@jaggerxtrm/specialists 3.6.11 → 3.6.12

package/config/benchmarks/executor-benchmark-matrix.json

@@ -0,0 +1,25 @@
+{
+  "id": "unitAI-gc2a",
+  "replicate": 1,
+  "reviewerModel": "openai-codex/gpt-5.4-mini",
+  "models": [
+    "openai-codex/gpt-5.3-codex",
+    "openai-codex/gpt-5.4-mini",
+    "dashscope/qwen3.5-plus",
+    "zai/glm-5"
+  ],
+  "tasks": [
+    {
+      "id": "bug-fix",
+      "seedBead": "unitAI-y4ia"
+    },
+    {
+      "id": "refactor",
+      "seedBead": "unitAI-22tq"
+    },
+    {
+      "id": "implementation",
+      "seedBead": "unitAI-8zui"
+    }
+  ]
+}

package/config/skills/using-specialists/SKILL.md

@@ -29,6 +29,27 @@ Specialists are autonomous AI agents that run independently — fresh context, d
 
 ---
 
+## Response Style Policy
+
+- Be direct, concise, and professional.
+- Answer the user's actual question first, in the first sentence when possible.
+- Do not append conversational filler like:
+  - "If you want, I can..."
+  - "I can also..."
+  - "Let me know if you want..."
+  unless the user explicitly asked for options.
+- Do not restate context the user already provided unless needed to resolve ambiguity.
+- Prefer short conclusions over long explanatory structures.
+- Use bullets only when they improve clarity; otherwise respond in plain prose.
+- Do not hedge unnecessarily. If the answer is clear, state it plainly.
+- Do not give a recommendation section unless the user asked for recommendations or a decision.
+- Do not propose next steps automatically after every answer.
+- When reporting status, give:
+  1. current state
+  2. blocker or result
+  3. only the next action if action is already implied or necessary
+- Default to terse operational language, not coaching language.
+
 ## Hard Rules
 
 1. **Zero implementation by orchestrator.** When this skill is active for substantial work, you do not implement the solution yourself.

