@pi-unipi/background-tasks 2.16.0 → 2.17.0

package/src/fusion/child-protocol.ts

@@ -1,305 +0,0 @@
-import { createHash } from 'node:crypto';
-import type { Usage } from '@earendil-works/pi-ai';
-import type { FusionClaudeCacheObservation } from './claude-cache.js';
-import {
-  FUSION_CANDIDATE_MAX_OUTPUT_BYTES,
-  fusionJsonRenderedTextBytes,
-} from './output-contract.js';
-
-export const FUSION_CHILD_RESULT_SCHEMA_VERSION =
-  'pi-background-tasks.fusion-child-result.v4' as const;
-export const FUSION_CHILD_RESULT_PREFIX = '\u001ePI_FUSION_CHILD_RESULT ';
-export const FUSION_CHILD_SETTLEMENT_SCHEMA_VERSION =
-  'pi-background-tasks.fusion-child-settlement.v3' as const;
-export const FUSION_CHILD_SETTLEMENT_PREFIX = '\u001ePI_FUSION_CHILD_SETTLEMENT ';
-export const FUSION_TOOL_CALL_LOG_PATH_ENV = 'PI_FUSION_TOOL_CALL_LOG_PATH';
-export const FUSION_CANDIDATE_OUTPUT_RECOVERY_PATH_ENV = 'PI_FUSION_CANDIDATE_OUTPUT_RECOVERY_PATH';
-export const FUSION_RESEARCH_ENABLED_ENV = 'PI_FUSION_RESEARCH_ENABLED';
-export const FUSION_SOURCE_POLICY_PATH_ENV = 'PI_FUSION_SOURCE_POLICY_PATH';
-export const FUSION_SOURCE_POLICY_SHA256_ENV = 'PI_FUSION_SOURCE_POLICY_SHA256';
-export const FUSION_TOOL_CALL_SEAL_SCHEMA_VERSION =
-  'pi-background-tasks.fusion-tool-call-seal.v1' as const;
-export const FUSION_TOOL_CALL_SEAL_SUFFIX = '.seal.json';
-export const FUSION_RUNTIME_GUARD_SCHEMA_VERSION =
-  'pi-background-tasks.fusion-runtime-guard.v2' as const;
-export const FUSION_RUNTIME_GUARD_PREFIX = '\u001ePI_FUSION_RUNTIME_GUARD ';
-export const FUSION_CHILD_MAX_PROVIDER_REQUESTS = 550;
-export const FUSION_CHILD_MAX_TOOL_CALLS = 600;
-
-/**
- * Aggregate ceiling on tool-result bytes a single candidate child may accumulate.
- *
- * The byte ceiling complements the tool/request count limits and pre-spawn stage
- * budgets. It remains an independent bound on total tool material across the child run.
- */
-export const FUSION_CHILD_MAX_TOTAL_TOOL_RESULT_BYTES = 32 * 1024 * 1024;
-
-export type FusionRuntimeGuardCode =
-  | 'provider_request_limit'
-  | 'provider_payload_invalid'
-  | 'claude_cache_policy'
-  | 'tool_call_limit';
-
-export interface FusionRuntimeGuardRecord {
-  schema_version: typeof FUSION_RUNTIME_GUARD_SCHEMA_VERSION;
-  code: FusionRuntimeGuardCode;
-  provider: string;
-  model: string;
-  request_ordinal: number;
-  tool_call_count: number;
-  payload_bytes: number;
-  payload_sha256: string;
-  message: string;
-}
-
-export interface FusionChildTextBlockMetadata {
-  utf8_bytes: number;
-  sha256: string;
-}
-
-export type FusionChildResultUsageMetadata = Usage;
-
-export type FusionChildOutputRecoveryRole = 'none' | 'oversized_original' | 'replacement';
-
-export interface FusionChildOutputContractMetadata {
-  json_rendered_bytes: number;
-  candidate_limit_bytes: number | null;
-  recovery_role: FusionChildOutputRecoveryRole;
-}
-
-export interface FusionChildResultMetadata {
-  schema_version: typeof FUSION_CHILD_RESULT_SCHEMA_VERSION;
-  provider: string;
-  model: string;
-  stop_reason: string;
-  text_blocks: FusionChildTextBlockMetadata[];
-  text_sha256: string;
-  usage: FusionChildResultUsageMetadata;
-  cache_observation: FusionClaudeCacheObservation;
-  output_contract: FusionChildOutputContractMetadata;
-}
-
-export type FusionChildSettlementFailureReason =
-  | 'no_records'
-  | 'final_not_stop'
-  | 'invalid_non_final'
-  | 'runtime_guard'
-  | 'cache_observation'
-  | 'output_recovery';
-
-export interface FusionChildSettlementRecord {
-  schema_version: typeof FUSION_CHILD_SETTLEMENT_SCHEMA_VERSION;
-  status: 'complete' | 'failed';
-  record_count: number;
-  records_sha256: string;
-  final_record_index: number | null;
-  final_text_sha256: string | null;
-  recovered_error_ordinals: number[];
-  recovered_output_cap_ordinals: number[];
-  failure_reason: FusionChildSettlementFailureReason | null;
