mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-09-12 23:02:41 +00:00
Fabro
parent
365d8c4981
commit
2dc61f8673
5 changed files with 264 additions and 116 deletions
359
run.json
359
run.json
|
|
@ -516,7 +516,7 @@
|
|||
"kind": "running"
|
||||
},
|
||||
"status_updated_at": "2026-05-21T22:36:05.837824Z",
|
||||
"last_event_at": "2026-05-21T23:20:10.785665Z",
|
||||
"last_event_at": "2026-05-21T23:20:19.788123Z",
|
||||
"pending_control": null,
|
||||
"checkpoints": [
|
||||
{
|
||||
|
|
@ -1480,9 +1480,9 @@
|
|||
}
|
||||
},
|
||||
{
|
||||
"seq": 0,
|
||||
"seq": 825,
|
||||
"checkpoint": {
|
||||
"timestamp": "2026-05-21T23:20:14.567384Z",
|
||||
"timestamp": "2026-05-21T23:20:19.787725Z",
|
||||
"current_node": "fmt",
|
||||
"completed_nodes": [
|
||||
"start",
|
||||
|
|
@ -1497,50 +1497,78 @@
|
|||
],
|
||||
"node_retries": {},
|
||||
"context_values": {
|
||||
"graph.rankdir": "LR",
|
||||
"internal.node_visit_count": 1,
|
||||
"thread.toolchain.current_node": "preflight_compile",
|
||||
"graph.goal": "# Plan: Compute LLM cost on-read for in-flight stages\n\n## Context\n\nOn the run billing page (`/runs/{id}/billing`), an active stage shows token\nusage but no dollar cost — cost renders as `—` until the stage completes.\n\nRoot cause: while a stage runs, `AgentMessage` events carry usage built by\n`billed_token_counts_from_llm` (`fabro-workflow/src/outcome.rs:43`), which\nhard-codes `total_usd_micros: None`. Dollar cost is only computed by\n`billed_model_usage_from_llm` (`outcome.rs:14`) — which needs the pricing\n`Catalog` — and that runs only on `StageCompleted`/`PromptCompleted`/`StageFailed`.\nSo an in-flight stage's `StageProjection.usage.total_usd_micros` stays `None`.\n\nFix: price stages whose cost is `None` when the billing rollup is built for a\nread request, using the model + token counts already in the projection. The\nwire contract is unchanged (`total_usd_micros` is already nullable everywhere)\nand the frontend already renders whatever value comes back — no UI change.\n\n## Decisions\n\n- **Price any stage with `total_usd_micros == None`**, not just in-flight ones.\n Completed stages with unpriceable providers (`BillingPolicy::None`) return\n `None` again — harmless; no need to thread `StageState`.\n- **No \"estimated\" label.** Cost-so-far is exact for tokens consumed so far,\n matching the already-unlabeled live token counts and ticking runtime.\n- **Aggregate billing stays finalized-only.** The `BillingAccumulator` call\n sites pass `None` so a run's running estimate is never folded into org-wide\n totals (avoids double-count when the run later finalizes).\n- Per-stage rows, `totals`, and `by_model` are all priced from the same source\n so the billing page stays internally consistent.\n\n## Changes\n\n### 1. `lib/crates/fabro-model/src/billing.rs`\n\n- Add `BilledTokenCounts::token_counts(&self) -> TokenCounts` — drops\n `total_tokens`/`total_usd_micros`, keeps the five disjoint buckets.\n- Add `Catalog::price_tokens(&self, model: &ModelRef, tokens: &TokenCounts) -> Option<i64>`\n next to `pricing_for`/`billing_facts_for`. Body mirrors the cost lines of\n `billed_model_usage_from_llm`: build `ModelBillingFacts` via\n `billing_facts_for`, assemble `ModelBillingInput { ModelUsage { model, tokens }, facts }`,\n then `pricing_for(model).and_then(|p| p.bill(&input)).map(|a| a.0)`. Returns\n `None` when the provider has no billing policy.\n\n### 2. `lib/crates/fabro-workflow/src/billing_rollup.rs`\n\n- Change signature to\n `billing_rollup_from_projection(projection: &RunProjection, catalog: Option<&Catalog>)`.\n- Add a module-private helper `stage_usage_with_cost(catalog, stage) -> BilledTokenCounts`:\n clone `stage.usage`; if `total_usd_micros.is_none()` and both `catalog` and\n `stage.model` are present, set it via `catalog.price_tokens(model, &usage.token_counts())`.\n- In the loop, compute `priced` once per stage and use it in place of\n `&stage.usage` for the `is_zero` check, `row.billing.add_counts`,\n `totals.add_counts`, and `model_entry.billing.add_counts`.\n- Update the existing tests to pass `None`; add one new test: an in-flight\n stage (no `completion`, non-zero `usage` with `total_usd_micros: None`, a\n builtin `model`) yields `Some(..)` cost on the stage row and in `totals` when\n called with `Some(Catalog::builtin())`.\n\n### 3. Call sites of `billing_rollup_from_projection`\n\n- `lib/crates/fabro-server/src/server/handler/billing.rs:82` — bind\n `let catalog = state.catalog();` (returns `Arc<Catalog>`) and pass\n `Some(&catalog)`.\n- `lib/crates/fabro-server/src/server.rs` (2 aggregate-billing sites) — pass `None`.