Commit graph

44 commits

Author SHA1 Message Date
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>
2026-05-22 13:44:42 -04:00
Bryan Helmkamp
9bdf30ad86
refactor(hooks): centralize run location handling (#325)
## Summary
- Fix host command hooks to use the submitter/source directory instead
of a sandbox-only working directory.
- Introduce `HookExecutionContext` and `RunLocations` so host source,
sandbox work, and run scratch paths are explicit.
- Route lifecycle hooks and tool hooks through the shared hook execution
context instead of rebuilding cwd pairs at call sites.

## Test Plan
- `cargo nextest run -p fabro-hooks`
- `cargo check -p fabro-workflow --tests`
- `cargo +nightly-2026-04-14 fmt --package fabro-hooks --package
fabro-workflow --check`
- `cargo +nightly-2026-04-14 clippy -p fabro-hooks -p fabro-workflow
--all-targets -- -D warnings`

---------

Co-authored-by: Jess Martin <jessmartin@gmail.com>
2026-05-20 09:31:46 -04:00
Bryan Helmkamp
87950295bd
refactor(llm): split provider identity from adapters (#280)
## Summary

This PR separates provider identity from adapter behavior across the LLM
stack. Provider IDs now represent catalog rows and provider metadata,
while adapter/profile routing owns protocol behavior for Anthropic,
OpenAI, Gemini, and OpenAI-compatible providers.

## Changes

- Replace the shared `fabro_model::Provider` enum with open-ended
`ProviderId` catalog identity and typed `AdapterKind` metadata.
- Route auth, CLI, ACP, workflow, memory selection, profile
construction, and LLM client registration through catalog provider rows
instead of provider-ID fallbacks.
- Move API-key URL/header/env metadata into provider catalog/auth flows
and require configured provider rows for credential-backed clients.
- Simplify billing to `algorithm`-tagged OpenAI, Anthropic, and Gemini
shapes; OpenAI-compatible adapters bill through the OpenAI algorithm.
- Remove greenfield compatibility paths for old provider aliases, legacy
provider-tagged billing JSON, and the `openai_compatible`
pseudo-provider env fallback.
- Update fixtures and tests to exercise catalog-driven
Kimi/Zai/Minimax/Inception/custom OpenAI-compatible routing.

## Validation

- `cargo test --no-run -p fabro-model -p fabro-auth -p fabro-agent -p
fabro-workflow -p fabro-server -p fabro-llm -p fabro-api -p fabro-cli -p
fabro-store -p fabro-static`
- `cargo nextest run -p fabro-model -p fabro-auth -p fabro-agent -p
fabro-workflow -p fabro-server --no-fail-fast`
- `cargo nextest run -p fabro-llm -p fabro-api -p fabro-cli -p
fabro-store -p fabro-static --no-fail-fast`
- `cargo +nightly-2026-04-14 fmt --check --all`
- `git diff --check`
- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D
warnings`

---

[![Compound
Engineering](https://img.shields.io/badge/Compound_Engineering-6366f1)](https://github.com/EveryInc/compound-engineering-plugin)
🤖 Generated with GPT-5 via [Codex](https://openai.com/codex)
2026-05-16 13:13:41 -04:00
Bryan Helmkamp
1b6189ee32
docs(llm): finish configurable provider cleanup (#260)
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
## Summary

Finish phase 9 of the configurable LLM provider/model work by aligning
public docs, release notes, and guardrails with the implementation
already landed in phases 0-8.

- documents settings-driven providers/models, OpenAI-compatible gateway
examples, typed `extra_headers`, model `api_id`, controls, and per-speed
costs
- adds the 2026-05-13 changelog entry and provider string migration note
- updates the internal phase plan ledger to reflect current
implementation status
- adds a workspace policy test blocking direct production
`Catalog::builtin()` usage outside catalog owner/test code
- clarifies `Provider` as a built-in compatibility enum while open-ended
identity is `ProviderId`

## Verification

- `cargo nextest run -p fabro-dev --features dev --test it policy`
- `cargo dev docs check`
- `cargo nextest run -p fabro-model -p fabro-config -p fabro-auth -p
fabro-llm`
- `cargo build --workspace`
- `cargo nextest run --workspace` (5717 passed, 182 skipped, nextest
reported 1 leaky test)
- `cargo +nightly-2026-04-14 fmt --check --all`
- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D
warnings`
- `git diff --check`
2026-05-13 17:17:54 -04:00
Bryan Helmkamp
a81eb09e78
feat(llm): add catalog controls and speed billing (#249)
## Summary

This PR advances the catalog-driven LLM work from fabro-sh/fabro#210 by
making the resolved model catalog the source of truth for provider
registration, request control validation, and billing identity. Runs now
preserve canonical provider/model/speed identity through pricing and API
responses instead of collapsing billing around provider API aliases or
model IDs alone.