-}
-
-function protocolSha256(value: string | Buffer): string {
-  return createHash('sha256').update(value).digest('hex');
-}
-
-export function serializeFusionChildResultRecords(
-  records: readonly FusionChildResultMetadata[],
-): Buffer {
-  return Buffer.from(
-    records.length === 0 ? '' : `${records.map((record) => JSON.stringify(record)).join('\n')}\n`,
-    'utf8',
-  );
-}
-
-function hasZeroUsage(record: FusionChildResultMetadata): boolean {
-  const usage = record.usage;
-  return (
-    usage.input === 0 &&
-    usage.output === 0 &&
-    usage.cacheRead === 0 &&
-    usage.cacheWrite === 0 &&
-    usage.totalTokens === 0 &&
-    usage.cost.input === 0 &&
-    usage.cost.output === 0 &&
-    usage.cost.cacheRead === 0 &&
-    usage.cost.cacheWrite === 0 &&
-    usage.cost.total === 0
-  );
-}
-
-export function isRecoverableFusionChildErrorRecord(record: FusionChildResultMetadata): boolean {
-  return (
-    record.stop_reason === 'error' &&
-    record.text_blocks.length === 0 &&
-    record.text_sha256 === protocolSha256(Buffer.alloc(0)) &&
-    hasZeroUsage(record) &&
-    record.output_contract.recovery_role === 'none'
-  );
-}
-
-function isOversizedOriginal(record: FusionChildResultMetadata): boolean {
-  const output = record.output_contract;
-  return (
-    output.recovery_role === 'oversized_original' &&
-    output.candidate_limit_bytes === FUSION_CANDIDATE_MAX_OUTPUT_BYTES &&
-    output.json_rendered_bytes > FUSION_CANDIDATE_MAX_OUTPUT_BYTES &&
-    record.stop_reason === 'stop'
-  );
-}
-
-function outputRecoveryProtocolInvalid(records: readonly FusionChildResultMetadata[]): boolean {
-  const originals = records.flatMap((record, ordinal) =>
-    record.output_contract.recovery_role === 'oversized_original' ? [ordinal] : [],
-  );
-  const replacements = records.flatMap((record, ordinal) =>
-    record.output_contract.recovery_role === 'replacement' ? [ordinal] : [],
-  );
-  for (const record of records) {
-    const output = record.output_contract;
-    if (
-      output.candidate_limit_bytes !== null &&
-      output.candidate_limit_bytes !== FUSION_CANDIDATE_MAX_OUTPUT_BYTES
-    ) {
-      return true;
-    }
-    if (output.recovery_role !== 'none' && output.candidate_limit_bytes === null) return true;
-    if (output.recovery_role === 'oversized_original' && !isOversizedOriginal(record)) return true;
-  }
-  if (originals.length === 0 && replacements.length === 0) return false;
-  if (originals.length !== 1 || replacements.length !== 1) return true;
-  const original = originals[0];
-  const replacement = replacements[0];
-  return (
-    original === undefined ||
-    replacement === undefined ||
-    original !== records.length - 2 ||
-    replacement !== records.length - 1
-  );
-}
-
-function finalCandidateOutputExceedsContract(
-  records: readonly FusionChildResultMetadata[],
-): boolean {
-  const final = records.at(-1);
-  if (final === undefined) return false;
-  const output = final.output_contract;
-  return (
-    output.candidate_limit_bytes === FUSION_CANDIDATE_MAX_OUTPUT_BYTES &&
-    output.json_rendered_bytes > FUSION_CANDIDATE_MAX_OUTPUT_BYTES
-  );
-}
-
-export function buildFusionChildSettlement(
-  records: readonly FusionChildResultMetadata[],
-  runtimeGuardFailed = false,
-  cacheObservationFailed = false,
-  outputRecoveryFailed = false,
-): FusionChildSettlementRecord {
-  const finalRecordIndex = records.length === 0 ? null : records.length - 1;
-  const final = records.at(-1);
-  const recoveredErrorOrdinals = records.flatMap((record, ordinal) =>
-    ordinal < records.length - 1 && isRecoverableFusionChildErrorRecord(record) ? [ordinal] : [],
-  );
-  const recoveredOutputCapOrdinals = records.flatMap((record, ordinal) =>
-    ordinal < records.length - 1 && isOversizedOriginal(record) ? [ordinal] : [],
-  );
-  const invalidRecovery = outputRecoveryProtocolInvalid(records);