\n- `lib/crates/fabro-workflow/src/pipeline/finalize.rs` (4 sites) — pass `None`\n (stages already priced at completion; pricing would be a no-op anyway).\n\nNo changes to `fabro-api.yaml`, the generated clients, or `apps/fabro-web`.\n\n## Out of scope / known limitation\n\nIn-flight **prompt** stages have no `model` until `PromptCompleted` (only\n`AgentMessage` sets `stage.model` mid-run), so they still show `—` while\nrunning. Acceptable: prompt stages are a single short LLM call. The bug report\nconcerns agent stages, where `model` is available.\n\n## Verification\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — new + updated unit tests pass.\n- `cargo nextest run -p fabro-server billing` — handler conformance still passes.\n- `cargo build --workspace` and `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings`.\n- Manual: `fabro server start` + `cd apps/fabro-web && bun run dev`, start a\n workflow with an agent stage, open `/runs/{id}/billing` mid-run — the active\n stage row and totals show a non-`—` dollar amount that grows with tokens.\n",
|
||||
"internal.retry_count.verify": 0,
|
||||
"thread.start.current_node": "toolchain",
|
||||
"response.simplify_gpt": "Implemented review cleanup on top of the billing cost-on-read changes.\n\nWhat changed:\n- Removed `BilledTokenCounts::ensure_priced`, which was an extra thin helper only used by rollup code.\n- Renamed `to_token_counts()` to `token_counts()` to match the requested API and nearby accessor style.\n- Updated `billing_rollup` pricing helper to avoid cloning stage usage unless a missing cost can actually be priced:\n - borrows existing usage for finalized/already-priced/no-catalog/no-model/unpriceable cases\n - only clones when setting a computed `total_usd_micros`\n\nReview outcome:\n- The parallel review agents did not return actionable findings.\n- I applied the above cleanup for reduced abstraction and less per-read work.\n\nVerification passed:\n- `cargo nextest run -p fabro-workflow billing_rollup`\n- `cargo nextest run -p fabro-server billing`\n- `cargo +nightly-2026-04-14 clippy -q -p fabro-model -p fabro-workflow -p fabro-server --all-targets -- -D warnings`\n\nCurrent working tree has modifications in:\n- `lib/crates/fabro-model/src/billing.rs`\n- `lib/crates/fabro-workflow/src/billing_rollup.rs`",
|
||||
"thread.implement.current_node": "simplify_opus",
|
||||
"last_stage": "simplify_gpt",
|
||||
"internal.retry_count.start": 0,
|
||||
"failure_signature": "",
|
||||
"internal.retry_count.simplify_gpt": 0,
|
||||
"graph.model_stylesheet": "\n * { model: claude-opus-4-7; }\n ",
|
||||
"current_node": "fmt",
|
||||
"thread.simplify_opus.current_node": "simplify_gpt",
|
||||
"internal.retry_count.preflight_lint": 0,
|
||||
"thread.preflight_lint.current_node": "implement",
|
||||
"internal.fidelity": "compact",
|
||||
"last_response": "Implemented review cleanup on top of the billing cost-on-read changes.\n\nWhat changed:\n- Removed `BilledTokenCounts::ensure_priced`, which was an extra thin helper only used by rollup code.\n- Renamed `",
|
||||
"thread.preflight_compile.current_node": "preflight_lint",
|
||||
"response.simplify_opus": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_counts()` → `to_token_counts()`** (`fabro-model/src/billing.rs`)\n - Quality finding: original name read like a field accessor and hid the fact that the conversion is lossy (drops `total_tokens` and `total_usd_micros`). The `to_` prefix is the established Rust convention for lossy conversions.\n\n2. **Moved pricing logic into `BilledTokenCounts::ensure_priced(catalog, model)`** (`fabro-model/src/billing.rs` + `fabro-workflow/src/billing_rollup.rs`)\n - Quality finding: the previous `stage_usage_with_cost` helper cloned `BilledTokenCounts` across a crate boundary and directly poked the private `total_usd_micros` field, leaking knowledge of how to price a `BilledTokenCounts` out of `fabro-model`. The new method encapsulates that logic next to `add_billed_usage` / `replace_with_billed_usage`, and the rollup-side helper is now a 3-line wrapper.\n\n### Considered and skipped\n\n- **Reuse #1 (refactor `billed_model_usage_from_llm` to use `price_tokens`)** — the \"duplicated\" pricing tail is 3 lines and the surrounding error-vs-option shapes don't compose cleanly. Refactoring adds more indirection than it removes.\n- **`Option<&Catalog>` parameter sprawl** — 6 of 7 call sites pass `None`, but splitting into two functions doubles the public surface for marginal benefit; the single signature is fine.\n- **`pricing_for` memoization across stages** — real but minor (a few `String` clones per stage on a polled endpoint). Worth doing if the path ever shows up in profiles; not justified at the cost of HashMap setup for this fix.\n- **`Cow::Borrowed` for the usage clone** — `BilledTokenCounts` is ~64 bytes of POD; no heap allocation.\n- **Bare `i64` return from `price_tokens`** — matches the established `total_usd_micros: Option<i64>` convention used throughout the codebase.\n\n### Verified\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — 4/4 pass (including the new in-flight pricing test).\n- `cargo nextest run -p fabro-model billed_token_counts` — 5/5 pass.\n- `cargo nextest run -p fabro-server billing` — 7/7 pass.\n- `cargo build --workspace` — clean.\n- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` — clean.\n- `cargo +nightly-2026-04-14 fmt --check --all` — clean.",
