From fc6eb4e7a3598c1380f0dd7200f8a043fc9bb2a6 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Tue, 28 Jul 2026 19:44:29 +0800 Subject: [PATCH] fix(web): retain live capacity before session creation --- .../runtime/src/client/sessions/manager.ts | 16 +++ .../runtime/src/client/sessions/session.ts | 9 +- packages/client/runtime/tests/manager.spec.ts | 121 ++++++++++++++++++ 3 files changed, 144 insertions(+), 2 deletions(-) diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index 66a0d00dd9..b6daecb97c 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -57,6 +57,12 @@ export class SessionManager { * drop-and-backfill path; replayed and cleared on instantiation. Bounded per session (these * frames are low-frequency; overflow drops oldest) and dropped on session-removed (audit S7). */ private readonly pendingBuffers = new Map[]>() + /** + * Latest model capacity observed for an uninstantiated session on the + * current mux generation. Unlike durable history, this transient frame + * cannot be backfilled when get() lazily creates the Session. + */ + private readonly modelRequestContextWindows = new Map() /** Per-session projection value stores, retained independently of instance arrival (the * title-snapshot precedent, generalized): push frames land here whether or not the Session * is instantiated (list rows read the 'title' key), and an instantiated Session adopts the @@ -160,6 +166,7 @@ export class SessionManager { } private createSession(sessionId: SessionId): Session { + const modelRequestContextWindow = this.modelRequestContextWindows.get(sessionId) return new Session(sessionId, this.api, { // The sender's local first-send flip mirrors into the list row so the // session surfaces (lists filter on blank) before any host frame lands. @@ -167,6 +174,7 @@ export class SessionManager { this.recordMutation({ kind: 'engaged', sessionId: engaged.sessionId }) }, projections: this.projectionStore(sessionId), + ...(modelRequestContextWindow === undefined ? {} : { modelRequestContextWindow }), }) } @@ -328,7 +336,14 @@ export class SessionManager { this.notifier.markDirty() return } + if (frame.type === 'session/model-request') { + // Transient and non-replayable: retain the latest capacity until lazy + // instantiation. An absent value explicitly clears an earlier one. + if (frame.contextWindow === undefined) this.modelRequestContextWindows.delete(frame.sessionId) + else this.modelRequestContextWindows.set(frame.sessionId, frame.contextWindow) + } if (frame.type === 'session/subscribed') { + this.modelRequestContextWindows.delete(frame.sessionId) // Rows past the host's durable baseline rode state a restart lost; drop // them so last-wins cannot pin a phantom value over recomputed truth. this.projectionStores.get(frame.sessionId)?.truncate(frame.lastSeq) @@ -391,6 +406,7 @@ export class SessionManager { this.recordMutation({ kind: 'remove', sessionId: frame.sessionId }) this.sessions.get(frame.sessionId)?.handleRemoved() // instance survives (resident-instance rule), only flagged in the snapshot this.pendingBuffers.delete(frame.sessionId) // a removed session's buffered frames must not replay on a future instantiation + this.modelRequestContextWindows.delete(frame.sessionId) // connection-local request capacity dies with the Host session this.projectionStores.delete(frame.sessionId) // removed sessions drop their projection rows with the instance return } diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index f3f4891de2..8c4cee798d 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -43,6 +43,8 @@ export interface SessionOptions { * private store (bare object-layer construction). */ projections?: ProjectionValueStore + /** Model capacity already observed on this mux generation before lazy construction. */ + modelRequestContextWindow?: number } /** Queue-row preview cap: the dock renders one line, the full content never leaves the host mirror. */ @@ -172,6 +174,7 @@ export class Session implements ObservableSnapshot { private readonly options: SessionOptions = {}, ) { this.projections = options.projections ?? new ProjectionValueStore() + this.contextWindow = options.modelRequestContextWindow this.snapshotCache = this.buildSnapshot() } @@ -479,10 +482,12 @@ export class Session implements ObservableSnapshot { this.notifier.markDirty() } - /** host/session-removed relay: flag the snapshot (instance survives — resident-instance rule). */ + /** host/session-removed relay: flag the resident snapshot and clear connection-local capacity. */ handleRemoved(): void { + const changed = !this.removed || this.contextWindow !