-  const invalidNonFinal = records.some(
-    (record, ordinal) =>
-      ordinal < records.length - 1 &&
-      record.stop_reason !== 'toolUse' &&
-      !isRecoverableFusionChildErrorRecord(record) &&
-      !isOversizedOriginal(record),
-  );
-  let failureReason: FusionChildSettlementFailureReason | null = null;
-  if (runtimeGuardFailed) failureReason = 'runtime_guard';
-  else if (cacheObservationFailed) failureReason = 'cache_observation';
-  else if (final === undefined) failureReason = 'no_records';
-  else if (final.stop_reason !== 'stop') failureReason = 'final_not_stop';
-  else if (
-    outputRecoveryFailed ||
-    invalidRecovery ||
-    finalCandidateOutputExceedsContract(records)
-  ) {
-    failureReason = 'output_recovery';
-  } else if (invalidNonFinal) failureReason = 'invalid_non_final';
-  return {
-    schema_version: FUSION_CHILD_SETTLEMENT_SCHEMA_VERSION,
-    status: failureReason === null ? 'complete' : 'failed',
-    record_count: records.length,
-    records_sha256: protocolSha256(serializeFusionChildResultRecords(records)),
-    final_record_index: finalRecordIndex,
-    final_text_sha256: final?.text_sha256 ?? null,
-    recovered_error_ordinals: recoveredErrorOrdinals,
-    recovered_output_cap_ordinals: recoveredOutputCapOrdinals,
-    failure_reason: failureReason,
-  };
-}
-
-export function buildFusionChildResultMetadata(
-  message: {
-    provider: string;
-    model: string;
-    stopReason: string;
-    content: ReadonlyArray<{ type: string; text?: string }>;
-    usage: Usage;
-  },
-  cacheObservation: FusionClaudeCacheObservation,
-  outputContract: {
-    candidateLimitBytes: number | null;
-    recoveryRole: FusionChildOutputRecoveryRole;
-  } = { candidateLimitBytes: null, recoveryRole: 'none' },
-): FusionChildResultMetadata {
-  if (
-    outputContract.candidateLimitBytes !== null &&
-    outputContract.candidateLimitBytes !== FUSION_CANDIDATE_MAX_OUTPUT_BYTES
-  ) {
-    throw new Error('fusion child candidate output limit does not match the shared contract');
-  }
-  if (outputContract.recoveryRole !== 'none' && outputContract.candidateLimitBytes === null) {
-    throw new Error('fusion child output recovery role requires the candidate output contract');
-  }
-  const textBlocks = message.content.flatMap((part) =>
-    part.type === 'text' && typeof part.text === 'string' ? [part.text] : [],
-  );
-  const text = textBlocks.join('');
-  const usage: FusionChildResultUsageMetadata = {
-    input: message.usage.input,
-    output: message.usage.output,
-    cacheRead: message.usage.cacheRead,
-    cacheWrite: message.usage.cacheWrite,
-    ...(message.usage.cacheWrite1h === undefined
-      ? {}
-      : { cacheWrite1h: message.usage.cacheWrite1h }),
-    ...(message.usage["reasoning" as keyof typeof message.usage] === undefined
-      ? {}
-      : { reasoning: message.usage["reasoning" as keyof typeof message.usage] as number }),
-    totalTokens: message.usage.totalTokens,
-    cost: {
-      input: message.usage.cost.input,
-      output: message.usage.cost.output,
-      cacheRead: message.usage.cost.cacheRead,
-      cacheWrite: message.usage.cost.cacheWrite,
-      total: message.usage.cost.total,
-    },
-  };
-  return {
-    schema_version: FUSION_CHILD_RESULT_SCHEMA_VERSION,
-    provider: message.provider,
-    model: message.model,
-    stop_reason: message.stopReason,
-    text_blocks: textBlocks.map((blockText) => ({
-      utf8_bytes: Buffer.byteLength(blockText, 'utf8'),
-      sha256: protocolSha256(blockText),
-    })),
-    text_sha256: protocolSha256(text),
-    usage,
-    cache_observation: cacheObservation,
-    output_contract: {
-      json_rendered_bytes: fusionJsonRenderedTextBytes(text),
-      candidate_limit_bytes: outputContract.candidateLimitBytes,
-      recovery_role: outputContract.recoveryRole,
