Commit Graph
21 Commits
Author SHA1 Message Date
Hypatia May 6d58953f30 fix(token-meter): close projected usage review gaps 2026-07-30 17:22:15 +08:00
Hypatia May 8a8c1965d7 feat(web): show durable token usage and context occupancy in the stats line
The chat stats line took its token totals from the loaded conversation nodes,
so paging changed them and compaction erased the billing behind replaced
content. It also had no way to show context occupancy: the numerator and
capacity never reached the browser.

Both now come from token-meter session projections read through the standard
useProjection seat. Window nodes keep supplying turn and step counts plus LLM
and tool wall times, which are correctly window-scoped facts about what is on
screen; accounting no longer comes from there.

`tokenUsage` supplies billing and cache hit. `contextPressure` supplies
occupancy, pairing the newest provider-reported prompt size with the newest
capacity recorded by `request/context`. Deployments without token-meter drop
the token groups; a route whose adapter advertises no capacity drops the
occupancy group rather than rendering a placeholder.

Occupancy is deliberately approximate: the numerator and capacity are
independent last-wins fields, not one atomic request observation, so switching
models pairs a fresh capacity with the prior route's pressure until the next
request reports usage. It is a user-facing reference figure that nothing in the
harness makes decisions from, and it matches how the TUI status line has always
computed occupancy. The Agent Note and token-meter README state this as a
decision, including why the atomic alternative was implemented and rejected, so
it is not re-litigated as a defect.

Snapshot delta is one added `Context N% of 128K` segment across eight web
goldens; the preceding commit absorbed master's pre-existing golden drift.
2026-07-30 14:48:19 +08:00
Hypatia May 7f30a7e30c Merge remote-tracking branch 'origin/master' into codex/status-bar-token-metrics
Conflict resolution notes:

- StatsLine: master redesigned the row into pipe-separated groups with LLM and
  tool wall times. Kept that design and swapped only the token accounting
  source, so counts and durations stay window-scoped while billing and context
  occupancy read the durable projections.
- Generated artifacts (cordis catalog, module graph, event producer/consumer,
  i18n pairing hashes) and web snapshots took master's side; they are
  regenerated and re-recorded after this merge.
- Web e2e goldens and details-panel/timeline assertions took master's side:
  that evolution is unrelated to this branch.
- ui-conversation package.json: kept master's devDependency ordering, re-adding
  only the token-meter entry this branch needs.
2026-07-30 13:56:39 +08:00
Hypatia May 4819210142 refactor(token-meter): make context occupancy durable projection state
Replace the transient `session/model-request` mux frame with ordinary durable
session state. Occupancy now rides two last-wins projection fields instead of a
non-replayable frame that needed removal tombstones and cross-stream fencing.

The frame was the only non-replayable class on the mux stream. Because host and
mux are independent SSE streams with no cross-stream order, a request emitted
before a removal could arrive after `host/session-removed`, and a legitimate
request for a new lifecycle reusing the same id could be fenced by a late
removal. Fixing that needed a lifecycle generation on every frame; the frame
itself was the problem.

Removed: the `session/model-request` frame and schema, the `agent/model-request`
core event, the ApiProxy measurement point, the client-side telemetry map and
removal tombstone, and the synthetic `cancelled` open error used to signal
reconnect through the error channel.

Added: `request/context`, a log-only session event recording the
registration-bound capacity of the route a request resolved to, appended beside
`request/header` from the lookup that already prepared the call and skipped when
the route is unchanged. Capacity stays out of `EpochHeader` because it is
adapter metadata about a route, not an input the request was built from, so it
must not join request reconstruction or header equality.

The `contextPressure` projection pairs the newest provider-reported prompt size
with the newest recorded capacity. The two are deliberately not one atomic
request observation: switching models can pair a fresh capacity with the prior
route's pressure until the next request reports usage. The figure is a
user-facing reference, and this matches how the TUI status line has always
computed occupancy.
2026-07-30 13:53:08 +08:00
Hypatia May 840e5eaa40 fix(web): address request telemetry review 2026-07-29 16:42:36 +08:00
Hypatia May e37cb23336 feat(token-meter): project durable token usage 2026-07-29 14:35:24 +08:00
Turtle 95a995968b refactor: migrate linting to Oxlint 2026-07-29 14:32:11 +08:00
_Kerman fbf87e660c refactor: identify and freeze messages at creation 2026-07-28 13:55:59 +08:00
_Kerman 009d113e0e refactor(agent): trim obsolete loop surfaces 2026-07-24 21:58:07 +08:00
Tianyi Cui 72c6696e4f Merge branch 'master' into worktree/routed-model-compaction-policy
# Conflicts:
#	docs/event-producer-consumer.md
2026-07-21 19:23:54 +08:00
Yichen Jiang 49a9bca9f6 fix: validate compaction config pairs 2026-07-21 14:49:57 +08:00
Tianyi Cui 1145ee5fc3 fix(invariants): assert runtime relationships, not API shapes 2026-07-20 19:34:19 +08:00
Yichen Jiang cfa180c127 Resolve compaction policy per routed model 2026-07-20 15:34:00 +08:00
Tianyi Cui 941b0411d8 feat(invariants): implement package runtime checks 2026-07-20 00:38:37 +08:00
Tianyi Cui 433670a754 feat(invariants): require package-owned companions 2026-07-19 22:13:50 +08:00
Tianyi Cui 06ea8643ff Merge newest origin/master into token-meter-service 2026-07-17 22:49:54 +08:00
Hypatia May 06e0450b8d fix(token-meter): keep pressure anchors conservative 2026-07-16 15:26:30 +08:00
Hypatia May 6d96b3e4a8 refactor(token-meter): merge measurement snapshots (round 1) 2026-07-16 14:38:24 +08:00
Hypatia May 19a56ec542 fix(token-meter): reject stale config (round 2) 2026-07-16 13:23:20 +08:00
Hypatia May 5c243e8a8d refactor(token-meter): simplify singleton service (round 1) 2026-07-16 12:58:07 +08:00
Hypatia May f038780ff6 feat(llm): add replay token metering (PR2 round 1) 2026-07-15 14:47:29 +08:00