control tools (#349)
## Summary
Ships the Ask Fabro sidebar on run pages end-to-end: the agent now has
live `fabro_run_interact` and `fabro_run_events` tools scoped to its
owning run, and the web sidebar talks to real session APIs instead of a
scripted adapter. The `?ask=1` prototype gate is dropped in favour of
server-reported `run.ask_fabro.available`.
## What changed and why
### Rust — run-control tools in Ask Fabro sessions (`fabro-server`,
`fabro-workflow`, `fabro-tool`)
**Tool registration** (`fabro-workflow`): `register_fabro_run_tools` is
now `pub`; a new `register_named_fabro_run_tools` variant accepts a name
allowlist so callers can register a subset without forking the catalog
loop. Unknown names are silently ignored.
**Run-scoped backend** (`fabro-tool`): `ClientBackend` gains a
`run_scope: Option<RunId>` field set via `.with_run_scope(run_id)`.
Every method checks the scope before delegating to the HTTP client,
returning an error before a network call is made. `list_store_runs`
returns a single-element vec of the owning run when scoped;
`resolve_run` rejects non-parseable selectors rather than forwarding
them.
**Session wiring** (`fabro-server`): `build_profile` now returns
`Box<dyn AgentProfile>` (mutably accessible) instead of `Arc`;
`build_agent_session` mints a same-run worker token, builds a
`ClientBackend::with_run_scope`, constructs `FabroRunToolServices`, and
calls `register_named_fabro_run_tools` for the two tools before freezing
into an `Arc`. `AppState::self_server_target()` reads the bound address
from the runtime daemon record for the loopback HTTP call.
**Approval gate**: `build_ask_fabro_tool_approval` now fast-paths
`fabro_run_interact` and `fabro_run_events` to `Ok(())`; all other tools
remain subject to the `ReadOnly` auto-approve check. File/shell tools
are still denied.
### Web — real session adapter and sidebar wiring (`fabro-web`)
**`ask-fabro-runtime.ts`** (new): a `ChatModelAdapter` that creates a
session lazily on the first turn (`sessionsApi.createRunSession`),
caches the session id in `sessionStorage` keyed by run id, and streams
turns via `streamSessionTurn`. `applyTurnEvent` maps `run.session.*` SSE
events to assistant-ui `ThreadAssistantMessagePart[]` incrementally
(text deltas, tool-call started/completed pairs). A 404 on stream clears
the cached id so the next turn starts fresh.
**`ask-fabro-sidebar.tsx`**: drops `scriptIndexRef`, `EMPTY_CHAT`, and
the scripted adapter import; accepts `runId` and `defaultModel` props;
constructs the real adapter via `createAskFabroAdapter`.
**`run-detail.tsx`**: removes `?ask=1` / `askEnabled`; reads
`run.ask_fabro.{available, default_model}` from the summary; always
renders an `AskFabroTriggerButton` (disabled with a tooltip when
unavailable); passes `runId` and `defaultModel` to `<AskFabroSidebar>`.
### Architecture
```mermaid
graph TB
Browser -->|SSE turn stream| SessionsHandler
SessionsHandler -->|spawn| AskFabroAgent
AskFabroAgent -->|fabro_run_interact\nfabro_run_events| ClientBackend
ClientBackend -->|HTTP + same-run\nworker token| RunsAPI[Runs API\n/runs/:id]
ClientBackend -->|run_scope check| ClientBackend
RunsAPI -->|403 cross-run| ClientBackend
```
### Design decisions
- **Same-run scoping is double-enforced**: the `ClientBackend` scope
check fires before the HTTP call; the worker token's run scope causes a
403 at the API layer if the check were somehow bypassed.
- **`build_profile` → `Box` not `Arc`**: the profile needs mutable
access for tool registration after construction, so the `Arc` wrapping
is deferred until registration is complete.
- **`sessionStorage` per-run**: one session is reused across sidebar
open/close cycles for the same run tab; a page reload or different run
always starts clean.