package/config/specialists/reviewer.specialist.json

@@ -27,8 +27,8 @@
       "max_retries": 0
     },
     "prompt": {
-      "system": "You = post-execution requirement compliance reviewer.\n\nAudit completed specialist run. Determine if final output satisfies original requirements.\n\n## Source-of-truth priority\n\n1. Originating bead requirements (highest priority)\n2. Explicit requirement source in task prompt\n3. Fallback inferred requirements from reviewed output context\n\nAlways prefer bead requirements when reviewed run used `--bead`.\n\n## Job linkage and evidence collection (required)\n\nGiven `reviewed_job_id`, resolve lineage and evidence in exact order:\n\n1) Run `sp ps <reviewed_job_id>`\n   - Capture metadata: `bead_id`, `status`, `worktree_path`, `specialist`, `model`\n\n2) Run `sp result <reviewed_job_id>`\n   - Primary reviewed output evidence source\n\n3) If `worktree_path` available, inspect actual code changes in that worktree\n   - Run `git diff` (or `git diff -- <paths>`) to verify file-level changes\n\n4) Requirement source binding result:\n   - Bead resolved: run `bd show <bead_id> --json` to load requirements\n   - Bead unresolved: inspect explicit prompt fields (`originating_bead_id`, `requirement_source`, `lineage`, `parent_job_id`)\n   - `parent_job_id` exists: recurse using `sp ps`/`sp result` for parent jobs\n   - Still unresolved: mark traceability missing, downgrade outcome\n\n5) CLI-unavailable fallback ONLY:\n   - Use file traversal under `.specialists/jobs/<reviewed_job_id>/status.json` and `events.jsonl`\n   - Fallback mode; skip when `sp ps`/`sp result` work\n\nIMPORTANT: Always use `bd show <bead_id>` or `bd show <bead_id> --json` to read bead data. NEVER search for or read `.beads/issues.jsonl` directly \u2014 beads uses database backend, not flat files.\n\n## Requirement extraction\n\nFrom `bd show --json` output, extract requirements from:\n- `title`\n- `description`\n- `notes`\n- `design` (if present)\n\nNormalize into atomic checklist items before scoring.\n\n## Evidence rules\n\n- Only concrete evidence from `sp result <reviewed_job_id>`, `git diff` in reviewed worktree, or explicitly provided output.\n- Quote short excerpts for each met/unmet requirement.\n- Never assume completion without evidence.\n\n## Decision rubric\n\n- PASS: all critical requirements met; no major gaps.\n- PARTIAL: some requirements met, at least one meaningful gap remains.\n- FAIL: core requirements unmet, missing evidence, or requirement linkage unresolved.\n\n## Compliance score\n\n0-100 score:\n- Coverage component (0-70): proportion of requirements met.\n- Evidence quality (0-20): directness and specificity of proof.\n- Traceability integrity (0-10): confidence in job->requirement linkage.\n\n## Required output format\n\n## Compliance Verdict\n- Verdict: PASS | PARTIAL | FAIL\n- Score: <0-100>\n- Reviewed Job: <job-id>\n- Originating Bead: <bead-id or unresolved>\n- Requirement Source Used: bead | explicit_prompt | inferred\n\n## Requirement Coverage Matrix\nFor each requirement:\n- Requirement\n- Status: met | partial | unmet\n- Evidence\n- Gap\n\n## Coverage Gaps\n- Bullet list of missing or weakly evidenced requirements\n\n## Lineage / Traceability Notes\n- What files/fields used to resolve job -> requirement source\n- Any ambiguity or unresolved linkage\n\n## Recommended Next Actions\n- Concrete follow-ups to reach PASS",
-      "task_template": "Audit the completed specialist run for requirement compliance.\n\n$prompt\n\nWorking directory: $cwd\n\nResolved lineage input:\n- reviewed_job_id: $reviewed_job_id\n\nPreferred input:\n- reviewed_job_id: <job-id>\nOptional input:\n- reviewed_output: <inline output>\n- requirement_source: <explicit requirements>\n- originating_bead_id: <bead-id>\n- parent_job_id or lineage chain if available\n\nResolve lineage first, then evaluate compliance using the required output format.\n\nWhen reviewing code changes, use `gitnexus_impact` to verify the specialist checked blast radius before edits. Flag missing impact analysis as a compliance gap.\n"
+      "system": "You = post-execution requirement compliance reviewer.\n\nAudit completed specialist run. Determine if final output satisfies original requirements.\n\n## Source-of-truth priority\n\n1. Originating bead requirements (highest priority)\n2. Explicit requirement source in task prompt\n3. Fallback inferred requirements from reviewed output context\n\nAlways prefer bead requirements when reviewed run used `--bead`.\n\n## AUTHORITATIVE REVIEW CONTEXT\n\nWhen these fields are injected, treat them as primary truth for review setup and traceability:\n- `reviewed_job_id`\n- `reviewed_output`\n- `requirement_source`\n- `originating_bead_id`\n- `parent_job_id`\n- lineage chain / worktree chain fields\n- auto-injected git diff context\n\nEvidence precedence, highest to lowest:\n1. Injected lineage / reviewed result / diff context\n2. Repo state inside reviewed worktree\n3. Local artifact lookup (`.specialists/jobs`, job history files, filesystem traces)\n4. Heuristics or guesses\n\nDecision rules:\n- If injected lineage/result/diff exists, trust it over missing local artifacts.\n- Missing local artifacts MUST NOT trigger FAIL by itself.\n- FAIL only for direct contradiction, internal inconsistency, or missing required injected fields.\n- If injected context exists but local lookup fails, continue review and emit limitation note.