mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-09-20 00:11:34 +00:00
3608 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
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
|
a64a58d567
|
fix: gate implement-plan PRs on CI checks | ||
|
Bryan Helmkamp
|
6cb3d03ade
|
feat(web): show rich hover popovers on waterfall rows
Replaces the native title tooltips on waterfall phase and stage rows with HoverCard popovers that surface the status pill, started timestamp, and live elapsed/duration. Promotes PopoverHeader, Rows, and Row from run-detail.tsx into components/ui.tsx so the waterfall and run header share one set of primitives, and lets HoverCard accept a className so a full-row block trigger can host the popover. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
14e2283fcd
|
feat(web): add Waterfall view to run events page
Adds a Waterfall mode to /runs/:id/events alongside the existing event log, selectable via a segmented toggle (URL-synced as ?view=, default waterfall). The waterfall renders run phases (Submitted, Queued, Initializing) derived from run.* events plus a row per stage with status-colored bars, and ticks the active stage's duration locally each second so wall_time_ms staleness doesn't freeze the display. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
ed5c1dc4f4
|
feat(web): list Teams, Discord, and Jira as coming soon integrations
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
5e3a30c1c3
|
feat(web): show duration breakdown in run header popover
Hovering the clock chip on a run header now reveals wall-clock-since-created alongside active (inference + tools) time. Also extends formatDurationMs to render hours and days for long-running runs instead of inflating minutes. |
||
|
fabro-releases[bot]
|
bcebc4508f | Bump version to 0.242.0-nightly.1 | ||
|
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
|
e67756c10c
|
style(web): bump run tab inner padding to 14px
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
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>
|
||
|
Bryan Helmkamp
|
37e527a115
|
chore: use GPT-55 for implement-plan implementation | ||
|
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
|
203ed5d029
|
docs: document agent pair and todo tools | ||
|
Bryan Helmkamp
|
8811054f99
|
docs(changelog): refresh recent product changes | ||
|
fabro-releases[bot]
|
fa474e36f7 | Bump version to 0.241.0-nightly.1 | ||
|
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
|
9df5c53bb5
|
feat: expand Ask Fabro example prompts to detailed text
Replace the four built-in Ask Fabro welcome prompts with more detailed prompt text covering errors, performance, run flow tracing, and workflow improvement recommendations. Card headings and descriptions are unchanged; only the verbatim prompt sent on click is expanded. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
7a0f536209
|
fix: tighten Ask Fabro sidebar markdown spacing
The assistant-ui markdown defaults (heading margins up to 32px, 20px paragraph margins, 24px list indent, 24px blockquote padding, 16px code padding) are tuned for the full-page Thread and waste space in the narrow sidebar column. Scope tighter spacing to .ask-fabro-sidebar for headings, paragraphs, lists, blockquotes, and code blocks. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
4df9e483ac
|
Merge remote-tracking branch 'origin/main' into ask-fabro-welcome-prompts | ||
|
Bryan Helmkamp
|
74f90c1123
|
fix: shrink Ask Fabro sidebar markdown heading sizes
The assistant-ui markdown defaults size headings up to 36px (h1), which dominated the narrow sidebar column. Scope smaller heading sizes to .ask-fabro-sidebar: H1 18px bold, H2/H3 14px bold, H4-H6 14px normal (no special styling). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
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
|
54329bdd98
|
feat: add welcome state with example prompts to Ask Fabro sidebar
Show a "How can I help?" heading and four example prompt cards on the empty Ask Fabro thread. Cards span four themes — errors, performance, key decisions, and suggested improvements. Each card is a ThreadPrimitive.Suggestion that sends its prompt on click, starting the session via the existing lazy ensureSession() flow. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.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
|
a8900c465d
|
feat: make the Ask Fabro sidebar resizable
Add a drag handle on the left edge of the docked Ask Fabro panel. The user can widen the panel up to 2x its default width and no narrower than the default. The chosen width persists across open/close. An `isResizing` flag on the layout context lets `<main>` and the steer bar drop their width transitions during a drag so the layout tracks the cursor instead of trailing it. Also bundles in-progress sidebar wiring: a collapsed tool-call summary renderer and the remark-gfm dependency for GitHub-flavored Markdown. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
5b5e0d83fd
|
fix: render Ask Fabro session responses
Handle the flattened session SSE event envelopes emitted by the API so assistant deltas are applied to the Ask Fabro runtime instead of being ignored. |
||
|
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-releases[bot]
|
3831c157fb | Bump version to 0.241.0-nightly.0 | ||
|
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/) |
||
|
fabro-sh-0530[bot]
|
54bc67017e
|
feat: Replace duration/elapsed fields with wall_time_ms and StageTiming (#343)
## Summary
Replaces the ambiguous `runtime_secs`, `elapsed_secs`, and `duration_ms`
timing fields on run/stage public API surfaces with explicit
`wall_time_ms` (elapsed clock time) and a `StageTiming` value object
that also carries `inference_time_ms`, `tool_time_ms`, and
`active_time_ms`.