|
||||
"outcome": "succeeded",
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126",
|
||||
"internal.thread_id": "verify",
|
||||
"internal.retry_count.toolchain": 0,
|
||||
"internal.work_dir": "/home/daytona/workspace/fabro",
|
||||
"internal.retry_count.simplify_opus": 0,
|
||||
"thread.verify.current_node": "fmt",
|
||||
"internal.retry_count.fmt": 0,
|
||||
"failure_class": "",
|
||||
"thread.simplify_gpt.current_node": "verify",
|
||||
"thread.toolchain.current_node": "preflight_compile",
|
||||
"graph.model_stylesheet": "\n * { model: claude-opus-4-7; }\n ",
|
||||
"internal.retry_count.verify": 0,
|
||||
"internal.thread_id": "verify",
|
||||
"internal.fidelity": "compact",
|
||||
"thread.preflight_lint.current_node": "implement",
|
||||
"internal.retry_count.simplify_gpt": 0,
|
||||
"graph.goal": "# Plan: Compute LLM cost on-read for in-flight stages\n\n## Context\n\nOn the run billing page (`/runs/{id}/billing`), an active stage shows token\nusage but no dollar cost — cost renders as `—` until the stage completes.\n\nRoot cause: while a stage runs, `AgentMessage` events carry usage built by\n`billed_token_counts_from_llm` (`fabro-workflow/src/outcome.rs:43`), which\nhard-codes `total_usd_micros: None`. Dollar cost is only computed by\n`billed_model_usage_from_llm` (`outcome.rs:14`) — which needs the pricing\n`Catalog` — and that runs only on `StageCompleted`/`PromptCompleted`/`StageFailed`.\nSo an in-flight stage's `StageProjection.usage.total_usd_micros` stays `None`.\n\nFix: price stages whose cost is `None` when the billing rollup is built for a\nread request, using the model + token counts already in the projection. The\nwire contract is unchanged (`total_usd_micros` is already nullable everywhere)\nand the frontend already renders whatever value comes back — no UI change.\n\n## Decisions\n\n- **Price any stage with `total_usd_micros == None`**, not just in-flight ones.\n Completed stages with unpriceable providers (`BillingPolicy::None`) return\n `None` again — harmless; no need to thread `StageState`.\n- **No \"estimated\" label.** Cost-so-far is exact for tokens consumed so far,\n matching the already-unlabeled live token counts and ticking runtime.\n- **Aggregate billing stays finalized-only.** The `BillingAccumulator` call\n sites pass `None` so a run's running estimate is never folded into org-wide\n totals (avoids double-count when the run later finalizes).\n- Per-stage rows, `totals`, and `by_model` are all priced from the same source\n so the billing page stays internally consistent.\n\n## Changes\n\n### 1. `lib/crates/fabro-model/src/billing.rs`\n\n- Add `BilledTokenCounts::token_counts(&self) -> TokenCounts` — drops\n `total_tokens`/`total_usd_micros`, keeps the five disjoint buckets.\n- Add `Catalog::price_tokens(&self, model: &ModelRef, tokens: &TokenCounts) -> Option<i64>`\n next to `pricing_for`/`billing_facts_for`. Body mirrors the cost lines of\n `billed_model_usage_from_llm`: build `ModelBillingFacts` via\n `billing_facts_for`, assemble `ModelBillingInput { ModelUsage { model, tokens }, facts }`,\n then `pricing_for(model).and_then(|p| p.bill(&input)).map(|a| a.0)`. Returns\n `None` when the provider has no billing policy.\n\n### 2. `lib/crates/fabro-workflow/src/billing_rollup.rs`\n\n- Change signature to\n `billing_rollup_from_projection(projection: &RunProjection, catalog: Option<&Catalog>)`.\n- Add a module-private helper `stage_usage_with_cost(catalog, stage) -> BilledTokenCounts`:\n clone `stage.usage`; if `total_usd_micros.is_none()` and both `catalog` and\n `stage.model` are present, set it via `catalog.price_tokens(model, &usage.token_counts())`.\n- In the loop, compute `priced` once per stage and use it in place of\n `&stage.usage` for the `is_zero` check, `row.billing.add_counts`,\n `totals.add_counts`, and `model_entry.billing.add_counts`.\n- Update the existing tests to pass `None`; add one new test: an in-flight\n stage (no `completion`, non-zero `usage` with `total_usd_micros: None`, a\n builtin `model`) yields `Some(..)