## What Changed

- Register LLM provider adapters from the resolved catalog, including
custom OpenAI-compatible providers and their credential resolution
paths.
- Validate effective model request controls, including run-level
defaults and node overrides, before dispatching LLM requests.
- Add catalog-aware billing lookup that prices canonical `ModelRef`
values, uses base model costs for standard speed, applies per-speed cost
overrides, and returns an unknown estimate instead of silently billing
zero for unsupported combinations.
- Move Anthropic Opus fast-mode pricing into the built-in catalog for
`claude-opus-4-6` and `claude-opus-4-7`.
- Thread the injected catalog and effective speed controls through
workflow billing, including API-mode and CLI-mode handlers.
- Update billing APIs, server aggregation, generated clients, and the
web billing view to expose provider/model/speed billing identity and
keep standard and fast usage in separate rows.

## Notes for Review

Billing lookup intentionally uses canonical catalog model IDs. Provider
`api_id` substitution remains limited to provider request construction,
so aliases can be used on the wire without changing billing identity.
Event conversion paths that do not have catalog access now preserve
token counts with a null dollar estimate rather than falling back to the
bootstrap catalog.

## Verification

- `cargo build -p fabro-api`
- `cd lib/packages/fabro-api-client && bun run generate`
- `cargo +nightly-2026-04-14 fmt --check --all`
- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D
warnings`
- `ulimit -n 4096 && cargo nextest run -p fabro-model -p fabro-workflow
-p fabro-server -p fabro-api -p fabro-cli --no-fail-fast`
- `ulimit -n 4096 && cargo nextest run --workspace --no-fail-fast`
- `cd apps/fabro-web && bun run typecheck`
- `cd apps/fabro-web && bun test`
- `git diff --check`

---

[![Compound
Engineering](https://img.shields.io/badge/Compound_Engineering-6366f1)](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>
2026-05-13 14:12:16 -04:00
Bryan Helmkamp
f1c247bc0f
fix(github): refresh installation tokens during workflows
Split PATs from installation access tokens so static configuration cannot accidentally store expiring ghs_* credentials. Workflow command and API agent stages now resolve GITHUB_TOKEN lazily from a refreshable source, while CLI agent stages surface their launch-time refresh limitation.
2026-05-06 07:15:18 -04:00
Bryan Helmkamp
e50df2b58b
feat(command): distinguish cancelled commands from timeouts
Represent command termination explicitly across sandbox results, events,
run projections, API types, and the run stage UI. This removes the fake
-1 exit code path for timeout/cancel and lets consumers tell cancelled
commands apart from timed-out commands.
2026-04-30 22:45:37 -04:00
Bryan Helmkamp
ca56c15f2f
refactor(llm): return Self from Client::from_source
Let callers decide whether to wrap in Arc. Also consolidates the two
state() fetches in build_pr_body into one.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-23 21:03:21 -04:00
Bryan Helmkamp
ec3d65928f
style(rustfmt): format remaining llm refactor files 2026-04-23 19:51:45 -04:00
Bryan Helmkamp
cb14dc43d1
refactor(llm): use credential sources and split run services 2026-04-23 18:54:27 -04:00
Bryan Helmkamp
e0b2d71668
refactor(unwrap): clear non-test workspace warnings 2026-04-19 20:56:38 -04:00
Bryan Helmkamp
ad0d532691
chore(clippy): require reasons on allow attributes
Enable clippy::allow_attributes_without_reason at the workspace level.
Add concise, callsite-specific reasons to existing allow attributes, including generated code paths.
2026-04-19 20:24:24 -04:00
Bryan Helmkamp
e8ad12fc30 fix: simplify fabro-http crate and fix correctness issues
- Replace unwrap_or_default() with expect() in hooks/llm HTTP client
  builders — Default silently discards all config (timeouts, TLS, proxy)
- Route fabro-mcp through fabro_http instead of raw reqwest, respecting
  FABRO_HTTP_PROXY_POLICY for MCP HTTP transport connections
- Deduplicate HttpClientBuilder / BlockingHttpClientBuilder via macro
- Extract helpers for repeated http_client error handling in diagnostics
  and web_auth
- Remove duplicate test_http_client() in fabro-cli and fabro-llm

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-12 12:20:55 -04:00
Bryan Helmkamp
3b2cffceaf refactor(http): centralize reqwest behind fabro-http
Add the shared fabro-http transport crate and route hand-written HTTP client construction through it.