\n- Required injected fields for authoritative traceability:\n  - `reviewed_job_id` (required)\n  - at least one evidence anchor: `reviewed_output` or auto-injected git diff context\n  - at least one requirement anchor: `requirement_source` or `originating_bead_id` or `parent_job_id`/lineage chain\n- Compute `missing_required_injected_fields` from that required set before assigning FAIL for missing inputs.\n- If required injected fields are absent, FAIL is allowed.\n- If injected context contradicts reviewed output or diff, FAIL is allowed.\n- If local artifact lookup fails but injected context is consistent, keep reviewing.\n\nStructured evidence fields to report:\n- authoritative_lineage_present: yes|no\n- authoritative_result_present: yes|no\n- authoritative_diff_present: yes|no\n- local_lookup_status: success|partial|missing|not_attempted\n- contradiction_detected: yes|no\n- missing_required_injected_fields: list\n- limitation_note: short explanation when local lookup fails but injected context remains usable\n\n## Job linkage and evidence collection (required)\n\nGiven `reviewed_job_id`, resolve lineage and evidence in exact order:\n\n1) Prefer injected lineage/result/diff context if present\n   - Use injected fields before any filesystem or job-history lookup\n\n2) Run `sp ps <reviewed_job_id>` only as supporting lookup\n   - Capture metadata: `bead_id`, `status`, `worktree_path`, `specialist`, `model`\n   - If unavailable or stale, do not fail solely for that\n\n3) Run `sp result <reviewed_job_id>` as primary reviewed output evidence source when injected result absent\n\n4) If `worktree_path` available, inspect actual code changes in that worktree\n   - Run `git diff` (or `git diff -- <paths>`) to verify file-level changes when needed\n\n5) Requirement source binding result:\n   - Bead resolved: run `bd show <bead_id> --json` to load requirements\n   - Bead unresolved: inspect explicit prompt fields (`originating_bead_id`, `requirement_source`, `lineage`, `parent_job_id`)\n   - `parent_job_id` exists: recurse using `sp ps`/`sp result` for parent jobs\n   - Still unresolved: mark traceability missing, but do not FAIL if injected context already supplies sufficient evidence\n\n6) CLI-unavailable fallback ONLY:\n   - Use file traversal under `.specialists/jobs/<reviewed_job_id>/status.json` and `events.jsonl`\n   - Fallback mode; skip when injected context or `sp ps`/`sp result` work\n\nIMPORTANT: Always use `bd show <bead_id>` or `bd show <bead_id> --json` to read bead data. NEVER search for or read `.beads/issues.jsonl` directly \u2014 beads uses database backend, not flat files.\n\n## Requirement extraction\n\nFrom `bd show --json` output, extract requirements from:\n- `title`\n- `description`\n- `notes`\n- `design` (if present)\n\nNormalize into atomic checklist items before scoring.\n\n## Evidence rules\n\n- Concrete evidence order: injected reviewed result/diff/lineage, then `sp result <reviewed_job_id>`, then `git diff` in reviewed worktree, then explicitly provided output.\n- Local artifact lookup failure alone is not a failure condition.\n- Quote short excerpts for each met/unmet requirement.\n- Never assume completion without evidence.\n\n## Decision rubric\n\n- PASS: all critical requirements met; no major gaps.\n- PARTIAL: some requirements met, at least one meaningful gap remains.\n- FAIL: core requirements unmet, injected evidence contradicts itself or reviewed output, or required injected fields missing.\n- Local lookup failure with valid injected context => PARTIAL or PASS, never FAIL by itself.\n\n## Compliance score\n\n0-100 score:\n- Coverage component (0-70): proportion of requirements met.\n- Evidence quality (0-20): directness and specificity of proof.\n- Traceability integrity (0-10): confidence in job->requirement linkage.\n\n## Required output format\n\n## Compliance Verdict\n- Verdict: PASS | PARTIAL | FAIL\n- Score: <0-100>\n- Reviewed Job: <job-id>\n- Originating Bead: <bead-id or unresolved>\n- Requirement Source Used: bead | explicit_prompt | inferred\n\n## Evidence Summary\n- authoritative_lineage_present: yes|no\n- authoritative_result_present: yes|no\n- authoritative_diff_present: yes|no\n- local_lookup_status: success|partial|missing|not_attempted\n- contradiction_detected: yes|no\n- missing_required_injected_fields: []|[list]\n- limitation_note: <short note or none>\n\n## Requirement Coverage Matrix\nFor each requirement:\n- Requirement\n- Status: met | partial | unmet\n- Evidence\n- Gap\n\n## Coverage Gaps\n- Bullet list of missing or weakly evidenced requirements\n\n## Lineage / Traceability Notes\n- What files/fields used to resolve job -> requirement source\n- Any ambiguity or unresolved linkage\n\n## Recommended Next Actions\n- Concrete follow-ups to reach PASS",
+      "task_template": "Audit the completed specialist run for requirement compliance.\n\n$prompt\n\nWorking directory: $cwd\n\nResolved lineage input:\n- reviewed_job_id: $reviewed_job_id\n\nPreferred input:\n- reviewed_job_id: <job-id>\nOptional input:\n- reviewed_output: <inline output>\n- requirement_source: <explicit requirements>\n- originating_bead_id: <bead-id>\n- parent_job_id or lineage chain if available\n\nResolve lineage first, then evaluate compliance using the required output format.\n\nWhen reviewing code changes, use `gitnexus_impact` to verify the specialist checked blast radius before edits. Flag missing impact analysis as a compliance gap."
     },
     "skills": {
       "paths": [

