fabro-sh-0530[bot] 2b168b4588 Compute LLM cost on-read for in-flight billing stages (#345) ... ## Summary The run billing page showed `—` for dollar cost on any active (in-flight) stage because `total_usd_micros` is only computed at stage completion. This PR prices stages whose cost is `None` at read time, using the model and token counts already present in the projection. ## What changed **`fabro-model/src/billing.rs`** gains two new methods on existing types: - `BilledTokenCounts::token_counts()` — extracts the five disjoint token buckets, dropping the derived sum and optional cost field. - `Catalog::price_tokens(model, tokens)` — mirrors the cost computation from `billed_model_usage_from_llm` but callable outside the completion path. Returns `None` for unknown models or providers with no billing policy. **`fabro-workflow/src/billing_rollup.rs`** — `billing_rollup_from_projection` gains an `Option<&Catalog>` parameter. A new private helper `stage_usage_with_cost` fills in `total_usd_micros` on-the-fly for any stage where it is `None` and both a catalog and model are available. All four accumulator call sites (`is_zero` check, per-stage row, `totals`, and `by_model`) use the priced copy, keeping the page internally consistent. **Call sites** — the read handler (`handler/billing.rs`) passes `Some(&catalog)` so active stages get priced. The aggregate-billing sites in `server.rs` and the four finalization sites in `finalize.rs` pass `None` — completed stages are already priced, and we deliberately exclude running estimates from org-wide totals to avoid double-counting when a run later finalizes. ## Design decisions - **Price any stage with `total_usd_micros == None`**, not just explicitly in-flight ones. Stages with no billing policy return `None` again — harmless. - **No "estimated" label** — cost-so-far is exact for tokens consumed so far, consistent with the already-unlabeled live token count and runtime. - In-flight **prompt** stages still show `—` because `stage.model` isn't set until `PromptCompleted`. This is acceptable; the reported bug concerns agent stages. ### Fabro Details <details> <summary>Ran 9 stages in 44m 13s for $7.17</summary> | Stage | Duration | Cost | Retries | |---|---|---|---| | start | 0s | – | 0 | | toolchain | 1s | – | 0 | | preflight_compile | 4m 6s | – | 0 | | preflight_lint | 4m 58s | – | 0 | | implement | 13m 24s | $3.84 | 0 | | simplify_opus | 10m 34s | $1.69 | 0 | | simplify_gpt | 5m 58s | $1.64 | 0 | | verify | 3m 40s | – | 0 | | fmt | 3s | – | 0 | | **Total** | **44m 13s** | **$7.17** | **0** | </details> <details> <summary>Ran <code>ImplementPlan.fabro</code> (12 nodes and 15 edges)</summary> ```dot digraph ImplementPlan { graph [ goal="Implement and simplify", model_stylesheet=" * { model: claude-opus-4-7; } " ] rankdir=LR start [shape=Mdiamond, label="Start"] exit [shape=Msquare, label="Exit"] toolchain [label="Toolchain", shape=parallelogram, script="command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1", max_retries=0] preflight_compile [label="Preflight Compile", shape=parallelogram, script="cargo check -q --workspace 2>&1", max_retries=0] preflight_lint [label="Preflight Lint", shape=parallelogram, script="cargo +nightly-2026-04-14 clippy -q --workspace --all-targets -- -D warnings 2>&1", max_retries=0] fix_lints [label="Fix Lints", prompt="The preflight lint step failed. Read the build output from context and fix all clippy lint warnings.", max_visits=3] implement [label="Implement", prompt="Read the plan file referenced in the goal and implement every step. Make all the code changes described in the plan. Use red/green TDD."] 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>		2026-05-21 19:25:00 -04:00
..
crates	Compute LLM cost on-read for in-flight billing stages (#345)	2026-05-21 19:25:00 -04:00
packages/fabro-api-client	chore(api-client): make client generation idempotent	2026-05-21 14:29:11 -04:00