- **Mutating actions included**: `interact` exposes
start/cancel/steer/archive/answer. This is intentional per the locked
decisions; the worker-token scope prevents cross-run blast radius.
### Fabro Details
<details>
<summary>Ran 9 stages in 74m 52s for $44.11</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 11s | – | 0 |
| preflight_lint | 2m 22s | – | 0 |
| implement | 38m 37s | $32.02 | 0 |
| simplify_opus | 17m 40s | $6.55 | 0 |
| simplify_gpt | 9m 32s | $5.55 | 0 |
| verify | 3m 43s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **74m 52s** | **$44.11** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: fabro <fabro@example.com>
Co-authored-by: fabro <fabro@fabro.sh>
|
||
|
fabro-sh-0530[bot]
|
f5f921aa3c
|
feat: add [run.agent] fabro_tools opt-in for worker run tools (#348)
## Summary
Workflow agents previously always received the `agent:run_tools` JWT
scope and had Fabro run tools registered unconditionally. This PR makes
Fabro run tool access an explicit per-run opt-in via `[run.agent]
fabro_tools = true`, defaulting to `false`.
## What changed
**Config layer** (`fabro-types`, `fabro-config`): `RunAgentSettings`
gains a `fabro_tools: bool` field (serialized with `#[serde(default)]`
for backward compatibility). The corresponding `RunAgentLayer` gets an
optional `fabro_tools: Option<bool>` that resolves to `false` when
absent. Layer merging follows the existing `Combine` macro semantics, so
a workflow-level `false` overrides a user-level `true`.
**Server** (`fabro-server`): `worker_command` gains an
`agent_fabro_tools_enabled: bool` parameter. The server reads
`run_state.spec.settings.run.agent.fabro_tools` from the stored run
before spawning `__run-worker`, then issues the worker JWT with either
`["run:worker"]` or `["run:worker", "agent:run_tools"]` accordingly.
`WorkerScopeSet::run_worker()` loses its `#[cfg(test)]` gate so it's
available in production paths.
**CLI worker** (`fabro-cli`): `FabroRunToolServices` construction is now
gated on `run_spec.settings.run.agent.fabro_tools` rather than being
unconditional. The resolved run spec already carries the setting, so no
env-var parsing is needed in the runner.
**Tests**: The single monolithic
`worker_command_always_sets_worker_token_env` test is replaced by two
focused tests — one confirming the default scope is `["run:worker"]`
only, and one confirming the opt-in scope includes `agent:run_tools`.
Shared assertion logic is extracted into
`assert_worker_command_passes_token_only_by_env` and
`worker_token_claims` helpers. Config resolver tests cover default,
explicit true/false, and layer-override behavior.
**Docs**: `[run.agent]` description and reference tables are updated; a
new `run-configuration.mdx` section explains the opt-in semantics before
the existing `[run.agent.mcps]` section.
### Plan Summary
- 1. Add `fabro_tools` to resolved and layered run config, with resolver
tests.
- 2. Gate worker JWT scope and pass setting from stored run state into
`worker_command`.
- 3. Gate CLI `FabroRunToolServices` construction on the resolved
setting.
- 4. Update docs generator sample and public reference/execution docs.
- 5. Full verification pass (nextest, fmt, clippy).