Use FABRO_HTTP_PROXY_POLICY for test no-proxy defaults, remove direct reqwest deps from ordinary crates, and add clippy bans for raw reqwest entrypoints.
2026-04-12 11:48:54 -04:00
Bryan Helmkamp
6a87f0a071 fmt: apply nightly rustfmt after merge
Restore a clean nightly rustfmt baseline on the merged main branch so
cargo +nightly fmt --check --all passes again after bringing in
origin/main.
2026-04-11 13:43:30 -04:00
Bryan Helmkamp
007cfed240 refactor: remove backwards-compat error type aliases
No production deployments exist, so there's no need for migration shims.
Remove all six backwards-compat type aliases (AgentError, SdkError,
CoreError, GraphvizError, StoreError, FabroError) and migrate ~880
callsites to use the canonical Error name directly within each crate,
or qualified imports (e.g., `use fabro_llm::Error as LlmError`) for
cross-crate references. Also fix a pre-existing absolute-path clippy
lint in fabro-server error.rs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-11 12:51:42 -04:00
Bryan Helmkamp
5eeacd7864 fmt 2026-04-11 11:27:46 -04:00
Bryan Helmkamp
12ada82b53 refactor: simplify template migration code
- Skip MiniJinja parse+render for plain-text strings (no {{ / {% / {#)
- Remove dead VariableExpansionTransform type alias
- Add From<TemplateError> for FabroError, replace manual map_err with ?
- Extract resolve_prompt_and_model helper in hooks executor

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-11 11:16:15 -04:00
Bryan Helmkamp
5ed04c3c57 feat(template): unify workflow and config template syntax
Add a shared MiniJinja-based template crate and migrate workflow prompts,
imports, hooks, and InterpString env references to the new {{ ... }}
syntax. This also threads typed run inputs through workflow rendering and
updates docs and tests to match the new templating model.
2026-04-11 10:58:50 -04:00
Bryan Helmkamp
98df4a82c9 refactor(settings): remove bridge shims and restore contracts
Drop the dead sandbox and hook bridge helpers that no longer have runtime
callers, and move the run settings serde coverage into fabro-types where the
wire types live. Add the missing /api/v1/runs/:id/settings contract test so the
outward sparse settings shape stays covered after the refactor.
2026-04-10 08:35:08 -04:00
Bryan Helmkamp
4e7839c202 refactor(settings): stage 6.5b sweep ::v2:: prefix out of consumers
Final mechanical pass: replaces every remaining
`fabro_types::settings::v2::*` import path with
`fabro_types::settings::*` (or the appropriate submodule) across 53
files in 10 crates, then deletes the transitional
`pub mod v2 { pub use super::*; }` alias from
`fabro-types/src/settings/mod.rs`.

No functional changes — all touches are `sed s|settings::v2::|settings::|g`
on import statements and fully-qualified type paths. The v2
namespace is now fully gone; the authoritative module path is
`fabro_types::settings::{accessors, cli, duration, features, interp,
model_ref, project, run, server, size, splice_array, tree, version,
workflow}`.

All 3,758 workspace tests pass. `cargo fmt --check --all` and
`cargo clippy --workspace -- -D warnings` are clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 18:42:05 -04:00
Bryan Helmkamp
581e063883 refactor(settings): stage 6.3b promote hook + project runtime types
Two more legacy runtime type modules deleted from `fabro-types`:

**project.rs** (19 LOC): `ProjectSettings` was a trivial one-field
struct with a `pub use` re-export in `fabro-config/src/project.rs`.
Nothing else referenced it. Deleted outright; `fabro-config/src/project.rs`
drops the re-export and fixes up a `v2::` import path.

