Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(token-meter): make context occupancy durable projection state

Browse Source 
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.
This commit is contained in:
Hypatia May
2026-07-30 13:53:08 +08:00
parent fdccc58cef
commit 4819210142
62 changed files with 382 additions and 1362 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
packages/client/connection/tests/fixture.spec.ts
View File

@@ -194,19 +194,17 @@ describe('createFixtureApi', () => {
expect(types).toContain('assistant/chunk')
expect(types).toContain('assistant/message')
expect(types.at(-1)).toBe('turn/end')
expect(frames).toContainEqual({
type: 'session/model-request',
sessionId: id,
turn: 1,
step: 1,
provider: 'deepseek',
model: 'deepseek-v4-flash',
contextWindow: 128_000,
})
// Capacity is durable log state, not a transient frame: the prompt path
// records request/context and the projection carries it to the client.
expect(types).toContain('request/context')
expect(frames.some(frame =>
frame.type === 'session/projection'
&& frame.key === 'tokenUsage'
&& (frame.value as { outputTokens?: number }).outputTokens === 8)).toBe(true)
expect(frames.some(frame =>
frame.type === 'session/projection'
&& frame.key === 'contextPressure'
&& (frame.value as { contextWindow?: number }).contextWindow === 128_000)).toBe(true)
const finalize = frames.find((f): f is Extract<MuxFrame, { type: 'session/event' }> => f.type === 'session/event' && f.event.type === 'assistant/message')
expect(JSON.stringify(finalize?.event.data)).toContain('（已中断）')
// Idle cancel: no replay in flight, must not explode; running flips false.
@@ -238,7 +236,7 @@ describe('createFixtureApi', () => {
const envelopes: RpcRequest<MuxFrame>[] = []
for await (const envelope of api.events.mux(req({}), abort.signal)) {
envelopes.push(envelope)
if (envelopes.length >= 9) abort.abort()
if (envelopes.length >= 10) abort.abort()
}
return envelopes
}
@@ -253,11 +251,11 @@ describe('createFixtureApi', () => {
expect(first[4]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'plan', value: { active: false, pending: false } })
expect(first[5]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'goal', value: null })
expect(first[6]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'tokenUsage' })
expect(first[7]?.payload).toMatchObject({ type: 'approval/requested', toolName: 'dangerous_tool' })
expect(second[7]?.rpcId).toBe(first[7]?.rpcId) // stable rpcId across replays (host replay semantics)
expect(first[8]?.payload).toMatchObject({ type: 'question/requested', sessionId: 'fx-alpha' })
expect(second[8]?.rpcId).toBe(first[8]?.rpcId)
expect(first.some(envelope => envelope.payload.type === 'session/model-request')).toBe(false)
expect(first[7]?.payload).toMatchObject({ type: 'session/projection', sessionId: 'fx-alpha', key: 'contextPressure' })
expect(first[8]?.payload).toMatchObject({ type: 'approval/requested', toolName: 'dangerous_tool' })
expect(second[8]?.rpcId).toBe(first[8]?.rpcId) // stable rpcId across replays (host replay semantics)
expect(first[9]?.payload).toMatchObject({ type: 'question/requested', sessionId: 'fx-alpha' })
expect(second[9]?.rpcId).toBe(first[9]?.rpcId)
})
it('steer with no replay in flight falls through to a fresh queued turn; non-text blocks stringify empty', async () => {