charles/claude-hooks

Fork

You've already forked claude-hooks

Code Issues 10 Pull requests Projects Releases Packages 1 Wiki Activity Actions

agents: per-model rate table + runner cost computation (cursor parity with claude-code) #953

New issue

Closed

opened 2026-05-08 12:05:13 +00:00 by claude-desktop · 1 comment

claude-desktop commented

2026-05-08 12:05:13 +00:00

Collaborator

Copy link

User story

As an operator I want every task to display its accumulated USD cost regardless of provider, so I can compare run cost across models and providers in the dashboard.

Context

Claude Code's result.total_cost_usd is set by the SDK. Cursor's SDK does not expose USD cost in any message — cursor-sdk-adapter.ts hardcodes totalCostUsd: 0. Without computing cost ourselves, every cursor row in task_history shows €0.00 forever.

Acceptance criteria

Rate table

Extend apps/server/src/infrastructure/agent/models-cache.ts (or sibling model-rates.ts) with per-model rates: { provider, modelId, inputPerMTok, outputPerMTok, cacheReadPerMTok, cacheCreationPerMTok }.
Seed at minimum: every Anthropic Claude 4.x model (Opus 4.7, Sonnet 4.6, Haiku 4.5), every Cursor model the SDK lists today (Composer 2, GPT-5.5, plus whatever Agent.listModels returns), and any GPT-5/Anthropic Bedrock variants we already use.
Source rates from the canonical pricing pages (Anthropic, OpenAI, Cursor); link the URL in a comment per model row. Mark unverified rates with a TODO so a real-world run can surface mismatches.
Allow runtime override via the existing service-config table — operator can patch a rate without a redeploy when pricing changes.

Runner / event log

On every usage_delta (and the terminal result), compute incremental cost from the table and accumulate into record.cost_usd. Persist to task_history.cost_usd on terminal.
If a model is not in the table, log a single warning per task and treat cost as 0 + emit a system { subtype: "cost_unknown_model", details: { model } } so the UI can flag the row instead of silently zeroing it.

Frontend

Cost chip rendered next to the token meter in the same surfaces. Format: 3 sig figs USD, e.g. $0.043 / $1.27.
When cost_unknown_model was raised for the run, show ? with a tooltip explaining the missing rate row.

Tests

Unit tests for the cost computation: feed a known usage stream, assert the running total matches hand-computed cost.
Test for the unknown-model fallback path.
Test that a runtime rate override applied mid-run is not retroactively applied — cost is computed from the rate at delta time, not at terminal time.

Out of scope

Currency conversion (USD↔EUR) — display USD only for now; multi-currency is a separate concern.
Budget enforcement / auto-cancel — separate ops issue.
Historical re-pricing of past runs — task_history.cost_usd is immutable.

References

Parent: #950
Depends on: live token meter issue (usage_delta event)
Pricing pages: anthropic.com/pricing, openai.com/api/pricing, cursor.com/pricing (verify each)

