Merge branch 'codex/invariant-service-seam' into codex/invariant-package-registration-gate

2026-07-20 19:48:51 +08:00
parent 3b7ce2e682 2f3ca3027b
commit 9c4cc05da6
391 changed files with 15415 additions and 8532 deletions
@@ -0,0 +1,77 @@
+/** Configuration resolution for deterministic tool-result pruning. */
+
+import { deepFreeze } from '@deepseek-ai/dsh-llm'
+import type { ResolvedConfig, ToolResultPruneConfig } from './types.ts'
+
+/** Fixed marker substituted for every removed middle span. */
+export const PRUNE_MARKER = '\n\n[... tool result middle pruned ...]\n\n'
+
+/** Low-friction defaults for coding-agent tool output. */
+export const DEFAULTS: ResolvedConfig = deepFreeze({
+  thresholdChars: 8192,
+  headChars: 4096,
+  tailChars: 1024,
+})
+
+const CONFIG_KEYS: ReadonlySet<string> = new Set([
+  'thresholdChars',
+  'headChars',
+  'tailChars',
+])
+
+/**
+ * Count Unicode code points without splitting surrogate pairs.
+ * @param text - text to measure.
+ * @returns the Unicode code-point count.
+ */
+export function codePointLength(text: string): number {
+  return Array.from(text).length
+}
+
+/**
+ * Resolve and validate pruning budgets.
+ * @param config - raw plugin configuration.
+ * @returns a detached deeply immutable configuration.
+ */
+export function resolveConfig(config: ToolResultPruneConfig = {}): ResolvedConfig {
+  for (const key of Object.keys(config)) {
+    if (!CONFIG_KEYS.has(key)) {
+      throw new Error(
+        `ToolResultPruneConfig: unknown key "${key}" `
+        + '(allowed: thresholdChars, headChars, tailChars)',
+      )
+    }
+  }
+
+  const resolved: ResolvedConfig = {
+    thresholdChars: config.thresholdChars ?? DEFAULTS.thresholdChars,
+    headChars: config.headChars ?? DEFAULTS.headChars,
+    tailChars: config.tailChars ?? DEFAULTS.tailChars,
+  }
+  assertPositiveInteger('thresholdChars', resolved.thresholdChars)
+  assertNonNegativeInteger('headChars', resolved.headChars)
+  assertNonNegativeInteger('tailChars', resolved.tailChars)
+
+  const emittedChars = resolved.headChars
+    + codePointLength(PRUNE_MARKER)
+    + resolved.tailChars
+  if (emittedChars > resolved.thresholdChars) {
+    throw new Error(
+      `ToolResultPruneConfig: headChars + marker + tailChars (${emittedChars}) `
+      + `must be at most thresholdChars (${resolved.thresholdChars})`,
+    )
+  }
+  return deepFreeze(structuredClone(resolved))
+}
+
+function assertPositiveInteger(name: string, value: number): void {
+  if (!Number.isInteger(value) || value <= 0) {
+    throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a positive integer`)
+  }
+}
+
+function assertNonNegativeInteger(name: string, value: number): void {
+  if (!Number.isInteger(value) || value < 0) {
+    throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a non-negative integer`)
+  }
+}
@@ -0,0 +1,159 @@
+/**
+ * Replay-safe, model-free tool-result pruning service.
+ *
+ * @module @deepseek-ai/dsh-compact-tool-result-prune
+ */
+
+import { Context, Service } from 'cordis'
+import z from 'schemastery'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
+import { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts'
+import type {
+  PrunedEntry,
+  PruneResult,
+  ResolvedConfig,
+  ToolResultPruneConfig,
+} from './types.ts'
+
+export { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts'
+export type {
+  PrunedEntry,
+  PruneResult,
+  ResolvedConfig,
+  ToolResultPruneConfig,
+} from './types.ts'
+
+declare module 'cordis' {
+  interface Context {
+    toolResultPrune: ToolResultPruneService
+  }
+}
+
+interface SnapshotCandidate {
+  readonly seq: number
+  readonly event: SessionEvent<'tool/result'>
+}
+
+/** Deterministic head/middle/tail pruning for current tool-result surface nodes. */
+export class ToolResultPruneService extends Service {
+  static Config: z<ToolResultPruneConfig> = z.object({
+    thresholdChars: z.number().step(1).min(1).default(DEFAULTS.thresholdChars),
+    headChars: z.number().step(1).min(0).default(DEFAULTS.headChars),
+    tailChars: z.number().step(1).min(0).default(DEFAULTS.tailChars),
+  })
+
+  /** Resolved and immutable character budgets. */
+  readonly config: ResolvedConfig
+
+  constructor(ctx: Context, config: ToolResultPruneConfig = {}) {
+    super(ctx, 'toolResultPrune')
+    this.config = resolveConfig(config)
+  }
+
+  /**
+   * Measure text content in Unicode code points; non-text blocks cost zero.
+   * @param blocks - tool-result content to measure.
+   * @returns total Unicode code points across text blocks.
+   */
+  measureContent(blocks: readonly ContentBlock[]): number {
+    let chars = 0
+    for (const block of blocks) {
+      if (block.type === 'text') chars += codePointLength(block.text)
+    }
+    return chars
+  }
+
+  /**
+   * Replace an over-budget text middle while retaining rich-block order.
+   * Text slicing is by Unicode code point, not UTF-16 code unit, so a retained
+   * boundary cannot split a surrogate pair. Grapheme clusters may still split.
+   * @param blocks - original tool-result content.
+   * @returns pruned content, or `null` when the text is within budget.