-    },
-  };
-}

package/src/fusion/claude-cache.ts

@@ -1,207 +0,0 @@
-import type { JsonObject } from '../types.js';
-
-export const FUSION_CLAUDE_CACHE_OBSERVATION_SCHEMA_VERSION =
-  'pi-background-tasks.fusion-claude-cache-observation.v1' as const;
-export const FUSION_CLAUDE_CACHE_RETENTION_ENV = 'PI_CACHE_RETENTION';
-export const FUSION_CLAUDE_CACHE_DEFAULT_RETENTION = 'long' as const;
-export const FUSION_CLAUDE_CACHE_BREAKPOINT_LIMIT = 4;
-export const FUSION_CLAUDE_PROMPT_CACHING_SCOPE_BETA = 'prompt-caching-scope-2026-01-05' as const;
-
-export type FusionClaudeCacheRetention = 'none' | 'short' | 'long';
-export type FusionClaudeCachePolicySource =
-  | 'default'
-  | typeof FUSION_CLAUDE_CACHE_RETENTION_ENV
-  | 'not_applicable';
-
-export interface FusionClaudeCacheObservation {
-  schema_version: typeof FUSION_CLAUDE_CACHE_OBSERVATION_SCHEMA_VERSION;
-  applicability: 'anthropic' | 'not_applicable';
-  source: FusionClaudeCachePolicySource;
-  requested_retention: FusionClaudeCacheRetention | null;
-  effective_retention: FusionClaudeCacheRetention | null;
-  breakpoint_count: number;
-  request_ordinal: number;
-}
-
-export interface FusionClaudeCacheNormalization {
-  payload: JsonObject;
-  observation: FusionClaudeCacheObservation;
-}
-
-function isRecord(value: unknown): value is JsonObject {
-  return typeof value === 'object' && value !== null && !Array.isArray(value);
-}
-
-function unknownArray(value: unknown): unknown[] | undefined {
-  return Array.isArray(value) ? (value as unknown[]) : undefined;
-}
-
-function requireRequestOrdinal(value: number): number {
-  if (!Number.isSafeInteger(value) || value <= 0) {
-    throw new Error('Fusion Claude cache request ordinal must be a positive safe integer');
-  }
-  return value;
-}
-
-function parseRetention(value: string): FusionClaudeCacheRetention {
-  if (value === 'none' || value === 'short' || value === 'long') return value;
-  throw new Error(
-    `${FUSION_CLAUDE_CACHE_RETENTION_ENV} must be one of none, short, or long; got ${JSON.stringify(value)}`,
-  );
-}
-
-export function resolveFusionClaudeCachePolicy(env: Readonly<NodeJS.ProcessEnv> = process.env): {
-  retention: FusionClaudeCacheRetention;
-  source: FusionClaudeCachePolicySource;
-} {
-  const configured = env[FUSION_CLAUDE_CACHE_RETENTION_ENV];
-  if (configured === undefined) {
-    return { retention: FUSION_CLAUDE_CACHE_DEFAULT_RETENTION, source: 'default' };
-  }
-  return {
-    retention: parseRetention(configured),
-    source: FUSION_CLAUDE_CACHE_RETENTION_ENV,
-  };
-}
-
-export function applyFusionClaudePromptCachingScopeHeader(
-  headers: Record<string, string | null>,
-): boolean {
-  const matchingKey = Object.keys(headers).find((key) => key.toLowerCase() === 'anthropic-beta');
-  const existing = matchingKey === undefined ? undefined : headers[matchingKey];
-  const values =
-    typeof existing === 'string'
-      ? existing
-          .split(',')
-          .map((value) => value.trim())
-          .filter((value) => value.length > 0)
-      : [];
-  if (!values.includes(FUSION_CLAUDE_PROMPT_CACHING_SCOPE_BETA)) {
-    values.push(FUSION_CLAUDE_PROMPT_CACHING_SCOPE_BETA);
-  }
-  const targetKey = matchingKey ?? 'anthropic-beta';
-  headers[targetKey] = values.join(',');
-  return true;
-}
-
-function validateCacheControl(value: unknown): JsonObject {
-  if (!isRecord(value)) {
-    throw new Error('Fusion Claude cache_control must be an object');
-  }
-  if (value['type'] !== 'ephemeral') {
-    throw new Error('Fusion Claude cache_control.type must be "ephemeral"');
-  }
-  const ttl = value['ttl'];
-  if (ttl !== undefined && ttl !== '1h' && ttl !== '5m') {
-    throw new Error('Fusion Claude cache_control.ttl must be "1h" or "5m" when present');
-  }
-  return value;
-}
-
-/**
- * Normalize only cache breakpoints already selected by Pi's Anthropic adapter.
