brynary-fabro[bot] 4df605e561 Map reasoning_effort to Anthropic output_config.effort (#115) ... This PR adds support for mapping the unified `reasoning_effort` field to Anthropic's `output_config.effort` API parameter, which is the recommended way to control thinking depth for Claude Opus 4.6 and Sonnet 4.6 models. Previously, the Anthropic provider silently dropped `reasoning_effort` from requests, while the OpenAI provider already correctly mapped it to `reasoning: { effort }`. This inconsistency meant that workflow nodes setting `reasoning_effort: "high"` (the default) had no effect when routing through Anthropic. The change adds an `output_config: Option<serde_json::Value>` field to the `ApiRequest` struct with `skip_serializing_if = "Option::is_none"` to ensure it's omitted when not set, then populates it in `build_api_request` by transforming `request.reasoning_effort` into `{"effort": <value>}` — mirroring the pattern used in the OpenAI provider. All existing `ApiRequest` constructions in tests are updated to include `output_config: None`. The PR also takes the opportunity to refactor the test module by extracting a `make_base_request()` helper, which reduces boilerplate in `build_api_request_omits_whitespace_only_system_prompt` and `make_request_with_format` and makes the two new tests (`build_api_request_maps_reasoning_effort_to_output_config` and `build_api_request_omits_output_config_when_no_reasoning_effort`) easy to read. All existing provider tests continue to pass and no new Clippy warnings are introduced. ### Fabro Details <details> <summary>Ran 9 stages in 10m 28s for $1.48</summary> | Stage | Duration | Cost | Retries | |---|---|---|---| | start | 0s | – | 0 | | toolchain | 0s | – | 0 | | preflight_compile | 1m 8s | – | 0 | | preflight_lint | 12s | – | 0 | | implement | 2m 13s | $0.49 | 0 | | simplify_opus | 4m 45s | $0.99 | 0 | | simplify_gpt | 0s | – | 0 | | verify | 1m 40s | – | 0 | | fmt | 1s | – | 0 | | **Total** | **10m 28s** | **$1.48** | **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>		2026-03-19 22:49:16 -04:00
..
crates	Map reasoning_effort to Anthropic output_config.effort (#115)	2026-03-19 22:49:16 -04:00
packages/fabro-api-client	Designate retros as experimental, disable by default via [features] flag	2026-03-15 20:36:32 -04:00