**hook.rs** (230 LOC): `HookDefinition`, `HookEvent`, `HookSettings`,
`HookType`, `TlsMode` plus the `resolved_hook_type` / `is_blocking`
/ `timeout` / `runs_in_sandbox` / `effective_name` behavior methods
are **moved** (not just re-exported) into
`fabro-hooks/src/config.rs`. They're runtime shapes owned by the
hook executor, so they belong in the consumer crate.

`bridge_hook` (and its private `resolve_hook_type` /
`bridge_hook_event` helpers) also moved from
`fabro-types/src/settings/v2/to_runtime.rs` into
`fabro-hooks/src/config.rs`, because the target type is now local
to `fabro-hooks`. `fabro-workflow/src/operations/start.rs` now
imports `bridge_hook` from `fabro_hooks::config::bridge_hook`
instead of the v2 `to_runtime` module.

`fabro-hooks/src/types.rs` re-export of `HookEvent` switches from
the deleted `fabro_types::settings::hook` path to the new
crate-local `crate::config::HookEvent`.

`settings/mod.rs` drops `pub mod {hook, project}` and the
corresponding `pub use` re-exports. Three of the seven legacy
runtime type modules are now gone; four remain (mcp, run, sandbox,
server).

3,758 workspace tests pass. `cargo fmt --check --all` and
`cargo clippy --workspace -- -D warnings` are clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 18:07:04 -04:00
Bryan Helmkamp
eb7f99310c refactor(config): stage 6.4 delete fabro-config re-export shims
fabro-config no longer carries the legacy pass-through shims that
forwarded type re-exports from `fabro_types::settings::{hook,mcp,sandbox,
server,user,run}`. Consumers now import the runtime types directly
from `fabro_types::settings::*`, which is the only definitional
location.

Deleted files:
- `fabro-config/src/hook.rs` (1 LOC glob re-export)
- `fabro-config/src/mcp.rs`   (1 LOC glob re-export)
- `fabro-config/src/sandbox.rs` (~8 LOC re-export list)
- `fabro-config/src/server.rs`  (re-exports + `resolve_storage_dir`;
  the `resolve_storage_dir` helper moved to `fabro_config`'s crate root
  and takes `&SettingsFile` directly)

Shrunk files:
- `fabro-config/src/run.rs` lost the `ArtifactsSettings` /
  `CheckpointSettings` / `GitHubSettings` / `LlmSettings` /
  `MergeStrategy` / `PullRequestSettings` / `SetupSettings` re-export
  block and the unused `resolve_env_refs` helper. What remains is just
  the workflow TOML loader helpers (`parse_run_config`, `load_run_config`,
  `resolve_graph_path`).
- `fabro-config/src/user.rs` lost the `ClientTlsSettings` /
  `ExecSettings` / `OutputFormat` / `PermissionLevel` /
  `ServerSettings` re-export block. The settings-path helpers and
  legacy-config warning logic stay. `fabro-cli/src/user_config.rs`
  now imports `ClientTlsSettings` directly from fabro_types.

Callers updated to use the canonical paths:
- `fabro-agent/src/cli.rs` imports `{OutputFormat, PermissionLevel}`
  from `fabro_types::settings::user`; added `fabro-types` dep.
- `fabro-hooks/src/{config,types}.rs` re-export from
  `fabro_types::settings::hook`.
- `fabro-mcp/src/config.rs` re-exports from `fabro_types::settings::mcp`.
- `fabro-sandbox/src/daytona/mod.rs` re-exports from
  `fabro_types::settings::sandbox`.
- `fabro-server/src/{lib,jwt_auth,tls,serve,demo}.rs` +
  `tests/it/openapi_conformance.rs` import server types from
  `fabro_types::settings::server` and call `fabro_config::resolve_storage_dir`
  from the crate root.
- `fabro-workflow/src/{operations/start,pipeline/types,pipeline/pull_request}.rs`
  import sandbox / pull_request types from `fabro_types::settings::*`.

Build, clippy, fmt, and 3756 / 3756 tests pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 16:30:38 -04:00
Bryan Helmkamp
a1e0762eb0 refactor(workspace): satisfy clippy all-targets warnings 2026-04-05 14:37:32 -04:00
Bryan Helmkamp
8a2d00591b fix(test): remove hidden HTTP client startup overhead
Disable proxy discovery for the hot test HTTP clients so nextest no longer
pays macOS system proxy lookup on repeated reqwest client creation.