## User story As an operator I want every task to display its accumulated USD cost regardless of provider, so I can compare run cost across models and providers in the dashboard. ## Context Claude Code's `result.total_cost_usd` is set by the SDK. Cursor's SDK does not expose USD cost in any message — `cursor-sdk-adapter.ts` hardcodes `totalCostUsd: 0`. Without computing cost ourselves, every cursor row in `task_history` shows €0.00 forever. ## Acceptance criteria ### Rate table - [ ] Extend `apps/server/src/infrastructure/agent/models-cache.ts` (or sibling `model-rates.ts`) with per-model rates: `{ provider, modelId, inputPerMTok, outputPerMTok, cacheReadPerMTok, cacheCreationPerMTok }`. - [ ] Seed at minimum: every Anthropic Claude 4.x model (Opus 4.7, Sonnet 4.6, Haiku 4.5), every Cursor model the SDK lists today (Composer 2, GPT-5.5, plus whatever `Agent.listModels` returns), and any GPT-5/Anthropic Bedrock variants we already use. - [ ] Source rates from the canonical pricing pages (Anthropic, OpenAI, Cursor); link the URL in a comment per model row. Mark unverified rates with a TODO so a real-world run can surface mismatches. - [ ] Allow runtime override via the existing `service-config` table — operator can patch a rate without a redeploy when pricing changes. ### Runner / event log - [ ] On every `usage_delta` (and the terminal `result`), compute incremental cost from the table and accumulate into `record.cost_usd`. Persist to `task_history.cost_usd` on terminal. - [ ] If a model is not in the table, log a single warning per task and treat cost as 0 + emit a `system { subtype: "cost_unknown_model", details: { model } }` so the UI can flag the row instead of silently zeroing it. ### Frontend - [ ] Cost chip rendered next to the token meter in the same surfaces. Format: 3 sig figs USD, e.g. `$0.043` / `$1.27`. - [ ] When `cost_unknown_model` was raised for the run, show `?` with a tooltip explaining the missing rate row. ### Tests - [ ] Unit tests for the cost computation: feed a known usage stream, assert the running total matches hand-computed cost. - [ ] Test for the unknown-model fallback path. - [ ] Test that a runtime rate override applied mid-run is *not* retroactively applied — cost is computed from the rate at delta time, not at terminal time. ## Out of scope - Currency conversion (USD↔EUR) — display USD only for now; multi-currency is a separate concern. - Budget enforcement / auto-cancel — separate ops issue. - Historical re-pricing of past runs — `task_history.cost_usd` is immutable. ## References - Parent: #950 - Depends on: live token meter issue (`usage_delta` event) - Pricing pages: anthropic.com/pricing, openai.com/api/pricing, cursor.com/pricing (verify each)

claude-desktop added the

area:agents

type:user-story

labels

2026-05-08 12:06:58 +00:00

claude-desktop referenced this issue

2026-05-08 12:15:53 +00:00

dashboard: two-meter run header — live context-window % + cumulative $ cost #967

claude-desktop added a new dependency

2026-05-08 12:19:18 +00:00

#967 dashboard: two-meter run header — live context-window % + cumulative $ cost

claude-desktop added a new dependency

2026-05-08 12:19:19 +00:00

#952 agents: live token meter — accumulate per-task usage across both providers

claude-desktop referenced this issue

2026-05-08 12:33:27 +00:00

cursor-sdk-adapter: visibility parity + cancel-race fix + stall watchdog #950

code-lead was assigned by architect

2026-05-08 20:55:43 +00:00

architect commented

2026-05-08 20:55:44 +00:00

Collaborator

Copy link

🤖 Auto-assigned to code-lead (heuristic: area:agents → code-lead (architecture-touching)). Reply /unassign to reroute.

🤖 Auto-assigned to **code-lead** (heuristic: area:agents → code-lead (architecture-touching)). Reply `/unassign` to reroute.

code-lead referenced this issue from a commit

2026-05-08 21:24:24 +00:00

feat(agents): per-model rate table + per-delta cost accumulation (cursor parity)

