Commit Graph
7 Commits
Author SHA1 Message Date
DottaandPaperclip efcce9cc8e fix(adapters): record unpriced CLI usage (#9505)
## Thinking Path

> - Paperclip is the open source control plane people use to manage
AI-agent companies
> - Budgets and spend telemetry are control-plane safety features, not
just reporting
> - Local Codex and Claude adapters can execute through either ACP or
their native CLI engines
> - The ACP lane records usage and reported cost, but CLI JSON output
often reports tokens without a price
> - The CLI lane was either losing per-run usage semantics or coercing
missing cost to zero, making real usage indistinguishable from a
genuinely free run
> - This pull request preserves CLI usage as per-run totals and records
token-bearing runs without a reported price as explicitly unpriced
ledger events
> - The benefit is accurate usage accounting and a visible pricing gap
instead of silently misleading zero-cost telemetry

## Linked Issues or Issue Description

Refs #9471
Refs #9230

**Bug description**

A `codex_local` run using the CLI engine can emit a final
`turn.completed` event with millions of input tokens and tens of
thousands of output tokens while the agent's spend ledger remains
indistinguishable from a true zero-usage, zero-cost run. Claude CLI
output has the same missing-price edge case.

**Expected behavior**

Token-bearing CLI runs should persist their usage. If the adapter
reports a price, the ledger should record it as reported; if the CLI
reports usage but no price, the ledger should explicitly mark the event
as unpriced rather than silently treating missing price data as a
reported `$0` cost.

**Reproduction shape**

1. Configure `codex_local` with `engine: cli`.
2. Run a task that produces a `turn.completed` usage payload.
3. Observe token usage in the run stream.
4. Before this change, missing price data is represented as ordinary
zero-cost spend and the CLI usage basis is not consistently propagated.

## What Changed

- Mark Codex and Claude native CLI usage totals as `per_run` and
propagate that basis through success and failure results.
- Stop coercing missing Claude CLI cost to `0`.
- Add `cost_status` to cost events with `reported` and `unpriced`
values, including an idempotent migration and shared validation/types.
- Persist token-bearing runs without a reported price as `unpriced`
ledger events while retaining zero cents until an authoritative price
exists.
- Add parser, execute-path, heartbeat-accounting, and cost-service
regression coverage for both local CLI adapters.
- Document the cost-status invariant and CLI accounting behavior.

## Verification

- `pnpm exec vitest run
packages/adapters/codex-local/src/server/parse.test.ts
packages/adapters/claude-local/src/server/parse.test.ts
server/src/__tests__/codex-local-execute.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/heartbeat-cost-accounting.test.ts
server/src/__tests__/costs-service.test.ts` — 6 files / 102 tests
passed.
- `pnpm --filter @paperclipai/shared typecheck`
- `pnpm --filter @paperclipai/db typecheck` — includes migration
numbering and safety checks.
- `pnpm --filter @paperclipai/adapter-codex-local typecheck`
- `pnpm --filter @paperclipai/adapter-claude-local typecheck`
- `pnpm --filter @paperclipai/server typecheck`

## Risks

- Existing cost rows default to `reported`, preserving current
interpretation; only new token-bearing events with absent cost are
marked `unpriced`.
- This change does not invent model pricing. Budget hard stops still
cannot charge an unknown amount, but operators and evals can now
distinguish missing pricing from a genuinely reported zero cost.
- Consumers that enumerate cost-event fields should tolerate the
additive `costStatus` field.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex, exact model `gpt-5.3-codex`, with repository tool use
and code execution; default reasoning mode.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-07-13 20:44:38 -05:00
dottaandPaperclip bd6d07d0b4 fix(ui): polish issue detail timelines and attachments
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-04-02 11:51:40 -05:00
DottaandPaperclip aeafeba12b Raise default max turns to 300
Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-03-12 09:34:05 -05:00
Dotta cabd16bc70 docs: sync docs and skills updates from backup branch 2026-03-02 16:44:10 -06:00
ForgottenandClaude Opus 4.6 2acf28a51a Implement task-scoped sessions, queued run chaining, and session reset API
Heartbeat service now resolves session state per-task using agentTaskSessions,
with resolveNextSessionState handling codec-based serialization and fallback
to legacy sessionId. Queued runs are chained — when a run finishes or is reaped,
the next queued run for the same agent starts automatically. Queued runs for
an agent with an already-running run wait instead of failing.

Add task-sessions list endpoint and extend reset-session to accept optional
taskKey for targeted session clearing. Block pending_approval agents from
API key auth. Update agent/company delete cascades to include task sessions.
Update spec docs with task-session architecture.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 14:02:17 -06:00
ForgottenandClaude Opus 4.6 774d74bcba Refine agent runs spec and fix Companies page layout
Add run log store as sixth component with pluggable storage adapter.
Rename wakeup triggers (ping→on_demand, add automation). Clarify
lightweight event timeline vs full-log storage separation. Fix
Companies page loading/error state layout shift.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-17 11:14:06 -06:00
ForgottenandClaude Opus 4.6 102f61c96d Add agent runs subsystem spec
Define agent execution runtime, adapter protocol, wakeup orchestration,
and live status delivery. Covers process and HTTP adapters, heartbeat
scheduling, run lifecycle, and status streaming.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-17 10:53:06 -06:00