== undefined this.removed = true - this.notifier.markDirty() + this.contextWindow = undefined + if (changed) this.notifier.markDirty() } /** diff --git a/packages/client/runtime/tests/manager.spec.ts b/packages/client/runtime/tests/manager.spec.ts index 2923cd0d3c..410058228d 100644 --- a/packages/client/runtime/tests/manager.spec.ts +++ b/packages/client/runtime/tests/manager.spec.ts @@ -41,6 +41,127 @@ describe('instances', () => { expect(manager.get(S2).getSnapshot().pending).toEqual([]) }) + it('retains the latest transient model capacity until lazy instantiation', () => { + const api = new FakeApiClient() + const manager = new SessionManager(api) + manager.handleMuxEnvelope({ + rpcId: 'request-1' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 1, + provider: 'test', + model: 'alpha', + contextWindow: 128_000, + }, + }) + manager.handleMuxEnvelope({ + rpcId: 'request-2' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 2, + provider: 'test', + model: 'beta', + contextWindow: 256_000, + }, + }) + + expect(manager.get(S1).getSnapshot().modelRequestContextWindow).toBe(256_000) + }) + + it('retains explicit capacity clearing before lazy instantiation', () => { + const api = new FakeApiClient() + const manager = new SessionManager(api) + manager.handleMuxEnvelope({ + rpcId: 'request-with-capacity' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 1, + provider: 'test', + model: 'alpha', + contextWindow: 128_000, + }, + }) + manager.handleMuxEnvelope({ + rpcId: 'request-without-capacity' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 2, + provider: 'test', + model: 'unknown-capacity', + }, + }) + + expect(manager.get(S1).getSnapshot().modelRequestContextWindow).toBeUndefined() + }) + + it('clears retained capacity on subscribed and resident capacity on removal', () => { + const api = new FakeApiClient() + const manager = new SessionManager(api) + manager.handleMuxEnvelope({ + rpcId: 'request-before-subscribe' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 1, + provider: 'test', + model: 'alpha', + contextWindow: 128_000, + }, + }) + manager.handleMuxEnvelope({ + rpcId: 'subscribed' as never, + payload: { type: 'session/subscribed', sessionId: S1, lastSeq: 0 }, + }) + const session = manager.get(S1) + expect(session.getSnapshot().modelRequestContextWindow).toBeUndefined() + + manager.handleMuxEnvelope({ + rpcId: 'request-after-subscribe' as never, + payload: { + type: 'session/model-request', + sessionId: S1, + turn: 1, + step: 2, + provider: 'test', + model: 'beta', + contextWindow: 256_000, + }, + }) + expect(session.getSnapshot().modelRequestContextWindow).toBe(256_000) + manager.handleHostEnvelope({ + rpcId: 'removed' as never, + payload: { type: 'host/session-removed', sessionId: S1 }, + }) + expect(session.getSnapshot().modelRequestContextWindow).toBeUndefined() + + manager.handleMuxEnvelope({ + rpcId: 'request-before-lazy-removal' as never, + payload: { + type: 'session/model-request', + sessionId: S2, + turn: 1, + step: 1, + provider: 'test', + model: 'gamma', + contextWindow: 64_000, + }, + }) + manager.handleHostEnvelope({ + rpcId: 'lazy-removed' as never, + payload: { type: 'host/session-removed', sessionId: S2 }, + }) + expect(manager.get(S2).getSnapshot().modelRequestContextWindow).toBeUndefined() + }) + it('caps the pending buffer at 32 keeping the newest, and drops it on session-removed', () => { const api = new FakeApiClient() const manager = new SessionManager(api)