Also keep the approved OAuth loopback cleanup and replace GitHub test key
generation with a checked-in PEM fixture.
2026-04-04 21:25:51 -04:00
Bryan Helmkamp
ddc57d458c Rename SessionConfig to SessionOptions and McpServerConfig to McpServerSettings
Aligns naming with the convention that "Config" is for file-level configuration
while "Options" and "Settings" describe runtime parameters. Also applies
rustfmt formatting fixes in web_auth.rs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 06:47:42 -07:00
Bryan Helmkamp
f2729d22ef Clean up workspace clippy warnings 2026-03-30 11:27:25 -04:00
Bryan Helmkamp
c6313d74bc Use typed RunId across workflows 2026-03-30 09:20:11 -04:00
Bryan Helmkamp
9aff6530b4 Add publish = false to all crates to prevent accidental crates.io publish
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:09 -04:00
Bryan Helmkamp
038420d9c8 Replace mockito with httpmock in fabro-hooks, fabro-openai-oauth, and fabro-tracker
mockito's Server::new_async() triggers macOS SCDynamicStoreCreateWithOptions
via hyper-util (~300ms per test), which serializes on configd under workspace
concurrency and causes 4s+ timeouts. httpmock avoids this path entirely.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:09 -04:00
Bryan Helmkamp
7de491ce8a Enable 7 additional pedantic clippy lints
Enables char_lit_as_u8, collapsible_else_if, collapsible_if,
map_unwrap_or, match_same_arms, used_underscore_binding, and
if_not_else. Fixes all violations: combines duplicate match arms,
renames underscore-prefixed bindings that are actually used, rewrites
if-not-else patterns, and applies map_or where appropriate.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
752d04cbcb Enable additional pedantic clippy lints and fix violations
Enables cast_possible_truncation, cast_sign_loss, items_after_statements,
needless_pass_by_value, return_self_not_must_use, uninlined_format_args,
unreadable_literal, and unnested_or_patterns. Keeps doc_markdown disabled.

Replaces unsafe `as` casts with try_from().unwrap() throughout, using
#[allow] only for f64-to-integer casts which have no try_from equivalent.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
1d304b771a Enable clippy pedantic lints and restriction lints workspace-wide
Adopts uv's clippy lint configuration: pedantic group at warn priority,
with noisy lints allowed, plus restriction lints for print/dbg/exit/use_self.
Fixes all violations across the workspace.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
97214c7d83 Apply rustfmt 2024 style edition across workspace
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
0b90305432 Enforce no-inline-qualified-paths via clippy absolute_paths lint
Add clippy.toml with absolute-paths-max-segments = 2 (allowing std/core/alloc)
and enable the absolute_paths = "warn" lint workspace-wide. Fix all ~300
violations across the codebase: replace 3+-segment inline paths with use
statements so call sites read as operations::create() rather than
fabro_workflows::operations::create(). The demo module gets an allow
attribute since it constructs many API types by design.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
41e1809b21 Enforce no-wildcard-imports via clippy workspace lint
Configure clippy `wildcard_imports = "warn"` at the workspace level and
opt all 28 crates in via `[lints] workspace = true`. Fix the three
production glob imports that triggered warnings: fabro-sandbox
read_guard, fabro-cli main, and fabro-api demo module (allowed via
attribute since it constructs many API types by design). Document the
import style convention in CLAUDE.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 13:47:08 -04:00
Bryan Helmkamp
48c21ed521 Create fabro-types and rewire shared types 2026-03-29 13:47:08 -04:00
Bryan Helmkamp
4711a9eb48 Redesign fabro-model with LanguageModel trait, Catalog struct, and ModelRef (#121)
Introduce OOP API for the model catalog: LanguageModel trait with blanket
impl on ModelInfo, Catalog struct with typed methods (get, list,
default_for_provider, closest, build_fallback_chain, etc.), ModelRef enum
replacing ModelId, and Provider::OpenAiCompatible variant. Migrate all
callers across the workspace to use Catalog::builtin() and remove the old
free-function API.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 11:15:40 -04:00
brynary-fabro[bot]
cd7f0b1415 Support Anthropic fast mode (speed: fast) (#127)
This PR adds support for Anthropic's fast mode beta feature (`speed:
fast`), which enables up to 2.5x faster output for Claude Opus 4.6 at a
6x pricing premium. The implementation follows the same patterns
established by `reasoning_effort`, threading a new `speed:
Option<String>` field through the request/response pipeline from graph
stylesheet properties down through agent configuration, session
management, and the Anthropic provider adapter.

