refactor: narrow compaction surface
This commit is contained in:
@@ -19,7 +19,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es
|
||||
| Member | Semantics |
|
||||
|---|---|
|
||||
| `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. |
|
||||
| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. |
|
||||
| `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. |
|
||||
|
||||
`compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value.
|
||||
|
||||
|
||||
@@ -14,7 +14,8 @@
|
||||
* implementation (deferred) / consumer (a `/compact` tool, deferred) — modeled
|
||||
* on the bash trio. Unlike `dsh-bash`, this interface necessarily
|
||||
* depends on `dsh-session` and `dsh-llm`: the contract's verbs are defined over
|
||||
* a `Session` and its output is the `ContentBlock` vocabulary. That deviation
|
||||
* an agent-owned `Session` and the durable summary event uses the
|
||||
* `ContentBlock` vocabulary. That deviation
|
||||
* from the "interface depends only on cordis" guidance is intentional and
|
||||
* recorded in the [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md).
|
||||
*
|
||||
@@ -132,10 +133,10 @@ export abstract class CompactService extends Service {
|
||||
* open (unclosed) tail step is invalid — its tool-calls have no results yet.
|
||||
* `dsh-session` exports `isToolPairingBalanced` for this check.
|
||||
*
|
||||
* @param session - the session whose surface is mutated.
|
||||
* @param start - inclusive seq of the first surface node to compact.
|
||||
* @param end - inclusive seq of the last surface node to compact.
|
||||
* @param agent - agent context used by router-aware summarizers.
|
||||
* @param agent - agent context whose session is mutated and whose routing
|
||||
* options are used by summarizers.
|
||||
* @param signal - optional cancellation signal. A backend that summarizes via
|
||||
* `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal`
|
||||
* so an abort/dispose tears down the in-flight summarization rather than
|
||||
@@ -146,10 +147,10 @@ export abstract class CompactService extends Service {
|
||||
* prior replace can leave the surface non-monotonic in seq order), or if
|
||||
* either boundary is not a balanced tool-pairing cut (would split a step's
|
||||
* tool-call/result pair).
|
||||
* @returns what the compaction did (the replaced range and its summary node).
|
||||
* @returns the replaced range and its token accounting. The durable
|
||||
* `compact/summary` event owns the summary and bookkeeping-event identity.
|
||||
*/
|
||||
abstract compactRegion(
|
||||
session: Session,
|
||||
start: number,
|
||||
end: number,
|
||||
agent: CompactAgentContext,
|
||||
|
||||
@@ -49,14 +49,6 @@ declare module '@deepseek-ai/dsh-session' {
|
||||
|
||||
/** Result of a successful compaction operation. */
|
||||
export interface CompactionResult {
|
||||
/** The seq of the appended `compact/start` event. */
|
||||
startSeq: number
|
||||
/** The seq of the appended `compact/summary` event. */
|
||||
summarySeq: number
|
||||
/** The seq of the appended `compact/end` event. */
|
||||
endSeq: number
|
||||
/** The summary content blocks produced by the backend. */
|
||||
summary: ContentBlock[]
|
||||
/**
|
||||
* The surface-boundary pair that was shadowed: the seqs of the first
|
||||
* (`start`) and last (`end`) surface nodes of the replaced range. A
|
||||
|
||||
@@ -27,28 +27,24 @@ class StubCompactService extends CompactService {
|
||||
}
|
||||
|
||||
override async compactRegion(
|
||||
session: Session,
|
||||
start: number,
|
||||
end: number,
|
||||
_agent: CompactAgentContext,
|
||||
agent: CompactAgentContext,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CompactionResult> {
|
||||
this.lastSignal = signal
|
||||
const session = agent.session
|
||||
// Minimal stub honoring the lock + log-only event contract.
|
||||
const startEvent = session.append('compact/start', { turn: 0 })
|
||||
const summaryEvent = session.append('compact/summary', {
|
||||
session.append('compact/start', { turn: 0 })
|
||||
session.append('compact/summary', {
|
||||
summary: [{ type: 'text', text: 'stub' }],
|
||||
shadowedRange: { start, end },
|
||||
shadowedSeqs: [],
|
||||
shadowedTokenCount: 0,
|
||||
model: 'stub',
|
||||
})
|
||||
const endEvent = session.append('compact/end', { turn: 0 })
|
||||
session.append('compact/end', { turn: 0 })
|
||||
return {
|
||||
startSeq: startEvent.seq,
|
||||
summarySeq: summaryEvent.seq,
|
||||
endSeq: endEvent.seq,
|
||||
summary: [{ type: 'text', text: 'stub' }],
|
||||
shadowedRange: { start, end },
|
||||
shadowedSeqs: [],
|
||||
shadowedTokenCount: 0,
|
||||
@@ -88,7 +84,7 @@ describe('CompactService seam', () => {
|
||||
const svc = new StubCompactService(ctx)
|
||||
const session = new Session(SessionId('s'))
|
||||
|
||||
const result = await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'))
|
||||
const result = await svc.compactRegion(0, 0, stubAgent(session, 'm'))
|
||||
|
||||
const startEvent = session.events.find(e => e.type === 'compact/start')
|
||||
expect(startEvent).toBeDefined()
|
||||
@@ -96,8 +92,9 @@ describe('CompactService seam', () => {
|
||||
// verify the runtime value is absent.
|
||||
const raw = startEvent as unknown as { surfaceOp?: unknown }
|
||||
expect(raw.surfaceOp).toBeUndefined()
|
||||
expect(result.summarySeq).toBeGreaterThan(result.startSeq)
|
||||
expect(result.endSeq).toBeGreaterThan(result.summarySeq)
|
||||
expect(result.shadowedRange).toEqual({ start: 0, end: 0 })
|
||||
expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type))
|
||||
.toEqual(['compact/start', 'compact/summary', 'compact/end'])
|
||||
})
|
||||
|
||||
it('threads the cancellation signal through to the backend', async () => {
|
||||
@@ -106,7 +103,7 @@ describe('CompactService seam', () => {
|
||||
const session = new Session(SessionId('s'))
|
||||
const controller = new AbortController()
|
||||
|
||||
await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal)
|
||||
await svc.compactRegion(0, 0, stubAgent(session, 'm'), controller.signal)
|
||||
expect(svc.lastSignal).toBe(controller.signal)
|
||||
|
||||
await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal)
|
||||
|
||||
Reference in New Issue
Block a user