Graph pipeline cost metrics: capture naming spend, fold all channels, cost pill + panel

- Cluster namer bills the money channel now: per-step usage + model
  captured via onStep, persisted as NamingRunUsage records to
  data/graph/naming-runs.jsonl (idempotent per startedAt; failed/aborted
  runs persist too — money spent either way). callUsage promoted to
  extraction.ts module scope for reuse.
- core/cost-summary.ts: the pure fold behind the pill — chat runs,
  notes-source runs, and naming runs into stage totals (extraction /
  audit / naming) + newest-first recent runs. Dollars INFERRED read-time
  via prices.ts, never stored; unpriced models excluded-but-counted
  (render '—', never a silent zero); tokens always sum.
- GET /api/graph/costs (src/server graphCosts composition, thin route).
- Graph view: bottom-left cost pill (cumulative dollars headline) +
  expandable breakdown panel (stage rows with tokens secondary, recent
  runs with time/title/merged/cost); fetched on mount, refetched when a
  pipeline run finishes; merged into one bottom-left stack with the
  running-pipeline pills.
- Tests: pure-fold suite, naming capture wiring (full importNotes ->
  naming path), store idempotency + strict reads.
This commit is contained in:
amosblomqvist
2026-09-19 20:55:35 +03:00
parent c32915b232
commit 3e263a18cc
14 changed files with 666 additions and 37 deletions
+16 -13
View File
@@ -588,6 +588,22 @@ export interface ExtractionPipeline {
importNotes(input: NotesImportInput): Promise<EmissionStats>;
}
/** pi's per-step usage, flattened to the persisted CallUsage fields
* (the money channel's capture shape, contracts/chat.ts). Exported for
* the cluster namer — the same capture shape (2026-09 graph cost
* metrics wave). Module scope: no closure deps, pure projection. */
export function callUsage(usage: Usage): CallUsage {
return {
inputTokens: usage.input,
outputTokens: usage.output,
cacheReadTokens: usage.cacheRead,
cacheWriteTokens: usage.cacheWrite,
// Optional in pi's Usage (providers that never emit reasoning
// tokens leave it unset) — persisted as 0, never dropped.
reasoningTokens: usage.reasoning ?? 0,
};
}
export function createExtractionPipeline(deps: ExtractionPipelineDeps): ExtractionPipeline {
const { chatStore, graphStore, embedder: embed } = deps;
// THE SHARED REGISTRIES (runs() above — globalThis): every pipeline
@@ -619,19 +635,6 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
run.usage[stage]!.steps.push(usage);
}
/** pi's per-step usage, flattened to the persisted CallUsage fields
* (the money channel's capture shape, contracts/chat.ts). */
function callUsage(usage: Usage): CallUsage {
return {
inputTokens: usage.input,
outputTokens: usage.output,
cacheReadTokens: usage.cacheRead,
cacheWriteTokens: usage.cacheWrite,
// Optional in pi's Usage (providers that never emit reasoning
// tokens leave it unset) — persisted as 0, never dropped.
reasoningTokens: usage.reasoning ?? 0,
};
}
async function extract(chatId: string, view: string): Promise<SessionFindings> {
const signal = runningExtractions.get(chatId)?.controller.signal;