On the provider side, when `speed: "fast"` is set, the `ApiRequest`
struct now includes the `speed` field in the serialized JSON body, and
the `build_beta_header` function injects the required `anthropic-beta:
fast-mode-2026-02-01` header alongside any existing beta headers (cache,
interleaved thinking, etc.) without duplication. The response's
`usage.speed` field is parsed and propagated back through both streaming
and non-streaming paths into `StageUsage` and `Usage` types for
tracking.

Cost accounting applies a 6x multiplier in `compute_stage_cost` when
`speed == "fast"`, reflecting Anthropic's actual pricing differential.
The feature is configurable via stylesheet (`* { speed: fast; }`), which
gets wired through `SessionConfig` and prompt-mode `Request`
construction in the backend layer. New tests cover the API request
serialization, beta header injection, combined cache+fast-mode headers,
and the cost multiplier, while all existing test fixtures have been
updated with `speed: None` to maintain struct exhaustiveness.

### Fabro Details

<details>
<summary>Ran 9 stages in 58m 27s for $6.56</summary>

| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 0s | – | 0 |
| preflight_compile | 1m 20s | – | 0 |
| preflight_lint | 14s | – | 0 |
| implement | 47m 31s | $5.36 | 0 |
| simplify_opus | 7m 59s | $1.20 | 0 |
| simplify_gpt | 0s | – | 0 |
| verify | 25s | – | 0 |
| fmt | 1s | – | 0 |
| **Total** | **58m 27s** | **$6.56** | **0** |

</details>

<details>
<summary>Ran <code>ImplementAndSimplify.fabro</code> (12 nodes and 15
edges)</summary>

```dot
digraph ImplementAndSimplify {
    graph [
        goal="Implement and simplify",
        model_stylesheet="
            * { backend: api; model: claude-opus-4-6;}
        "
    ]
    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 clippy -q --workspace -- -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-54)", prompt="@prompts/simplify.md", model="gpt-54"]
    verify            [label="Verify", shape=parallelogram, script="cargo clippy -q --workspace -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 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 and test failures.", max_visits=3]
    fmt               [label="Format", shape=parallelogram, script="cargo fmt --all 2>&1", max_retries=0]

    start -> toolchain
    toolchain -> preflight_compile [condition="outcome=success"]
    toolchain -> exit
    preflight_compile -> preflight_lint [condition="outcome=success"]
    preflight_compile -> exit
    preflight_lint -> implement [condition="outcome=success"]
    preflight_lint -> fix_lints
    fix_lints -> preflight_lint
    implement -> simplify_opus -> simplify_gpt -> verify
    verify -> fmt   [condition="outcome=success"]
    verify -> fixup
    fixup -> verify
    fmt -> exit
}

```

</details>

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

---------

Co-authored-by: Fabro <noreply@fabro.sh>
2026-03-21 14:37:42 -04:00
brynary-fabro[bot]
c81fd1740b Extract fabro-model crate from fabro-llm (#109)
This PR extracts a new `fabro-model` crate from `fabro-llm`, isolating
the model catalog, provider identity types, and model metadata into a
focused, lightweight package. The new crate contains `Provider`,
`ModelId`, `ModelInfo` (and related structs), and the full catalog API
(`get_model_info`, `list_models`, `default_model_from_env`,
`build_fallback_chain`, etc.) — with only `serde` and `serde_json` as
runtime dependencies, no async runtime required.

The extraction follows a clean boundary: `fabro-llm` now depends on
`fabro-model` and re-exports `Provider` and `ModelId` at its root so
existing `fabro_llm::Provider` usage remains valid without a migration.
The `ProviderAdapter` trait, `StreamEventStream`, and
`validate_tool_choice` stay in `fabro-llm` since they depend on async
streaming types. All seven consumer crates (`fabro-agent`, `fabro-api`,
`fabro-cli`, `fabro-hooks`, `fabro-workflows`, `fabro-validate`, and
`fabro-llm` itself) are updated to import catalog functions and provider
types directly from `fabro_model` rather than `fabro_llm::catalog` or
`fabro_llm::provider`.

The most impactful dependency reduction is in `fabro-validate`, which
previously pulled in all of `fabro-llm` (tokio, reqwest, the full async
runtime) just to perform catalog lookups and validate provider names. It
now depends solely on `fabro-model`, eliminating that heavyweight
transitive closure. All other consumers retain their `fabro-llm`
dependency for client and streaming functionality, but gain a precise
import path for catalog and identity concerns.