` cost on the stage row and in `totals` when\n called with `Some(Catalog::builtin())`.\n\n### 3. Call sites of `billing_rollup_from_projection`\n\n- `lib/crates/fabro-server/src/server/handler/billing.rs:82` — bind\n `let catalog = state.catalog();` (returns `Arc<Catalog>`) and pass\n `Some(&catalog)`.\n- `lib/crates/fabro-server/src/server.rs` (2 aggregate-billing sites) — pass `None`.\n- `lib/crates/fabro-workflow/src/pipeline/finalize.rs` (4 sites) — pass `None`\n (stages already priced at completion; pricing would be a no-op anyway).\n\nNo changes to `fabro-api.yaml`, the generated clients, or `apps/fabro-web`.\n\n## Out of scope / known limitation\n\nIn-flight **prompt** stages have no `model` until `PromptCompleted` (only\n`AgentMessage` sets `stage.model` mid-run), so they still show `—` while\nrunning. Acceptable: prompt stages are a single short LLM call. The bug report\nconcerns agent stages, where `model` is available.\n\n## Verification\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — new + updated unit tests pass.\n- `cargo nextest run -p fabro-server billing` — handler conformance still passes.\n- `cargo build --workspace` and `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings`.\n- Manual: `fabro server start` + `cd apps/fabro-web && bun run dev`, start a\n workflow with an agent stage, open `/runs/{id}/billing` mid-run — the active\n stage row and totals show a non-`—` dollar amount that grows with tokens.\n",
|
||||
"response.implement": "All changes implemented as specified in the plan:\n\n**1. `lib/crates/fabro-model/src/billing.rs`** ✅\n- Added `BilledTokenCounts::token_counts(&self) -> TokenCounts` (drops `total_tokens`/`total_usd_micros`).\n- Added `Catalog::price_tokens(&self, model, tokens) -> Option<i64>` that mirrors the cost lines of `billed_model_usage_from_llm`.\n\n**2. `lib/crates/fabro-workflow/src/billing_rollup.rs`** ✅\n- Changed `billing_rollup_from_projection` signature to take `catalog: Option<&Catalog>`.\n- Added private helper `stage_usage_with_cost` that clones `stage.usage` and prices it when `total_usd_micros.is_none()` and both `catalog` and `stage.model` are available.\n- Uses `priced` in place of `&stage.usage` for the `is_zero` check, `row.billing.add_counts`, `totals.add_counts`, and `model_entry.billing.add_counts`.\n- Updated existing tests to pass `None`; added a new `rollup_prices_in_flight_stage_usage_using_catalog` test (in-flight stage with no completion, non-zero usage, builtin model → `Some(..)` cost on stage row, totals, and `by_model`).\n\n**3. Call sites** ✅\n- `fabro-server/src/server/handler/billing.rs:82` — binds `let catalog = state.catalog();` and passes `Some(&catalog)`.\n- `fabro-server/src/server.rs` (2 aggregate-billing sites) — pass `None`.\n- `fabro-workflow/src/pipeline/finalize.rs` (4 sites) — pass `None`.\n\n**Verification** ✅\n- `cargo nextest run -p fabro-workflow billing_rollup` — 4 tests pass (new + 3 updated).\n- `cargo nextest run -p fabro-server billing` — 7 tests pass.\n- `cargo nextest run -p fabro-model billing` — 23 tests pass.\n- `cargo check --workspace --all-targets` — clean.\n- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` — clean.\n- `cargo +nightly-2026-04-14 fmt --check --all` — clean.\n- Broader test sweep on `fabro-workflow` + `fabro-server`: 1674 passing; the 2 unrelated `*graph*svg*` failures are pre-existing graphviz subprocess env issues (confirmed by stashing my changes and reproducing).",
|
||||
"internal.run_id": "01KS6AW28FZVV4M2EHBJA7JMNP",
|
||||
"thread.simplify_opus.current_node": "simplify_gpt",
|
||||
"current_node": "fmt",
|
||||
"internal.retry_count.fmt": 0,
|
||||
"internal.retry_count.simplify_opus": 0,
|
||||
"internal.work_dir": "/home/daytona/workspace/fabro",
|
||||
"last_stage": "simplify_gpt",
|
||||
"outcome": "succeeded",
|
||||
"internal.retry_count.implement": 0,
|
||||
"internal.retry_count.preflight_lint": 0,
|
||||
"failure_class": "",
|
||||
"internal.node_visit_count": 1,
|
||||
"last_response": "Implemented review cleanup on top of the billing cost-on-read changes.\n\nWhat changed:\n- Removed `BilledTokenCounts::ensure_priced`, which was an extra thin helper only used by rollup code.\n- Renamed `",
|
||||