### Fabro Details
<details>
<summary>Ran 9 stages in 54m 4s for $15.21</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 4s | – | 0 |
| preflight_lint | 2m 18s | – | 0 |
| implement | 28m 5s | $10.58 | 0 |
| simplify_opus | 12m 4s | $2.86 | 0 |
| simplify_gpt | 5m 19s | $1.77 | 0 |
| verify | 3m 37s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **54m 4s** | **$15.21** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: fabro-agent <agent@fabro.local>
|
||
|
Bryan Helmkamp
|
c6356cbd77
|
feat: improve run board, thread, and MCP create flows (#347)
## Summary This branch improves several run-management surfaces that agents and users rely on: archived runs now stay visible and ordered correctly in the board view, pair-session messages appear in the stage Thread tab, and the `fabro_run_create` MCP tool accepts the workflow-string shorthand it advertises. ## Changes - Updates the web board cache invalidation and archived-column handling so archive/unarchive actions refresh both active and archived board queries and keep archived runs in a predictable column position. - Adds pair user/system message events to stage activity parsing, Thread rendering, search, details, and DNA timeline items. - Aligns `fabro_run_create` MCP runtime deserialization and `tools/list` schema so each run entry may be either a workflow string or a full create spec object. ## Test Plan - `cargo nextest run -p fabro-tool -p fabro-mcp-server` - `cargo nextest run -p fabro-cli stdio_server_initializes_and_lists_run_tools mcp_create_string_shorthand_deserializes_before_auth mcp_create_validation_errors_happen_before_auth_or_network mcp_create_and_search_manage_real_runs_with_cli_auth` - `cargo +nightly-2026-04-14 fmt --check --all` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
fabro-sh-0530[bot]
|
f5ec711a2c
|
Stage-based pairing API and fabro_run_pair MCP tool (#344)
Some checks are pending
Rust / Clippy (push) Waiting to run
Rust / Generated Docs (push) Waiting to run
Rust / Test (Linux) (push) Waiting to run
Rust / Test (macOS) (push) Waiting to run
Rust / Format (push) Waiting to run
TypeScript / Build (push) Waiting to run
TypeScript / Typecheck (push) Waiting to run
TypeScript / Test (push) Waiting to run
## Summary
Run pairing previously required callers to supply an opaque
`agent_session_id` alongside a `stage_id` to start or target a pair
session. This leaked an internal runtime identifier across the public
HTTP API, generated TypeScript client, and would have bled into any MCP
tooling. This PR removes that coupling: the public pair API now
identifies targets by `StageId` alone, the server resolves the live
session internally, and a new `fabro_run_pair` MCP tool exposes the full
pair lifecycle without ever seeing session identifiers.
### What changed
**Public contract simplification** (`fabro-types`, OpenAPI, generated TS
client)
- `PairTarget` is now `{ stage_id, node_label }` — `node_id`, `visit`,
`agent_session_id`, `provider`, and `model` are removed.
- `PairStartRequest` accepts `{ stage_id }` instead of `{ target:
PairTargetSelector }`.
- `PairTargetSelector` and `PairTranscriptModel` types are deleted
entirely.
- `PairMessageRecord.target` (selector) replaced by
`PairMessageRecord.stage_id`.
- `PairTranscriptAssistantMessage.model` field removed.
- `MAX_PAIR_MESSAGE_BYTES` extracted as a public constant shared between
the server handler and the MCP tool.
**Internal session binding** (`SteeringHub`, server projection)
- `ActivePair` now carries `session_id: String` separately from the
public `PairRecord`. This preserves the stale-session protection that
previously relied on `target.agent_session_id`.
- Transcript matching changed from `(session_id AND stage_id)` to
`stage_id` within the already-scoped pair window sequence range —
simpler and sufficient.
- `active_api_targets` deactivation no longer does a per-target
`agent_session_id` check; it relies on the `active_steerable_stages`
lease already doing that guard.
**New `fabro_run_pair` MCP tool** (`fabro-mcp-server`)
- Actions: `status`, `start`, `get`, `message`, `end`, `transcript`.
- Validation happens before any network call; missing `run_id`, missing
`stage_id` for `start`, missing/invalid `pair_id` for other actions, and
overlong message text all return clean tool-level errors.
- `strum::IntoStaticStr` on `RunPairAction` enables the
`parse_pair_id_for_action` helper to embed the action name in error
messages without a `match`.
- MCP result schema and serialized results are covered by leakage
assertions confirming none of the removed fields surface.
**Tests**
- Negative leakage assertions added to pair DTO tests, event round-trip
tests, control-protocol tests, server handler tests, MCP validation
tests, and MCP schema test.
- Tool count updated from 5 → 6 in all CLI MCP integration tests.