### Fabro Details

<details>
<summary>Ran 9 stages in 21m 16s for $5.47</summary>

| Stage | Duration | Cost | Retries |
|---|---|---|---|
| start | 0s | – | 0 |
| toolchain | 0s | – | 0 |
| preflight_compile | 1m 10s | – | 0 |
| preflight_lint | 12s | – | 0 |
| implement | 13m 29s | $3.81 | 1 |
| simplify_opus | 5m 41s | $1.66 | 0 |
| simplify_gpt | 0s | – | 0 |
| verify | 15s | – | 0 |
| fmt | 1s | – | 0 |
| **Total** | **21m 16s** | **$5.47** | **1** |

</details>

<details>
<summary>Ran <code>ImplementAndSimplify.fabro</code> (12 nodes and 15
edges)</summary>

```dot
digraph ImplementAndSimplify {
    graph [
        goal="Implement and simplify",
        model_stylesheet="
            * { backend: api; model: claude-opus-4-6;}
        "
    ]
    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 clippy -q --workspace -- -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-54)", prompt="@prompts/simplify.md", model="gpt-54"]
    verify            [label="Verify", shape=parallelogram, script="cargo clippy -q --workspace -- -D warnings 2>&1 && cargo nextest run --cargo-quiet --workspace --status-level fail 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 and test failures.", max_visits=3]
    fmt               [label="Format", shape=parallelogram, script="cargo fmt --all 2>&1", max_retries=0]

    start -> toolchain
    toolchain -> preflight_compile [condition="outcome=success"]
    toolchain -> exit
    preflight_compile -> preflight_lint [condition="outcome=success"]
    preflight_compile -> exit
    preflight_lint -> implement [condition="outcome=success"]
    preflight_lint -> fix_lints
    fix_lints -> preflight_lint
    implement -> simplify_opus -> simplify_gpt -> verify
    verify -> fmt   [condition="outcome=success"]
    verify -> fixup
    fixup -> verify
    fmt -> exit
}

```

</details>

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

---------

Co-authored-by: Fabro <noreply@fabro.sh>
2026-03-19 22:26:47 -04:00
Bryan Helmkamp
33e5a41cad Fix: Remove std::env::set_var/remove_var from tests (#101)
Introduce an Env trait in fabro-util so tests can inject a HashMap-backed
TestEnv instead of mutating process-global environment variables, which
is unsafe since Rust 1.66+ and causes flakiness in concurrent tests.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 13:09:46 -04:00
Bryan Helmkamp
6ebbad800d Move config type tests into fabro-config
Tests for types defined in fabro-config (HookEvent, HookDefinition,
HookConfig, McpServerConfig, McpTransport, etc.) now live alongside
their definitions rather than in the downstream re-exporting crates.

Tests for types that remain in fabro-hooks (HookContext, HookDecision,
PromptHookResponse) stay in fabro-hooks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 15:21:16 -04:00
Bryan Helmkamp
98e8a9b7f6 Fix fabro-config dependency inversion
Move config/data types from upstream crates (fabro-agent, fabro-mcp,
fabro-workflows, fabro-hooks) down into fabro-config so it becomes a
leaf crate depending only on fabro-util + external crates.

New modules in fabro-config:
- mcp.rs: McpServerConfig, McpTransport, McpServerEntry
- sandbox.rs: DaytonaConfig, ExeConfig, SshConfig, SandboxConfig, etc.
- hook.rs: HookEvent, HookDefinition, HookConfig, HookType, TlsMode
- run.rs: RunDefaults, WorkflowRunConfig, LlmConfig, SetupConfig, etc.
- project.rs: ProjectConfig, workflow discovery/resolution functions

Source crates re-export from fabro-config for backward compatibility.
Also removes stale strsim dep and moves toml to dev-deps in
fabro-workflows.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 15:17:55 -04:00
Bryan Helmkamp
6c3607440f Extract fabro-hooks crate from fabro-workflows
Move the self-contained hooks module (~2900 LOC) into its own crate to
clarify the dependency graph and make the hook system independently
reusable. The set_node convenience method is inlined at its two call
sites in parallel.rs since it depends on fabro-graphviz types.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 14:08:02 -04:00