"response.simplify_gpt": "Implemented review cleanup on top of the billing cost-on-read changes.\n\nWhat changed:\n- Removed `BilledTokenCounts::ensure_priced`, which was an extra thin helper only used by rollup code.\n- Renamed `to_token_counts()` to `token_counts()` to match the requested API and nearby accessor style.\n- Updated `billing_rollup` pricing helper to avoid cloning stage usage unless a missing cost can actually be priced:\n - borrows existing usage for finalized/already-priced/no-catalog/no-model/unpriceable cases\n - only clones when setting a computed `total_usd_micros`\n\nReview outcome:\n- The parallel review agents did not return actionable findings.\n- I applied the above cleanup for reduced abstraction and less per-read work.\n\nVerification passed:\n- `cargo nextest run -p fabro-workflow billing_rollup`\n- `cargo nextest run -p fabro-server billing`\n- `cargo +nightly-2026-04-14 clippy -q -p fabro-model -p fabro-workflow -p fabro-server --all-targets -- -D warnings`\n\nCurrent working tree has modifications in:\n- `lib/crates/fabro-model/src/billing.rs`\n- `lib/crates/fabro-workflow/src/billing_rollup.rs`",
|
||||
"thread.verify.current_node": "fmt",
|
||||
"response.simplify_opus": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_counts()` → `to_token_counts()`** (`fabro-model/src/billing.rs`)\n - Quality finding: original name read like a field accessor and hid the fact that the conversion is lossy (drops `total_tokens` and `total_usd_micros`). The `to_` prefix is the established Rust convention for lossy conversions.\n\n2. **Moved pricing logic into `BilledTokenCounts::ensure_priced(catalog, model)`** (`fabro-model/src/billing.rs` + `fabro-workflow/src/billing_rollup.rs`)\n - Quality finding: the previous `stage_usage_with_cost` helper cloned `BilledTokenCounts` across a crate boundary and directly poked the private `total_usd_micros` field, leaking knowledge of how to price a `BilledTokenCounts` out of `fabro-model`. The new method encapsulates that logic next to `add_billed_usage` / `replace_with_billed_usage`, and the rollup-side helper is now a 3-line wrapper.\n\n### Considered and skipped\n\n- **Reuse #1 (refactor `billed_model_usage_from_llm` to use `price_tokens`)** — the \"duplicated\" pricing tail is 3 lines and the surrounding error-vs-option shapes don't compose cleanly. Refactoring adds more indirection than it removes.\n- **`Option<&Catalog>` parameter sprawl** — 6 of 7 call sites pass `None`, but splitting into two functions doubles the public surface for marginal benefit; the single signature is fine.\n- **`pricing_for` memoization across stages** — real but minor (a few `String` clones per stage on a polled endpoint). Worth doing if the path ever shows up in profiles; not justified at the cost of HashMap setup for this fix.\n- **`Cow::Borrowed` for the usage clone** — `BilledTokenCounts` is ~64 bytes of POD; no heap allocation.\n- **Bare `i64` return from `price_tokens`** — matches the established `total_usd_micros: Option<i64>` convention used throughout the codebase.\n\n### Verified\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — 4/4 pass (including the new in-flight pricing test).\n- `cargo nextest run -p fabro-model billed_token_counts` — 5/5 pass.\n- `cargo nextest run -p fabro-server billing` — 7/7 pass.\n- `cargo build --workspace` — clean.\n- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` — clean.\n- `cargo +nightly-2026-04-14 fmt --check --all` — clean.",
|
||||
"internal.retry_count.preflight_compile": 0,
|
||||
"internal.retry_count.implement": 0
|
||||
"failure_signature": "",
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126",
|
||||
"internal.run_id": "01KS6AW28FZVV4M2EHBJA7JMNP",
|
||||
"thread.implement.current_node": "simplify_opus",
|
||||
"thread.simplify_gpt.current_node": "verify",
|
||||
"thread.start.current_node": "toolchain",
|
||||
"internal.retry_count.start": 0,
|
||||
"graph.rankdir": "LR",
|
||||
"thread.preflight_compile.current_node": "preflight_lint"
|
||||
},
|
||||
"node_outcomes": {
|
||||
"fmt": {
|
||||
"simplify_opus": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126"
|
||||
"response.simplify_opus": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_counts()` → `to_token_counts()`** (`fabro-model/src/billing.rs`)\n - Quality finding: original name read like a field accessor and hid the fact that the conversion is lossy (drops `total_tokens` and `total_usd_micros`). The `to_` prefix is the established Rust convention for lossy conversions.\n\n2. **Moved pricing logic into `BilledTokenCounts::ensure_priced(catalog, model)`** (`fabro-model/src/billing.rs` + `fabro-workflow/src/billing_rollup.rs`)\n - Quality finding: the previous `stage_usage_with_cost` helper cloned `BilledTokenCounts` across a crate boundary and directly poked the private `total_usd_micros` field, leaking knowledge of how to price a `BilledTokenCounts` out of `fabro-model`. The new method encapsulates that logic next to `add_billed_usage` / `replace_with_billed_usage`, and the rollup-side helper is now a 3-line wrapper.\n\n### Considered and skipped\n\n- **Reuse #1 (refactor `billed_model_usage_from_llm` to use `price_tokens`)** — the \"duplicated\" pricing tail is 3 lines and the surrounding error-vs-option shapes don't compose cleanly. Refactoring adds more indirection than it removes.