Commit Graph

8 Commits

Author SHA1 Message Date
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 2f1ced77ca Merge remote-tracking branch 'origin/master' into codex/status-bar-token-metrics
# Conflicts:
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/event-producer-consumer.md
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/tests/request-reconstruction.spec.ts
#	packages/core/agent/README.i18n.yaml
#	packages/llm/llm/README.i18n.yaml
2026-07-28 19:54:58 +08:00
_Kerman fbf87e660c refactor: identify and freeze messages at creation 2026-07-28 13:55:59 +08:00
Hypatia May 9ca0241d5d feat(web): add durable session metrics (round 1) 2026-07-28 12:10:48 +08:00
_Kerman a59ce0367c fix(agent-loop): route next-step input during admission 2026-07-27 17:55:55 +08:00
_Kerman 1aefcbf4d7 fix(apiproxy): derive queued steering on the client, drop it from the wire
The session/queued frame no longer carries steering — AgentMessage no longer
has the field. The client derives it from the same ordered turn boundaries the
host saw (a frame arriving while a turn is open joined the steering FIFO).
2026-07-27 10:22:28 +08:00
imccyu f6396f2573 style: fix lint across client packages
eslint --fix autofixes plus manual repairs: max-len line splits
(fake-api handlers, notifier/slots JSDoc, spec signatures), charAt over
non-null-asserted indexing in slash detect/menu cores, Array.from for
code-point capping, typeof assertions for unbound-method in specs,
generic getByRole for the send-button cast, effect disposer void-wrap in
command register, and dropped unused type imports.
2026-07-27 04:13:00 +08:00
imccyu a27be43ac1 feat: slash system / input service / agent scope 2026-07-27 03:28:39 +08:00