code-lead referenced this issue from a pull request that will close it,

2026-05-08 21:24:44 +00:00

feat(agents): per-model rate table + per-delta cost accumulation #1003

code-lead was unassigned by architect

2026-05-08 21:29:12 +00:00

code-lead was assigned by architect

2026-05-08 21:29:13 +00:00

reviewer closed this issue

2026-05-08 21:32:54 +00:00

No Branch/Tag specified

main

chore/sync-pre-push-from-forge-base

fix/flows-yaml-dispatch-identity

feat/board-tap-to-assign

dev/1107

code-lead/1106

code-lead/1108

dev/1104

code-lead/1103

code-lead/1080

dev/1087

feat/flows-yaml-ci-events

chore/board-drop-stalled-and-density-controls

fix/flows-yaml-routes-always-register

flows-yaml/api-defaults

dev/1023

fix/event-log-history-bleed

fix/janitor-fix-ci-logs-and-cap

dev/1022

fix/board-card-provider

code-lead/1036

dev/1025

code-lead/1020

dev/1017

code-lead/1026

feat/web-shortcut-registry-1018

dev/1015

code-lead/1009

code-lead/1008

dev/975

dev/969

dev/973

dev/967

code-lead/968

code-lead/953

dev/970

dev/976

code-lead/966

code-lead/956

code-lead/951

dev/962

dev/963

dev/977

dev/955

dev/983

dev/961

dev/974

code-lead/950

code-lead/939

dev/941

dev/940

dev/937

dev/938

dev/936

dev/935

feat/web-i18n-fr-locale

feat/spec-editor-ui-polish

chore/drop-legacy-compat

fix/skills-drop-preview-pane

fix/882-skills-safety-rail

dev/911

dev/909

dev/923

dev/917

dev/915

feat/879-sr11-m2-drop-legacy-skill

code-lead/873

dev/881

code-lead/869

dev/867

code-lead/845

code-lead/843

code-lead/844

dev/837

dev/861

dev/849

code-lead/837

code-lead/842

fix/dedup-rebase-inflight

dev/838

code-lead/847

dev/833

code-lead/848

pr/838

code-lead/841

feat/settings-save-bar/836

code-lead/840

dev/846

code-lead/839

dev/832

fix/board-sse-stale-cache

dev/834

dev/835

feat/settings-breadcrumbs

feat/forge-oauth-credentials

refactor/service-config-consolidation

feat/agent-tokens-to-secrets

feat/gitlab-oauth-to-db

feat/authelia-rip-and-voice-fixes

fix/rebase-storm-and-dead-letter

code-lead/797

code-lead/796

dev/811

code-lead/798

dev/810

code-lead/795

dev/808

code-lead/794

dev/805

dev/802

dev/803

feat/avatar-menu-settings-entry

feat/per-agent-token-tracking

dev/793

dev/747

dev/752

code-lead/790

code-lead/759

dev/756

dev/760

dev/741

dev/767

dev/740

dev/709

dev/644

dev/637

boss/614

dev/600

dev/611

dev/585

fix/login-bonus-fixes

boss/544

dev/542

refactor/api-prefix-and-session-gate

dev/489

boss/531

boss/518

dev/499

boss/516

dev/530

dev/517

dev/519

dev/515

dev/522

dev/503

dev/471

boss/329

dev/417

dev/418

dev/402

boss/327

dev/334

dev/332

boss/326

boss/325

dev/331

boss/324

boss/323

boss/322

dev/294

test/s11-task-analytics

dev/262

boss/270

dev/268

foreman/ui-consolidation-spec

dev/234

boss/196

boss/176

boss/164

fix/124-session-persist-bind

boss/52

dev/87

boss/73

dev/77

dev/81

dev/82

boss/79

dev/42

dev/35

boss/7

No results found.

Labels

Clear labels

area:agents

Agent types, pool scheduling, per-instance config

area:dashboard

Dashboard UI and observability surfaces

area:database

DB layer — schema, migrations, ORM, raw SQL

area:design

UI/UX mockup work — routes to designer agent

area:design-review

Design review dispatch — routes to design-reviewer agent

area:flows

Flow runner — YAML loader, executor, op registry, expression eval

area:infra

Deployment, isolation, containers, systemd units

area:meta

Tracking, scaffolding, project setup

area:security

Security — routes to reviewer-security (opus)

area:sessions

Session-id store, Claude SDK resume logic

area:webhook

Forgejo webhook routing and handlers

area:workdir

Clone cache, worktrees, git identity

security

Security-sensitive issue

Tracking or decisions, not implementation work

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

code-lead

2 participants

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Blocks

#967 dashboard: two-meter run header — live context-window % + cumulative $ cost

charles/claude-hooks

Depends on

#952 agents: live token meter — accumulate per-task usage across both providers

charles/claude-hooks

Reference

charles/claude-hooks#953

Reference in a new issue

Repository

charles/claude-hooks

Title

Body

No description provided.

Delete branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?

Rows
Columns