This is a greenfield breaking change — no compatibility shims are
preserved.
### What changed
**API shape**
- `RunBillingStage.runtime_secs` → `RunBillingStage.timing: StageTiming`
- `RunBillingTotals.runtime_secs` → `RunBillingTotals.timing:
StageTiming`
- `RunSummary.timestamps.duration_ms` / `elapsed_secs` removed; a
top-level `timing: StageTiming | null` field added
- Stage list item `duration_secs` → `wall_time_ms`
**Web app (`apps/fabro-web`)**
- `run-billing.tsx`: `liveRuntimeSecs` → `liveWallTimeMs`; live ticking
now returns milliseconds and the footer total sums `wallTimeMs` across
rows
- `stage-sidebar.ts`: `duration_secs` → `wall_time_ms` for the per-stage
duration display
- `runs.ts`: `elapsed_secs` lookup replaced with `timing.wall_time_ms`
- `formatElapsedSecs` / `formatDurationSecs` call sites replaced with
`formatDurationMs`
**Lockfile / tooling**
- `@openapitools/openapi-generator-cli@2.20.2` added as a dev dependency
to `@qltysh/fabro-api-client` to support regenerating the TypeScript
client after schema edits; several transitive deps pulled in alongside
it.
### Design notes
- **Units are now consistent**: every timing value on run/stage surfaces
is in milliseconds; the old API mixed seconds (`runtime_secs`,
`elapsed_secs`) with milliseconds (`duration_ms`).
- **Live ticking** still works correctly: the in-flight billing row
computes `now - startedAt` in ms and sums across rows for the footer,
avoiding a server round-trip during a running stage.
- **`StageTiming.active_time_ms = inference_time_ms + tool_time_ms`** —
parallel work is summed, so run active time can exceed wall time.
- Subsystem-internal `duration_ms` fields (sandbox setup, devcontainer
lifecycle, hooks) are intentionally left unchanged; only public
run/stage timing surfaces are affected.