\n- **`Option<&Catalog>` parameter sprawl** — 6 of 7 call sites pass `None`, but splitting into two functions doubles the public surface for marginal benefit; the single signature is fine.\n- **`pricing_for` memoization across stages** — real but minor (a few `String` clones per stage on a polled endpoint). Worth doing if the path ever shows up in profiles; not justified at the cost of HashMap setup for this fix.\n- **`Cow::Borrowed` for the usage clone** — `BilledTokenCounts` is ~64 bytes of POD; no heap allocation.\n- **Bare `i64` return from `price_tokens`** — matches the established `total_usd_micros: Option<i64>` convention used throughout the codebase.\n\n### Verified\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — 4/4 pass (including the new in-flight pricing test).\n- `cargo nextest run -p fabro-model billed_token_counts` — 5/5 pass.\n- `cargo nextest run -p fabro-server billing` — 7/7 pass.\n- `cargo build --workspace` — clean.\n- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` — clean.\n- `cargo +nightly-2026-04-14 fmt --check --all` — clean.",
|
||||
"last_stage": "simplify_opus",
|
||||
"last_response": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_c"
|
||||
},
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"usage": null
|
||||
"notes": "Stage completed: simplify_opus",
|
||||
"usage": {
|
||||
"input": {
|
||||
"usage": {
|
||||
"model": {
|
||||
"provider": "anthropic",
|
||||
"model_id": "claude-opus-4-7"
|
||||
},
|
||||
"tokens": {
|
||||
"input_tokens": 55570,
|
||||
"output_tokens": 17369,
|
||||
"reasoning_tokens": 0,
|
||||
"cache_read_tokens": 1126033,
|
||||
"cache_write_tokens": 66184
|
||||
}
|
||||
},
|
||||
"facts": {
|
||||
"algorithm": "anthropic",
|
||||
"cache_write_5m_tokens": 66184,
|
||||
"cache_write_1h_tokens": 0
|
||||
}
|
||||
},
|
||||
"total_usd_micros": 1688741
|
||||
},
|
||||
"files_touched": [
|
||||
"/home/daytona/workspace/fabro/lib/crates/fabro-model/src/billing.rs",
|
||||
"/home/daytona/workspace/fabro/lib/crates/fabro-workflow/src/billing_rollup.rs"
|
||||
]
|
||||
},
|
||||
"implement": {
|
||||
"status": "succeeded",
|
||||
|
|
@ -1581,20 +1609,12 @@
|
|||
"/home/daytona/workspace/fabro/lib/crates/fabro-workflow/src/pipeline/finalize.rs"
|
||||
]
|
||||
},
|
||||
"preflight_compile": {
|
||||
"fmt": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126"
|
||||
},
|
||||
"notes": "Script completed: cargo check -q --workspace 2>&1",
|
||||
"usage": null
|
||||
},
|
||||
"preflight_lint": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126"
|
||||
},
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1",
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"usage": null
|
||||
},
|
||||
"verify": {
|
||||
|
|
@ -1605,54 +1625,6 @@
|
|||
"notes": "Script completed: 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",
|
||||
"usage": null
|
||||
},
|
||||
"toolchain": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/fc14b2ba2d770e5cd3169df7a29525c962adfc4cfa3097b9098c63ebd61a748c"
|
||||
},
|
||||
"notes": "Script completed: 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",
|
||||
"usage": null
|
||||
},
|
||||
"start": {
|
||||
"status": "succeeded",
|
||||
"usage": null
|
||||
},
|
||||
"simplify_opus": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"response.simplify_opus": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_counts()` → `to_token_counts()`** (`fabro-model/src/billing.rs`)\n - Quality finding: original name read like a field accessor and hid the fact that the conversion is lossy (drops `total_tokens` and `total_usd_micros`). The `to_` prefix is the established Rust convention for lossy conversions.\n\n2. **Moved pricing logic into `BilledTokenCounts::ensure_priced(catalog, model)`** (`fabro-model/src/billing.rs` + `fabro-workflow/src/billing_rollup.rs`)\n - Quality finding: the previous `stage_usage_with_cost` helper cloned `BilledTokenCounts` across a crate boundary and directly poked the private `total_usd_micros` field, leaking knowledge of how to price a `BilledTokenCounts` out of `fabro-model`. The new method encapsulates that logic next to `add_billed_usage` / `replace_with_billed_usage`, and the rollup-side helper is now a 3-line wrapper.\n\n### Considered and skipped\n\n- **Reuse #1 (refactor `billed_model_usage_from_llm` to use `price_tokens`)** — the \"duplicated\" pricing tail is 3 lines and the surrounding error-vs-option shapes don't compose cleanly. Refactoring adds more indirection than it removes.