- *
- * Not creating new breakpoints is deliberate: an empty marker set may represent
- * Pi's explicit cacheRetention="none" compaction request or a model compatibility
- * restriction. The package may strengthen or disable native markers, but it must
- * not override an upstream call-level opt-out that is no longer visible in the
- * final provider payload.
- */
-export function normalizeFusionClaudeCachePayload(input: {
-  payload: unknown;
-  requestOrdinal: number;
-  env?: Readonly<NodeJS.ProcessEnv>;
-  supportsLongCacheRetention?: boolean | undefined;
-}): FusionClaudeCacheNormalization {
-  if (!isRecord(input.payload)) {
-    throw new Error('Fusion Claude provider payload must be an object');
-  }
-  const requestOrdinal = requireRequestOrdinal(input.requestOrdinal);
-  const policy = resolveFusionClaudeCachePolicy(input.env ?? process.env);
-  const normalizedRetention: FusionClaudeCacheRetention =
-    policy.retention === 'long' && input.supportsLongCacheRetention === false
-      ? 'short'
-      : policy.retention;
-  let incomingBreakpoints = 0;
-  let outputBreakpoints = 0;
-
-  const normalizeBlock = (value: unknown): unknown => {
-    if (!isRecord(value) || !Object.hasOwn(value, 'cache_control')) return value;
-    const existing = value['cache_control'];
-    if (existing === undefined) {
-      const next = { ...value };
-      Reflect.deleteProperty(next, 'cache_control');
-      return next;
-    }
-    incomingBreakpoints += 1;
-    if (incomingBreakpoints > FUSION_CLAUDE_CACHE_BREAKPOINT_LIMIT) {
-      throw new Error(
-        `Fusion Claude payload has ${String(incomingBreakpoints)} cache_control breakpoints; Anthropic supports at most ${String(FUSION_CLAUDE_CACHE_BREAKPOINT_LIMIT)}`,
-      );
-    }
-    const control = validateCacheControl(existing);
-    const next = { ...value };
-    if (normalizedRetention === 'none') {
-      Reflect.deleteProperty(next, 'cache_control');
-      return next;
-    }
-    const normalizedControl = { ...control, type: 'ephemeral' };
-    Reflect.deleteProperty(normalizedControl, 'ttl');
-    if (normalizedRetention === 'long') Object.assign(normalizedControl, { ttl: '1h' });
-    next['cache_control'] = normalizedControl;
-    outputBreakpoints += 1;
-    return next;
-  };
-
-  const system = unknownArray(input.payload['system']);
-  const tools = unknownArray(input.payload['tools']);
-  const messages = unknownArray(input.payload['messages']);
-  const payload = {
-    ...input.payload,
-    ...(system === undefined ? {} : { system: system.map(normalizeBlock) }),
-    ...(tools === undefined ? {} : { tools: tools.map(normalizeBlock) }),
-    ...(messages === undefined
-      ? {}
-      : {
-          messages: messages.map((message) => {
-            if (!isRecord(message)) return message;
-            const content = unknownArray(message['content']);
-            return content === undefined
-              ? message
-              : { ...message, content: content.map(normalizeBlock) };
-          }),
-        }),
-  };
-  if (outputBreakpoints > FUSION_CLAUDE_CACHE_BREAKPOINT_LIMIT) {
-    throw new Error(
-      `Fusion Claude payload produced ${String(outputBreakpoints)} cache_control breakpoints; Anthropic supports at most ${String(FUSION_CLAUDE_CACHE_BREAKPOINT_LIMIT)}`,
-    );
-  }
-
-  return {
-    payload,
-    observation: {
-      schema_version: FUSION_CLAUDE_CACHE_OBSERVATION_SCHEMA_VERSION,
-      applicability: 'anthropic',
-      source: policy.source,
-      requested_retention: policy.retention,
-      effective_retention: outputBreakpoints === 0 ? 'none' : normalizedRetention,
-      breakpoint_count: outputBreakpoints,
-      request_ordinal: requestOrdinal,
-    },
-  };
-}
-
-export function nonAnthropicFusionCacheObservation(
-  requestOrdinal: number,
-): FusionClaudeCacheObservation {
-  return {
-    schema_version: FUSION_CLAUDE_CACHE_OBSERVATION_SCHEMA_VERSION,
-    applicability: 'not_applicable',
-    source: 'not_applicable',
-    requested_retention: null,
-    effective_retention: null,
-    breakpoint_count: 0,
-    request_ordinal: requireRequestOrdinal(requestOrdinal),
-  };
-}

package/src/fusion/clean-context.ts

@@ -1,91 +0,0 @@
-import { createHash } from 'node:crypto';
-import { canonicalJson } from '../attested-pi-run.js';
-import { normalizeFusionDeclaredSources, type DeclaredFusionSourceInput } from './source-policy.js';
-import {
-  FUSION_INPUT_SCHEMA_VERSION,
-  FusionError,
-  type FusionCanonicalRequestV3,
-  type FusionCleanTaskCanonicalInputV5,
-  type FusionDeclaredSourceV1,
-  type FusionSource,
-  type FusionWorkflowId,
-} from './types.js';
-
-export interface BuildFusionCleanTaskInputOptions {
-  cwd: string;
-  source: FusionSource;
-  request: string;
-  workflow: Exclude<FusionWorkflowId, 'reason'>;
-  declaredSources?: readonly DeclaredFusionSourceInput[] | undefined;
-}
-
-/**
- * Public v1 clean builder. It is deliberately pure: callers provide cwd and
- * normalized request text explicitly, and this module has no dependency on Pi
- * session, snapshot, parent-context, or visible-conversation APIs.
- */
-export const buildCleanFusionCanonicalInput = buildFusionCleanTaskCanonicalInput;
-
-export interface BuiltFusionCleanTaskCanonicalInput {
-  input: FusionCleanTaskCanonicalInputV5;
-  serialized: string;
-  declaredSources: readonly FusionDeclaredSourceV1[];
-  transcriptLeafId: null;
-}
-
-function sha256Text(value: string): string {
-  return createHash('sha256').update(Buffer.from(value, 'utf8')).digest('hex');
-}
-
-export function buildFusionCleanTaskCanonicalInput(
-  options: BuildFusionCleanTaskInputOptions,
-): BuiltFusionCleanTaskCanonicalInput {
-  if (options.request.trim().length === 0) {
-    throw new FusionError('fusion request must not be blank', {
-      code: 'context_capture_failed',
-      childCreated: false,
-    });
-  }
-  if (!['investigate', 'research', 'validate'].includes(options.workflow)) {
-    throw new FusionError('clean-task fusion input is available only to investigate, research, and validate workflows', {
-      code: 'context_capture_failed',
-      childCreated: false,
-    });
-  }
-  const declaredSources = normalizeFusionDeclaredSources(options.declaredSources ?? []);
-  if (options.workflow === 'research' && declaredSources.length === 0) {
-    throw new FusionError('fusion research requires at least one declared source URL and purpose', {
-      code: 'context_capture_failed',
-      childCreated: false,
-    });
-  }
-  if (options.workflow !== 'research' && declaredSources.length > 0) {
-    throw new FusionError('declared sources are accepted only by the research workflow', {
-      code: 'context_capture_failed',
-      childCreated: false,
-    });
-  }
-  const request: FusionCanonicalRequestV3 = {
-    source: options.source,
-    authority: 'explicit_text',
-    text: options.request,
-    sha256: sha256Text(options.request),
-  };
-  const input: FusionCleanTaskCanonicalInputV5 = {
-    schema_version: FUSION_INPUT_SCHEMA_VERSION,
-    workflow: options.workflow,
-    cwd: options.cwd,
-    request,
-    context: {
-      kind: 'clean_task',
-      policy_id: 'fusion-clean-task-v1',
-      declared_sources: declaredSources,
-    },
-  };
-  return {
-    input,
-    serialized: canonicalJson(input),
-    declaredSources,
-    transcriptLeafId: null,
-  };
-}