### Fabro Details
<details>
<summary>Ran 9 stages in 115m 53s for $108.50</summary>
| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 1s | – | 0 |
| preflight_compile | 2m 6s | – | 0 |
| preflight_lint | 2m 18s | – | 0 |
| implement | 80m 53s | $101.97 | 0 |
| simplify_opus | 21m 35s | $4.09 | 0 |
| simplify_gpt | 5m 1s | $2.44 | 0 |
| verify | 3m 11s | – | 0 |
| fmt | 3s | – | 0 |
| **Total** | **115m 53s** | **$108.50** | **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
|
178adf15ea
|
feat(web): add Context tab to the stage detail view (#340)
## What Adds a **Context** tab to the stage detail view (`/runs/:id/stages/:stageId`), beside the existing primary tab (Thread / Logs / …) and Debug tab. It surfaces a stage's *deliberate per-visit outputs* — the data the workflow author makes a stage write into shared context, plus the routing hints it emitted: - **Routing** — `preferred_label` and `suggested_next_ids` - **Context writes** — author-set `context_updates` keys This data flow was previously invisible in the UI, which made it hard to debug "why did the next stage get the wrong input / take the wrong edge". ## Why no backend change The per-visit `stage.completed` event already carries `context_updates`, `preferred_label`, and `suggested_next_ids`, and the web UI already fetches it via `useRunStageEvents`. The checkpoint's `node_outcomes` map was rejected as a source: it is keyed by `node_id` only, so it is lossy across visits (`implement@2` would overwrite `implement@1`). ## How - `extractStageContext` (in `stage-renderers/helpers.ts`) reads the `stage.completed` event and filters `context_updates` through an engine-key denylist: `last_stage`, `last_response`, `response.*`, `internal.*`, `current.*`, `command.output`, `human.gate.*`, `parallel.*`. Those are bookkeeping or already shown in the stage's primary tab. - It returns `null` when nothing is left, so the tab stays **conditional** — same pattern as Thread/Logs. It only appears when a stage actually wrote something deliberate. - New `stage-context.tsx` renders the result, reusing `CodeBlock` / `JsonBlock`. - `run-stages.tsx` gains a dynamic `availableTabs` list; `effectiveTab` falls back to `primary` gracefully when the Context tab is absent. ## Verification - `bun run typecheck` clean, `bun test` — 412 pass / 0 fail (4 new tests for the denylist + routing extraction). - Live run `01KS5WBZAE7K8321NHR7KFAHF9` (`context-demo` workflow): the `emit@1` stage emitted `demo.greeting` / `demo.answer` / `demo.payload` plus `preferred_label: "Done"` and `suggested_next_ids: ["exit"]`, and the Context tab rendered them correctly. ## Notes - The second commit adds a small `context-demo` workflow used for that verification — kept separate so it can be dropped independently. - Known limitations (acceptable for v1): data is read from `stage.completed` only, so a stage ending in `stage.failed` shows no tab; parallel stages write `parallel.*` directly to context (denylisted), so they show no tab. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bryan Helmkamp
|
fb2174c7d0
|
feat(agent): expose Fabro run tools in sessions (#339)
## Summary API-backed Fabro agent sessions can now use the same five run-control tools that were previously MCP-only, while the server uses a single scoped `FABRO_WORKER_TOKEN` path for worker authorization. This lets server-dispatched API agents create, gather, inspect, and interact with runs without reintroducing a separate delegated run-agent token or leaking credentials into sandboxed child environments. ## Changes - Moved the reusable run-tool implementation into the new `fabro-tool` crate so MCP and API agent backends share the same tool schemas and client behavior. - Registered the five `fabro_run_*` tools for API-mode agents, with ACP sessions continuing to omit those tools. - Replaced `FABRO_RUN_AGENT_TOKEN` with scoped worker-token auth: base worker tokens keep same-run access, and `run:worker agent:run_tools` tokens can call the run-control API across runs. - Added server auth guards for run-tool actors and run-scoped-or-run-tools routes, then applied them only to the routes used by the run-tool client backend. - Kept `FABRO_WORKER_TOKEN` scrubbed from sandbox commands, hooks, ACP subprocesses, MCP env providers, and other child tool environments. ## Testing - `cargo nextest run -p fabro-server worker_token principal_middleware spawn_env --no-fail-fast` - `cargo nextest run -p fabro-cli runner --no-fail-fast` - `cargo nextest run -p fabro-workflow agent_run --no-fail-fast` - `cargo nextest run -p fabro-static --no-fail-fast` - `cargo +nightly-2026-04-14 fmt --check --all` - `cargo +nightly-2026-04-14 clippy -p fabro-server -p fabro-cli -p fabro-static --all-targets -- -D warnings` - `git diff --check` --- [](https://github.com/EveryInc/compound-engineering-plugin) 🤖 Generated with GPT-5 via [Codex](https://openai.com/codex) |