\n- **`Option<&Catalog>` parameter sprawl** — 6 of 7 call sites pass `None`, but splitting into two functions doubles the public surface for marginal benefit; the single signature is fine.\n- **`pricing_for` memoization across stages** — real but minor (a few `String` clones per stage on a polled endpoint). Worth doing if the path ever shows up in profiles; not justified at the cost of HashMap setup for this fix.\n- **`Cow::Borrowed` for the usage clone** — `BilledTokenCounts` is ~64 bytes of POD; no heap allocation.\n- **Bare `i64` return from `price_tokens`** — matches the established `total_usd_micros: Option<i64>` convention used throughout the codebase.\n\n### Verified\n\n- `cargo nextest run -p fabro-workflow billing_rollup` — 4/4 pass (including the new in-flight pricing test).\n- `cargo nextest run -p fabro-model billed_token_counts` — 5/5 pass.\n- `cargo nextest run -p fabro-server billing` — 7/7 pass.\n- `cargo build --workspace` — clean.\n- `cargo +nightly-2026-04-14 clippy --workspace --all-targets -- -D warnings` — clean.\n- `cargo +nightly-2026-04-14 fmt --check --all` — clean.",
|
||||
"last_stage": "simplify_opus",
|
||||
"last_response": "All clean. Here's the summary:\n\n## Summary\n\nThree review agents (reuse, quality, efficiency) ran in parallel against the diff. Aggregated findings:\n\n### Fixed\n\n1. **Renamed `BilledTokenCounts::token_c"
|
||||
},
|
||||
"notes": "Stage completed: simplify_opus",
|
||||
"usage": {
|
||||
"input": {
|
||||
"usage": {
|
||||
"model": {
|
||||
"provider": "anthropic",
|
||||
"model_id": "claude-opus-4-7"
|
||||
},
|
||||
"tokens": {
|
||||
"input_tokens": 55570,
|
||||
"output_tokens": 17369,
|
||||
"reasoning_tokens": 0,
|
||||
"cache_read_tokens": 1126033,
|
||||
"cache_write_tokens": 66184
|
||||
}
|
||||
},
|
||||
"facts": {
|
||||
"algorithm": "anthropic",
|
||||
"cache_write_5m_tokens": 66184,
|
||||
"cache_write_1h_tokens": 0
|
||||
}
|
||||
},
|
||||
"total_usd_micros": 1688741
|
||||
},
|
||||
"files_touched": [
|
||||
"/home/daytona/workspace/fabro/lib/crates/fabro-model/src/billing.rs",
|
||||
"/home/daytona/workspace/fabro/lib/crates/fabro-workflow/src/billing_rollup.rs"
|
||||
]
|
||||
},
|
||||
"simplify_gpt": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
|
|
@ -1682,25 +1654,135 @@
|
|||
},
|
||||
"total_usd_micros": 1643598
|
||||
}
|
||||
},
|
||||
"preflight_compile": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126"
|
||||
},
|
||||
"notes": "Script completed: cargo check -q --workspace 2>&1",
|
||||
"usage": null
|
||||
},
|
||||
"preflight_lint": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126"
|
||||
},
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1",
|
||||
"usage": null
|
||||
},
|
||||
"toolchain": {
|
||||
"status": "succeeded",
|
||||
"context_updates": {
|
||||
"command.output": "blob://sha256/fc14b2ba2d770e5cd3169df7a29525c962adfc4cfa3097b9098c63ebd61a748c"
|
||||
},
|
||||
"notes": "Script completed: 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",
|
||||
"usage": null
|
||||
},
|
||||
"start": {
|
||||
"status": "succeeded",
|
||||
"usage": null
|
||||
}
|
||||
},
|
||||
"next_node_id": "exit",
|
||||
"git_commit_sha": "cc7f63071f75b09f6639210abd2cc5bcb1747b31",
|
||||
"node_visits": {
|
||||
"simplify_opus": 1,
|
||||
"fmt": 1,
|
||||
"preflight_lint": 1,
|
||||
"toolchain": 1,
|
||||
"verify": 1,
|
||||
"implement": 1,
|
||||
"preflight_compile": 1,
|
||||
"start": 1,
|
||||
"implement": 1,
|
||||
"simplify_gpt": 1,
|
||||
"verify": 1,
|
||||
"preflight_lint": 1,
|
||||
"toolchain": 1
|
||||
"fmt": 1,
|
||||
"simplify_opus": 1
|
||||
}
|
||||
},
|
||||
"diff": {}
|
||||
"diff": {
|
||||
"summary": {
|
||||
"files_changed": 5,
|
||||
"additions": 118,
|
||||
"deletions": 17
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"conclusion": null,
|
||||
"conclusion": {
|
||||
"timestamp": "2026-05-21T23:20:19.838528Z",
|
||||
"status": "succeeded",
|
||||
"duration_ms": 2653948,
|
||||
"final_git_commit_sha": "cc7f63071f75b09f6639210abd2cc5bcb1747b31",
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": "start",
|
||||
"stage_label": "start",
|
||||
"duration_ms": 0,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "toolchain",
|
||||
"stage_label": "toolchain",
|
||||
"duration_ms": 1671,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "preflight_compile",
|
||||
"stage_label": "preflight_compile",
|
||||
"duration_ms": 246352,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "preflight_lint",
|
||||
"stage_label": "preflight_lint",
|
||||
"duration_ms": 298559,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "implement",
|
||||
"stage_label": "implement",
|
||||
"duration_ms": 804582,
|
||||
"billing_usd_micros": 3841995,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "simplify_opus",