- Steering hub test renamed:
`pair_start_rejects_non_selected_or_missing_target` →
`pair_start_rejects_missing_target` (session-mismatch rejection is now
an internal concern).
### Fabro Details
<details>
<summary>Ran 9 stages in 60m 29s for $31.78</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 9s | – | 0 |
| preflight_lint | 2m 26s | – | 0 |
| implement | 33m 14s | $25.51 | 0 |
| simplify_opus | 15m 7s | $4.18 | 0 |
| simplify_gpt | 3m 46s | $2.08 | 0 |
| verify | 3m 9s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **60m 29s** | **$31.78** | **0** |
</details>
<details>
<summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15
edges)</summary>
```dot
digraph ImplementPlan {
graph [
goal="Implement and simplify",
model_stylesheet="
* { model: claude-opus-4-7; }
"
]
rankdir=LR
start [shape=Mdiamond, label="Start"]
exit [shape=Msquare, label="Exit"]
toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0]
preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0]
preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0]
fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3]
implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."]
simplify_opus [label="Simplify (Opus)", prompt="@prompts/simplify.md"]
simplify_gpt [label="Simplify (GPT-55)", prompt="@prompts/simplify.md", model="gpt-55"]
verify [label="Verify", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 2>&1 && cargo dev docs refresh 2>&1 && cargo dev docs check 2>&1", goal_gate=true, retry_target="fixup"]
fixup [label="Fixup", prompt="The verify step failed. Read the build output from context and fix all clippy lint warnings, test failures, and generated docs errors.", max_visits=3]
fmt [label="Format", shape=parallelogram, script="cargo +nightly-2026-04-14 fmt --all 2>&1", max_retries=0]
start -> toolchain
toolchain -> preflight_compile [condition="outcome=succeeded"]
toolchain -> exit
preflight_compile -> preflight_lint [condition="outcome=succeeded"]
preflight_compile -> exit
preflight_lint -> implement [condition="outcome=succeeded"]
preflight_lint -> fix_lints
fix_lints -> preflight_lint
implement -> simplify_opus -> simplify_gpt -> verify
verify -> fmt [condition="outcome=succeeded"]
verify -> fixup
fixup -> verify
fmt -> exit
}
```
</details>
⚒️ Generated with [Fabro](https://fabro.sh)
---------
Co-authored-by: Fabro <noreply@fabro.sh>
Co-authored-by: Bryan Helmkamp <bryan@brynary.com>
|
||
|
Bryan Helmkamp
|
296fbddec9
|
feat(api): add ask fabro session endpoints (#342)
## Summary Adds the run-backed API surface needed for a real Ask Fabro sidebar: run readiness metadata, detailed session projections, session-scoped event listing/attach streaming, and turn control that exposes durable turn IDs and machine-readable failures. ## What Changed - Extended the OpenAPI contract and regenerated Rust/TypeScript clients for `Run.ask_fabro`, `SessionDetail`, `SessionTurn`, paginated run sessions, session event APIs, and optional client-supplied `turn_id` values. - Updated `fabro-types` and `fabro-store` so durable `run.session.*` events project active turn state, transcript messages, and the latest owning run event sequence. - Implemented server routing for session details, `/events`, `/attach`, turn conflict headers, typed turn failure codes, and cheap run readiness decoration across run responses. - Added browser helpers for POST turn streaming and session attach SSE parsing, plus an exported generated `sessionsApi`. ## Verification - `cargo +nightly-2026-04-14 fmt --check --all` - `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` - `cargo build --workspace` - `cargo test -p fabro-types run_session_turn_failed_defaults_code_for_old_events` - `cargo test -p fabro-store run_sessions::tests` - `cargo test -p fabro-api` - `cargo test -p fabro-server --features test-support --test it api::sessions` - `cargo test -p fabro-server --features test-support --test it api::runs` - `cd apps/fabro-web && bun test app/lib/session-stream.test.ts` - `cd apps/fabro-web && bun run typecheck` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 Codex (context unknown, medium reasoning) via [Codex](https://openai.com/codex/) |