+   */
+  pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null {
+    const totalChars = this.measureContent(blocks)
+    if (totalChars <= this.config.thresholdChars) return null
+
+    const removedStart = this.config.headChars
+    const removedEnd = totalChars - this.config.tailChars
+    const pruned: ContentBlock[] = []
+    let consumed = 0
+    let markerInserted = false
+
+    for (const block of blocks) {
+      if (block.type !== 'text') {
+        pruned.push(block)
+        continue
+      }
+
+      const points = Array.from(block.text)
+      const blockStart = consumed
+      const blockEnd = blockStart + points.length
+      const headEnd = Math.min(points.length, Math.max(0, removedStart - blockStart))
+      const tailStart = Math.min(points.length, Math.max(0, removedEnd - blockStart))
+      const intersectsRemoved = blockStart < removedEnd && blockEnd > removedStart
+      const marker = intersectsRemoved && !markerInserted ? PRUNE_MARKER : ''
+      if (marker.length > 0) markerInserted = true
+      const text = points.slice(0, headEnd).join('')
+        + marker
+        + points.slice(tailStart).join('')
+      if (text.length > 0) pruned.push({ ...block, text })
+      consumed = blockEnd
+    }
+
+    /* v8 ignore next -- totalChars > threshold and valid budgets guarantee a removed text span. */
+    if (!markerInserted) throw new Error('tool-result prune: failed to locate the removed text span')
+    const charsAfter = this.measureContent(pruned)
+    /* v8 ignore next -- config validation fixes the emitted head + marker + tail budget. */
+    if (charsAfter > this.config.thresholdChars || charsAfter >= totalChars) {
+      throw new Error('tool-result prune: replacement must be smaller and within threshold')
+    }
+    return pruned
+  }
+
+  /**
+   * Prune every over-budget tool result from one stable current-surface snapshot.
+   * Each replacement preserves the complete event data except for `content`,
+   * and points at the shadowed node for durable provenance and replay.
+   * @param session - session whose current surface is rewritten.
+   * @returns landed replacements and aggregate Unicode-code-point savings.
+   * @throws when the session rejects a replacement; replacements committed
+   * earlier in the pass remain durable.
+   */
+  pruneSession(session: Session): PruneResult {
+    const candidates: SnapshotCandidate[] = []
+    for (const seq of [...session.surface.nodes]) {
+      const event = session.events[seq]
+      /* v8 ignore next -- surface seqs are validated contiguous log references. */
+      if (event?.type === 'tool/result') candidates.push({ seq, event })
+    }
+
+    const pruned: PrunedEntry[] = []
+    let charsRemoved = 0
+    for (const { seq, event } of candidates) {
+      const content = this.pruneContent(event.data.content)
+      if (content === null) continue
+      const charsBefore = this.measureContent(event.data.content)
+      const charsAfter = this.measureContent(content)
+      const replacement = session.append('tool/result', {
+        ...event.data,
+        content,
+      }, {
+        surfaceOp: { op: 'replace', start: seq, end: seq },
+        sourceEventSeqs: [seq],
+      })
+      pruned.push({
+        originalSeq: seq,
+        replacementSeq: replacement.seq,
+        callId: event.data.callId,
+        charsBefore,
+        charsAfter,
+      })
+      charsRemoved += charsBefore - charsAfter
+    }
+    return { pruned, charsRemoved }
+  }
+}
+
+export default ToolResultPruneService
@@ -0,0 +1,27 @@
+/**
+ * Package-owned invariant companion for `@deepseek-ai/dsh-compact-tool-result-prune`.
+ * @module @deepseek-ai/dsh-compact-tool-result-prune/invariant
+ */
+
+/* jscpd:ignore-start */
+import type { Context } from 'cordis'
+import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
+
+const PACKAGE_NAME = '@deepseek-ai/dsh-compact-tool-result-prune'
+
+/** Cordis companion plugin name. */
+export const name = 'compact-tool-result-prune-invariant'
+/** Services required before the companion can register. */
+export const inject = ['invariants']
+
+/** No runtime invariant: Session validates each content-only rewrite and its companion owns cross-event enclosure. */
+const install: InvariantInstaller = () => {}
+
+/**
+ * Register this package's invariant companion.
+ * @param ctx - Cordis context carrying the invariant service.
+ * @returns the installed registration's disposer after setup succeeds.
+ */
+export const apply = (ctx: Context): Promise<() => void> =>
+  Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
+/* jscpd:ignore-end */
@@ -0,0 +1,40 @@
+import type { CallId } from '@deepseek-ai/dsh-llm'
+
+/** Character-budget policy for deterministic tool-result pruning. */
+export interface ToolResultPruneConfig {
+  /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */
+  thresholdChars?: number
+  /** Maximum leading Unicode code points retained. Defaults to `4096`. */
+  headChars?: number
+  /** Maximum trailing Unicode code points retained. Defaults to `1024`. */
+  tailChars?: number
+}
+
+/** Validated, detached, deeply immutable pruning configuration. */
+export interface ResolvedConfig {
+  readonly thresholdChars: number
+  readonly headChars: number
+  readonly tailChars: number
+}
+
+/** Provenance and size accounting for one landed surface replacement. */
+export interface PrunedEntry {
+  /** Full-fidelity tool-result event shadowed by the replacement. */
+  readonly originalSeq: number
+  /** Newly appended pruned tool-result event. */
+  readonly replacementSeq: number
+  /** Tool call shared by the original and replacement. */
+  readonly callId: CallId
+  /** Original text size in Unicode code points. */
+  readonly charsBefore: number
+  /** Replacement text size in Unicode code points. */
+  readonly charsAfter: number
+}
+
+/** Aggregate outcome of one stable-surface pruning pass. */
+export interface PruneResult {
+  /** Replacements in the snapshotted surface order. */
+  readonly pruned: readonly PrunedEntry[]
+  /** Total Unicode code points removed across replacements. */
+  readonly charsRemoved: number
+}