|
||||
"stage_label": "simplify_opus",
|
||||
"duration_ms": 634760,
|
||||
"billing_usd_micros": 1688741,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "simplify_gpt",
|
||||
"stage_label": "simplify_gpt",
|
||||
"duration_ms": 358429,
|
||||
"billing_usd_micros": 1643598,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "verify",
|
||||
"stage_label": "verify",
|
||||
"duration_ms": 220240,
|
||||
"retries": 0
|
||||
},
|
||||
{
|
||||
"stage_id": "fmt",
|
||||
"stage_label": "fmt",
|
||||
"duration_ms": 3780,
|
||||
"retries": 0
|
||||
}
|
||||
],
|
||||
"billing": {
|
||||
"input_tokens": 238086,
|
||||
"output_tokens": 40677,
|
||||
"total_tokens": 7993585,
|
||||
"reasoning_tokens": 3776,
|
||||
"cache_read_tokens": 7543790,
|
||||
"cache_write_tokens": 167256,
|
||||
"total_usd_micros": 7174334
|
||||
},
|
||||
"total_retries": 0,
|
||||
"diff": {}
|
||||
},
|
||||
"sandbox": {
|
||||
"provider": "daytona",
|
||||
"image": "buildpack-deps:noble",
|
||||
|
|
@ -2036,23 +2118,25 @@
|
|||
},
|
||||
"state": "succeeded"
|
||||
},
|
||||
"fmt@1": {
|
||||
"first_event_seq": 818,
|
||||
"exit@1": {
|
||||
"first_event_seq": 828,
|
||||
"prompt": null,
|
||||
"response": null,
|
||||
"completion": null,
|
||||
"completion": {
|
||||
"outcome": "succeeded",
|
||||
"notes": null,
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-21T23:20:19.788123Z"
|
||||
},
|
||||
"provider_used": null,
|
||||
"diff": null,
|
||||
"script_invocation": {
|
||||
"script": "cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"command": "exec 2>&1\ncargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"language": "shell"
|
||||
},
|
||||
"script_invocation": null,
|
||||
"script_timing": null,
|
||||
"parallel_results": null,
|
||||
"output": null,
|
||||
"started_at": "2026-05-21T23:20:10.784946Z",
|
||||
"handler": "command",
|
||||
"started_at": "2026-05-21T23:20:19.788048Z",
|
||||
"handler": "exit",
|
||||
"duration_ms": 0,
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"output_tokens": 0,
|
||||
|
|
@ -2061,7 +2145,50 @@
|
|||
"cache_read_tokens": 0,
|
||||
"cache_write_tokens": 0
|
||||
},
|
||||
"state": "running"
|
||||
"state": "succeeded"
|
||||
},
|
||||
"fmt@1": {
|
||||
"first_event_seq": 818,
|
||||
"prompt": null,
|
||||
"response": null,
|
||||
"completion": {
|
||||
"outcome": "succeeded",
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-21T23:20:14.566089Z"
|
||||
},
|
||||
"provider_used": null,
|
||||
"diff": null,
|
||||
"script_invocation": {
|
||||
"script": "cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"command": "exec 2>&1\ncargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"language": "shell"
|
||||
},
|
||||
"script_timing": {
|
||||
"output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126",
|
||||
"exit_code": 0,
|
||||
"duration_ms": 3763,
|
||||
"termination": "exited",
|
||||
"output_bytes": 0,
|
||||
"live_streaming": false
|
||||
},
|
||||
"parallel_results": null,
|
||||
"output": null,
|
||||
"output_bytes": 0,
|
||||
"live_streaming": false,
|
||||
"termination": "exited",
|
||||
"started_at": "2026-05-21T23:20:10.784946Z",
|
||||
"handler": "command",
|
||||
"duration_ms": 3780,
|
||||
"usage": {
|
||||
"input_tokens": 0,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
"reasoning_tokens": 0,
|
||||
"cache_read_tokens": 0,
|
||||
"cache_write_tokens": 0
|
||||
},
|
||||
"state": "succeeded"
|
||||
}
|
||||
}
|
||||
}
|
||||
1
stages/009-fmt@1/output.log
Normal file
1
stages/009-fmt@1/output.log
Normal file
|
|
@ -0,0 +1 @@
|
|||
blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126
|
||||
8
stages/009-fmt@1/script_timing.json
Normal file
8
stages/009-fmt@1/script_timing.json
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
{
|
||||
"output": "blob://sha256/12ae32cb1ec02d01eda3581b127c1fee3b0dc53572ed6baf239721a03d82e126",
|
||||
"exit_code": 0,
|
||||
"duration_ms": 3763,
|
||||
"termination": "exited",
|
||||
"output_bytes": 0,
|
||||
"live_streaming": false
|
||||
}
|
||||
6
stages/009-fmt@1/status.json
Normal file
6
stages/009-fmt@1/status.json
Normal file
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"outcome": "succeeded",
|
||||
"notes": "Script completed: cargo +nightly-2026-04-14 fmt --all 2>&1",
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-21T23:20:14.566089Z"
|
||||
}
|
||||
6
stages/010-exit@1/status.json
Normal file
6
stages/010-exit@1/status.json
Normal file
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"outcome": "succeeded",
|
||||
"notes": null,
|
||||
"failure_reason": null,
|
||||
"timestamp": "2026-05-21T23:20:19.788123Z"
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue