@equationalapplications/core-llm-wiki 5.5.0 → 6.0.0

package/dist/testing.js

@@ -387,7 +387,12 @@ function extractParsePosition(err) {
   return match ? Number(match[1]) : null;
 }
 function safeErrorToString(e) {
-  if (e instanceof Error) {
+  let isErrorLike = false;
+  try {
+    isErrorLike = e instanceof Error;
+  } catch {
+  }
+  if (isErrorLike) {
     const msg = readErrorField(e, "message");
     if (typeof msg === "string" && msg.length > 0) return msg;
     const name = readErrorField(e, "name");
@@ -412,16 +417,54 @@ function readErrorField(e, key) {
   }
 }
 function sanitizeRankerError(err, sanitizeRankerErrors) {
+  let isErrorLike = false;
+  try {
+    isErrorLike = err instanceof Error;
+  } catch {
+  }
   if (sanitizeRankerErrors === false) {
-    return err instanceof Error ? err : new Error(String(err));
+    return isErrorLike ? err : new Error(safeErrorToString(err));
+  }
+  let errLike = null;
+  if (isErrorLike) errLike = err;
+  let typeName;
+  try {
+    if (errLike) {
+      const rawName = errLike.constructor?.name;
+      typeName = typeof rawName === "string" ? rawName : "Error";
+    } else {
+      typeName = typeof err;
+    }
+  } catch {
+    typeName = isErrorLike ? "Error" : typeof err;
+  }
+  let innerCause;
+  if (errLike) {
+    let cause;
+    try {
+      cause = errLike.cause;
+    } catch {
+      cause = void 0;
+    }
+    if (cause !== void 0) {
+      let causeName;
+      try {
+        const rawCauseName = cause?.constructor?.name;
+        causeName = typeof rawCauseName === "string" ? rawCauseName : typeof cause;
+      } catch {
+        causeName = typeof cause;
+      }
+      innerCause = new Error(`Caused by: ${causeName}`);
+    }
   }
-  const typeName = err instanceof Error ? err.constructor?.name ?? "Error" : typeof err;
-  const innerCause = err instanceof Error && err.cause !== void 0 ? new Error(`Caused by: ${err.cause?.constructor?.name ?? typeof err.cause}`) : void 0;
   const sanitized = new Error(
     `VectorRanker ${typeName} (message scrubbed for security)`,
     innerCause ? { cause: innerCause } : void 0
   );
-  sanitized.name = typeName;
+  try {
+    sanitized.name = typeName;
+  } catch {
+  }
   return sanitized;
 }
 function safeSlice(value, start, end) {
@@ -1227,6 +1270,12 @@ Return ONLY a valid JSON object matching this schema:
 If no manifest type fits a fact, omit that fact from "classifications" entirely \u2014 do not guess.
 When echoing an existing fact's title verbatim into "target_title", preserve every JSON escape sequence (\\", \\n, \\\\, \\/) exactly as it appeared in the input body \u2014 do not strip backslashes, do not add unescaped quotes. Do not return markdown, just raw JSON.`;
 
+// src/utils/healConstants.ts
+var HEAL_MAX_ANCHORS = 50;
+var HEAL_ANCHORS_PER_CANDIDATE = 4;
+var HEAL_MAX_FACT_BODY_CHARS_L3 = 4e3;
+var HEAL_MAX_TASKS = 50;
+
 // src/services/PromptService.ts
 var PromptService = class {
   constructor(globalOverrides) {
@@ -1294,25 +1343,67 @@ Current Facts:
 ${JSON.stringify(currentFacts, null, 2)}`
     };
   }
-  buildHealPrompt(healCandidates, documentAnchors, allTasks, recentEvents, runtimeOverride) {
+  /**
+   * Heal-prompt level interpretation for the `attemptLevel` ladder.
+   *
+   * Caller contract: `documentAnchors` may be a slice sized for `batch.length`
+   * or a larger set (e.g. a cache hit from `_selectHealAnchors`). This function
+   * applies the prompt-side anchor cap `min(HEAL_MAX_ANCHORS=50, batch.length
+   * * HEAL_ANCHORS_PER_CANDIDATE=4)` so the rendered prompt is bounded
+   * regardless of caller input. `HEAL_MAX_ANCHORS` and
+   * `HEAL_ANCHORS_PER_CANDIDATE` live here too — keeping the formula
+   * co-located with its application avoids a "MaintenanceService policy"
+   * import cycle (`PromptService` is constructed before `MaintenanceService`
+   * exists) and makes the cap testable without a `MaintenanceService`
+   * instance. Task 3 exports the same two constants from `MaintenanceService`
+   * for caller-side overfetch sizing; the values must match.
+   *
+   * Level semantics:
+   * - L0: allTasks + recentEvents + full candidate bodies; anchors re-capped
+   * - L1: drop allTasks; recentEvents present; candidate bodies full
+   * - L2: drop allTasks and recentEvents; candidate bodies full
+   * - L3: drop allTasks and recentEvents; truncate each candidate body to
+   *   `bodyTruncationChars` and emit a `degraded` record per truncated fact
+   */
+  buildHealPrompt(healCandidates, documentAnchors, allTasks, recentEvents, runtimeOverride, attemptLevel, bodyTruncationChars = HEAL_MAX_FACT_BODY_CHARS_L3) {
+    const effectiveTasks = attemptLevel >= 1 ? [] : allTasks;
+    const effectiveEvents = attemptLevel >= 2 ? [] : recentEvents;
+    const maxAnchors = Math.max(1, Math.min(HEAL_MAX_ANCHORS, healCandidates.length * HEAL_ANCHORS_PER_CANDIDATE));
+    const effectiveAnchors = documentAnchors.slice(0, maxAnchors);
+    const { shapedCandidates, degraded } = applyBodyTruncation(
+      healCandidates,
+      attemptLevel,
+      bodyTruncationChars
+    );
     const template = runtimeOverride ?? this.globalOverrides?.healSystemPrompt ?? HEAL_SYSTEM_PROMPT;
     if (/\{\{\s*healCandidates\s*\}\}/.test(template) || /\{\{\s*documentAnchors\s*\}\}/.test(template) || /\{\{\s*allTasks\s*\}\}/.test(template) || /\{\{\s*recentEvents\s*\}\}/.test(template)) {
       return {
-        systemPrompt: this.hydrate(template, { healCandidates, documentAnchors, allTasks, recentEvents }),
-        userPrompt: "Please heal the memory graph."
+        prompts: {
+          systemPrompt: this.hydrate(template, {
+            healCandidates: shapedCandidates,
+            documentAnchors: effectiveAnchors,
+            allTasks: effectiveTasks,
+            recentEvents: effectiveEvents
+          }),
+          userPrompt: "Please heal the memory graph."
+        },
+        degraded
       };
     }
     return {
-      systemPrompt: template,
-      userPrompt: `Heal Candidates:
-${JSON.stringify(healCandidates, null, 2)}
+      prompts: {
+        systemPrompt: template,
+        userPrompt: `Heal Candidates:
+${JSON.stringify(shapedCandidates, null, 2)}
 Document Anchors (DO NOT MODIFY OR DELETE):
-${JSON.stringify(documentAnchors, null, 2)}
+${JSON.stringify(effectiveAnchors, null, 2)}
 All Tasks:
-${JSON.stringify(allTasks, null, 2)}
+${JSON.stringify(effectiveTasks, null, 2)}
 Recent Events:
-${JSON.stringify(recentEvents, null, 2)}
+${JSON.stringify(effectiveEvents, null, 2)}
 The following document anchors are provided for contradiction detection only. Do not include them in \`downgraded\`, \`deleted\`, or \`newFacts\`.`
+      },
+      degraded
     };
   }
   buildOntologyBackfillPrompt(facts, runtimeOverride, ontologyContext) {
@@ -1332,6 +1423,36 @@ ${JSON.stringify(facts, null, 2)}`
     };
   }
 };
+function applyBodyTruncation(candidates, attemptLevel, bodyTruncationChars) {
+  if (attemptLevel < 3) {
+    return { shapedCandidates: candidates, degraded: [] };
+  }
+  const shapedCandidates = [];
+  const degraded = [];
+  for (const c of candidates) {
+    if (typeof c !== "object" || c === null) {
+      shapedCandidates.push(c);
+      continue;
+    }
+    const fact = c;
+    const body = typeof fact.body === "string" ? fact.body : "";
+    if (body.length <= bodyTruncationChars) {
+      shapedCandidates.push(c);
+      continue;
+    }
+    if (typeof fact.id !== "string") {
+      shapedCandidates.push(c);
+      continue;
+    }
+    const originalBodyChars = body.length;
+    const prefix = safeSlice(body, 0, bodyTruncationChars);
+    const truncatedBodyChars = prefix.length;
+    const truncated = `${prefix}\u2026[truncated at ${truncatedBodyChars} chars, original was ${originalBodyChars}]`;
+    shapedCandidates.push({ ...fact, body: truncated });
+    degraded.push({ id: fact.id, originalBodyChars, truncatedBodyChars });
+  }
+  return { shapedCandidates, degraded };
+}
 
 // src/utils/chunkingDefaults.ts
 var DEFAULT_MAX_CHUNK_LENGTH = 12e3;
@@ -1842,11 +1963,24 @@ var TRUNCATION_PATTERNS = [
   /finish[_ ]?reason/i
 ];
 var EXCEEDS_LIMIT_PATTERN = /exceed[a-z]*[^.]{0,40}\b(model|context)?[ _-]?limit/i;
+function getErrorMessage(err) {
+  try {
+    return err instanceof Error ? err.message : String(err ?? "");
+  } catch {
+    return void 0;
+  }
+}
 function isTruncationError(err) {
-  const message = err instanceof Error ? err.message : String(err ?? "");
+  const message = getErrorMessage(err);
+  if (message === void 0) return false;
   if (EXCEEDS_LIMIT_PATTERN.test(message)) return false;
   return TRUNCATION_PATTERNS.some((pattern) => pattern.test(message));
 }
+function isConfigError(err) {
+  const message = getErrorMessage(err);
+  if (message === void 0) return false;
+  return EXCEEDS_LIMIT_PATTERN.test(message);
+}
 function initialBatchSize(maxOutputTokens) {
   if (!maxOutputTokens || !Number.isFinite(maxOutputTokens) || maxOutputTokens <= 0) {
     return DEFAULT_BATCH_SIZE;
@@ -1888,14 +2022,18 @@ async function runBatched(args) {
     const single = candidate.slice(0, 1);
     return { batch: single, prompts: await buildPrompt(single) };
   };
-  const onFailure = async (batch, err) => {
-    if (batch.length <= 1) {
-      if (batch.length === 1) {
-        skipped.push(batch[0]);
+  const onFailure = async (batch, err, attemptLevel, fromCall) => {
+    if (batch.length === 1) {
+      if (fromCall && isTruncationError(err) && attemptLevel < 3) {
+        await attempt(batch, void 0, attemptLevel + 1);
+      } else {
+        const reason = fromCall && !isTruncationError(err) && !isConfigError(err) ? "call_error" : "non_convergent";
+        skipped.push({ item: batch[0], reason });
         onSkip?.(batch[0], err);
       }
       return;
     }
+    if (fromCall && !isTruncationError(err)) throw err;
     const mid = Math.ceil(batch.length / 2);
     if (mid < batchSize) batchSize = mid;
     let i = 0;
@@ -1906,23 +2044,22 @@ async function runBatched(args) {
       i += trimmed.batch.length;
     }
   };
-  const attempt = async (batch, prebuilt) => {
+  const attempt = async (batch, prebuilt, attemptLevel = 0) => {
     if (batch.length === 0) return;
-    const prompts = prebuilt ?? await buildPrompt(batch);
+    const prompts = prebuilt && attemptLevel === 0 ? prebuilt : await buildPrompt(batch, attemptLevel);
     batches++;
     let responseText;
     try {
       responseText = await call(prompts);
     } catch (err) {
-      if (!isTruncationError(err)) throw err;
-      await onFailure(batch, err);
+      await onFailure(batch, err, attemptLevel, true);
       return;
     }
     let result;
     try {
       result = parse(responseText, batch);
     } catch (err) {
-      await onFailure(batch, err);
+      await onFailure(batch, err, attemptLevel, false);
       return;
     }
     results.push(result);
@@ -1931,7 +2068,7 @@ async function runBatched(args) {
   while (index < items.length) {
     const { batch, prompts } = await trim(items.slice(index, index + batchSize));
     index += batch.length;
-    await attempt(batch, prompts);
+    await attempt(batch, prompts, 0);
   }
   return { results, skipped, batches };
 }
@@ -1942,7 +2079,6 @@ var MIN_TOKENS_TO_QUALIFY = 3;
 var ONTOLOGY_BACKFILL_BATCH_SIZE = 25;
 var ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS = 4e4;
 var ONTOLOGY_BACKFILL_RECHECK_MS = 7 * 24 * 60 * 60 * 1e3;
-var HEAL_MAX_ANCHORS = 50;
 var HEAL_ANCHOR_SEARCH_OVERFETCH = 4;
 var HEAL_MAX_PROMPT_CHARS = 4e4;
 var HEAL_BATCH_SIZE = 25;
@@ -1950,7 +2086,12 @@ var HEAL_RECHECK_MS = 7 * 24 * 60 * 60 * 1e3;
 var SKIP_ERROR_LOG_CHARS = 4096;
 var formatSkipError = (err) => {
   let base;
-  if (err instanceof Error || typeof err !== "object" && typeof err !== "function") {
+  let isErrorLike = false;
+  try {
+    isErrorLike = err instanceof Error;
+  } catch {
+  }
+  if (isErrorLike || typeof err !== "object" && typeof err !== "function") {
     base = safeErrorToString(err);
   } else {
     try {
@@ -2368,6 +2509,10 @@ var MaintenanceService = class {
     if (!Number.isInteger(batchSize) || batchSize < 1) {
       throw new Error("Invalid batchSize: must be an integer >= 1");
     }
+    const bodyTruncationChars = options?.bodyTruncationChars ?? HEAL_MAX_FACT_BODY_CHARS_L3;
+    if (!Number.isInteger(bodyTruncationChars) || bodyTruncationChars < 1) {
+      throw new Error("Invalid bodyTruncationChars: must be an integer >= 1");
+    }
     const now = Date.now();
     const recheckCutoff = now - HEAL_RECHECK_MS;
     const orphanAfterDays = this.options.config?.orphanAfterDays !== void 0 ? this.options.config?.orphanAfterDays : 30;
@@ -2408,29 +2553,44 @@ var MaintenanceService = class {
         downgraded: staleDowngradedIds.length,
         deleted: orphanedIds.length,
         newFactsCreated: 0,
-        skipped: 0,
+        skipped: [],
+        degraded: [],
         remaining: counts2.eligible,
         deferred: counts2.deferred
       };
     }
-    const allTasks = await this.taskRepo.findAllPending([entityId]);
+    const allTasks = await this.taskRepo.findAllPending([entityId], HEAL_MAX_TASKS);
     const recentEvents = await this.eventRepo.getRecent(entityId, 20);
     const toPromptShape = (f) => {
       const { embedding: _embedding, embedding_blob: _blob, ...rest } = f;
       return { ...rest, tags: typeof rest.tags === "string" ? JSON.parse(rest.tags) : rest.tags };
     };
     const anchorCache = /* @__PURE__ */ new Map();
+    const degraded = [];
     const outcome = await runBatched({
       items: healCandidates,
-      buildPrompt: async (batch) => {
-        const documentAnchors = await this._selectHealAnchors(entityId, batch, anchorCache);
-        return this.promptService.buildHealPrompt(
+      buildPrompt: async (batch, attemptLevel = 0) => {
+        const documentAnchors = await this._selectHealAnchors(
+          entityId,
+          batch,
+          // Per-batch anchor cap: `batch.length * HEAL_ANCHORS_PER_CANDIDATE` (capped at
+          // HEAL_MAX_ANCHORS) right-sizes the anchor lookup so a 1-fact batch does
+          // not overfetch the same 200 keyword hits a 25-fact batch once did.
+          // buildHealPrompt applies the matching cap on its side — values must match.
+          Math.min(HEAL_MAX_ANCHORS, batch.length * HEAL_ANCHORS_PER_CANDIDATE),
+          anchorCache
+        );
+        const { prompts, degraded: batchDegraded } = await this.promptService.buildHealPrompt(
           batch.map(toPromptShape),
           documentAnchors,
           allTasks,
           recentEvents,
-          promptOverride
+          promptOverride,
+          attemptLevel,
+          bodyTruncationChars
         );
+        degraded.push(...batchDegraded);
+        return prompts;
       },
       call: (prompts) => this.options.llmProvider.generateText(prompts),
       parse: (responseText, batch) => {
@@ -2504,8 +2664,14 @@ var MaintenanceService = class {
         insertedFacts.push({ id, entity_id: entityId, title: fact.title, body: fact.body, tags: JSON.stringify(fact.tags) });
         healFactsForDedupe.push({ id, title: fact.title });
       }
+      const callErrorIds = new Set(
+        outcome.skipped.filter((s) => s.reason === "call_error").map((s) => s.item.id)
+      );
       await this.entryRepo.markHealChecked(
-        [...healCandidates.map((f) => f.id), ...insertedFacts.map((f) => f.id)],
+        [
+          ...healCandidates.map((f) => f.id).filter((id) => !callErrorIds.has(id)),
+          ...insertedFacts.map((f) => f.id)
+        ],
         entityId,
         now,
         tx
@@ -2523,6 +2689,13 @@ var MaintenanceService = class {
       await this.embeddingService.embedFact(fact);
     }
     this.searchService.evictCache(entityId);
+    const skippedIds = new Set(outcome.skipped.map(({ item }) => item.id));
+    const healedDegraded = degraded.filter((d) => !skippedIds.has(d.id));
+    for (const d of healedDegraded) {
+      console.warn(
+        `[WikiMemory] heal healed under degraded context ${entityId}/${d.id}: body truncated from ${d.originalBodyChars} to ${d.truncatedBodyChars} chars`
+      );
+    }
     let scanned = outcome.skipped.length;
     for (const batchResult of outcome.results) scanned += batchResult.batch.length;
     const allDowngraded = /* @__PURE__ */ new Set([...staleDowngradedIds, ...safeDowngraded]);
@@ -2533,7 +2706,8 @@ var MaintenanceService = class {
       downgraded: allDowngraded.size,
       deleted: allDeleted.size,
       newFactsCreated: insertedFacts.length,
-      skipped: outcome.skipped.length,
+      skipped: outcome.skipped.map(({ item, reason }) => ({ id: item.id, reason })),
+      degraded: healedDegraded,
       remaining: counts.eligible,
       deferred: counts.deferred
     };
@@ -2617,7 +2791,15 @@ var MaintenanceService = class {
       };
     }
     if (outcome.skipped.length > 0) {
-      await this.entryRepo.markOntologyChecked(outcome.skipped.map((f) => f.id), entityId, now, this.db);
+      const callErrorIds = new Set(
+        outcome.skipped.filter((s) => s.reason === "call_error").map((s) => s.item.id)
+      );
+      await this.entryRepo.markOntologyChecked(
+        outcome.skipped.filter(({ item }) => !callErrorIds.has(item.id)).map(({ item }) => item.id),
+        entityId,
+        now,
+        this.db
+      );
     }
     this.searchService.evictCache(entityId);
     const counts = await this.entryRepo.countUntypedByEntityId(entityId, recheckCutoff);
@@ -2733,7 +2915,7 @@ var MaintenanceService = class {
    * batches that reduce to the same query share one lookup. Caller-owned and
    * per-pass — see the call site in doRunHeal.
    */
-  async _selectHealAnchors(entityId, batch, cache) {
+  async _selectHealAnchors(entityId, batch, cap = HEAL_MAX_ANCHORS, cache) {
     const query = batch.map((f) => f.title).join(" ").trim();
     if (!query) return [];
     const cached = cache?.get(query);
@@ -2741,7 +2923,7 @@ var MaintenanceService = class {
     const hits = this.searchService.searchKeyword(
       query,
       [entityId],
-      HEAL_MAX_ANCHORS * HEAL_ANCHOR_SEARCH_OVERFETCH
+      cap * HEAL_ANCHOR_SEARCH_OVERFETCH
     );
     const hitIds = hits.map((h) => h.id);
     const anchors = [];
@@ -2752,7 +2934,7 @@ var MaintenanceService = class {
         const row = byId.get(id);
         if (!row) continue;
         anchors.push(row);
-        if (anchors.length >= HEAL_MAX_ANCHORS) break;
+        if (anchors.length >= cap) break;
       }
     }
     cache?.set(query, anchors);
@@ -3043,7 +3225,12 @@ var RetrievalService = class {
                   }
                 }
               } catch (rankerErr) {
-                const rankerError = rankerErr instanceof Error ? rankerErr : new Error(String(rankerErr));
+                let isErrorLike = false;
+                try {
+                  isErrorLike = rankerErr instanceof Error;
+                } catch {
+                }
+                const rankerError = isErrorLike ? rankerErr : new Error(safeErrorToString(rankerErr));
                 const policy = this.options.vectorRankerFallback ?? "js-cosine";
                 this.options.onVectorRankerFallback?.({
                   error: this._sanitizeRankerError(rankerError),
@@ -3155,12 +3342,21 @@ var RetrievalService = class {
             }
           }
         } catch (err) {
-          const error = err instanceof Error ? err : new Error(String(err));
+          let isErrorLike = false;
+          try {
+            isErrorLike = err instanceof Error;
+          } catch {
+          }
+          const error = isErrorLike ? err : new Error(safeErrorToString(err));
           if (rankerShouldRethrow) {
             throw error;
           }
           if (pendingRankerFallbackError) {
-            error.cause = pendingRankerFallbackError;
+            try {
+              error.cause = pendingRankerFallbackError;
+            } catch {
+              this.options.onRetrievalFallback?.(pendingRankerFallbackError);
+            }
             pendingRankerFallbackError = void 0;
           }
           this.options.onRetrievalFallback?.(error);