package/dist/index.js

@@ -17907,6 +17907,49 @@ function findTokenUsage(payload) {
   }
   return normalizeTokenUsage(record3);
 }
+function findApiErrorMessage(payload) {
+  if (!payload || typeof payload !== "object")
+    return;
+  const record3 = payload;
+  const direct = [record3.errorMessage, record3.error_message, record3.error, record3.message].find((value) => typeof value === "string" && value.trim().length > 0);
+  if (typeof direct === "string")
+    return direct.trim();
+  const nestedError = record3.error;
+  if (nestedError && typeof nestedError === "object") {
+    const nested = nestedError;
+    const nestedMessage = [nested.message, nested.errorMessage, nested.error_message].find((value) => typeof value === "string" && value.trim().length > 0);
+    if (typeof nestedMessage === "string")
+      return nestedMessage.trim();
+  }
+  const message = record3.assistantMessageEvent;
+  if (message && typeof message === "object") {
+    const nested = message;
+    const nestedMessage = [nested.errorMessage, nested.error_message, nested.error, nested.message].find((value) => typeof value === "string" && value.trim().length > 0);
+    if (typeof nestedMessage === "string")
+      return nestedMessage.trim();
+  }
+  return;
+}
+function extractApiErrorFromStderr(stderr) {
+  const compact = stderr.trim();
+  if (!compact)
+    return;
+  const patterns = [
+    /You have hit your ChatGPT usage limit[^\n]*/i,
+    /rate limit[^\n]*/i,
+    /quota[^\n]*/i,
+    /auth(?:entication)?[^\n]*/i,
+    /unauthori[sz]ed[^\n]*/i,
+    /forbidden[^\n]*/i,
+    /overloaded[^\n]*/i
+  ];
+  for (const pattern of patterns) {
+    const match = compact.match(pattern);
+    if (match)
+      return match[0].trim();
+  }
+  return;
+}
 function normalizeToolResultPart(contentPart) {
   if (!contentPart || typeof contentPart !== "object")
     return;
@@ -18049,6 +18092,7 @@ class PiAgentSession {
   _pendingRequests = new Map;
   _nextRequestId = 1;
   _stderrBuffer = "";
+  _apiError;
   _stallTimer;
   _stallError;
   _testWindowToolCallIds = new Set;
@@ -18147,7 +18191,9 @@ class PiAgentSession {
     donePromise.catch(() => {});
     this._donePromise = donePromise;
     this.proc.stderr?.on("data", (chunk) => {
-      this._stderrBuffer += chunk.toString();
+      const text = chunk.toString();
+      this._stderrBuffer += text;
+      this._apiError ??= extractApiErrorFromStderr(this._stderrBuffer) ?? extractApiErrorFromStderr(text);
     });
     this.proc.stdout?.on("data", (chunk) => {
       this._lineBuffer += chunk.toString();
@@ -18308,6 +18354,12 @@ class PiAgentSession {
       }
       this._updateTokenUsage(findTokenUsage(event), "agent_end");
       this._updateFinishReason(findFinishReason(event), "agent_end");
+      const apiError = findApiErrorMessage(event) ?? this._apiError ?? extractApiErrorFromStderr(this._stderrBuffer);
+      if (apiError) {
+        this._apiError = apiError;
+        this._metrics.api_error = apiError;
+        this.options.onMetric?.({ type: "api_error", source: "stderr", errorMessage: apiError });
+      }
       this._agentEndReceived = true;
       this._clearStallTimer();
       this.options.onEvent?.("agent_end");
@@ -18434,6 +18486,16 @@ class PiAgentSession {
           this.options.onEvent?.("message_done");
           break;
         }
+        case "error": {
+          const apiError = findApiErrorMessage(ae) ?? findApiErrorMessage(event);
+          if (apiError) {
+            this._apiError = apiError;
+            this._metrics.api_error = apiError;
+            this.options.onMetric?.({ type: "api_error", source: "rpc", errorMessage: apiError });
+          }
+          this.options.onEvent?.("message_error");
+          break;
+        }
       }
     }
   }
@@ -20083,6 +20145,19 @@ class SqliteClient {
       return this.db.query("SELECT chain_id, epic_id, chain_root_bead_id, chain_root_job_id, updated_at_ms FROM epic_chain_membership WHERE epic_id = ? ORDER BY updated_at_ms DESC").all(epicId);
     }, "listEpicChains");
   }
+  deleteEpicChainMembership(epicId, chainIds) {
+    if (chainIds.length === 0)
+      return [];
+    return withRetry(() => {
+      const existing = new Set(this.db.query("SELECT chain_id FROM epic_chain_membership WHERE epic_id = ?").all(epicId).map((row) => row.chain_id));
+      const removable = chainIds.filter((chainId) => existing.has(chainId));
+      if (removable.length === 0)
+        return [];
+      const placeholders = removable.map(() => "?").join(", ");
+      this.db.query(`DELETE FROM epic_chain_membership WHERE epic_id = ? AND chain_id IN (${placeholders})`).run(epicId, ...removable);
+      return removable;
+    }, "deleteEpicChainMembership");
+  }
   listEpicChainsWithLatestJob(epicId) {
     return withRetry(() => {
       const rows = this.db.query(`
@@ -20995,6 +21070,9 @@ function resolveOutputContractSchema(responseFormat, outputType, outputSchema) {
   }
   return mergedSchema;
 }
+function shellQuote(value) {
+  return `'${value.replace(/'/g, `'''`)}'`;
+}
 function buildOutputContractInstruction(responseFormat, outputType, outputSchema) {
   if (responseFormat === "text")
     return "";
@@ -21019,6 +21097,58 @@ function buildOutputContractInstruction(responseFormat, outputType, outputSchema
 ${lines.join(`
 `)}`;
 }
+function buildReviewerDiffContext(cwd, maxFiles = 20) {
+  const stat2 = execSync2("git diff --stat", {
+    cwd,
+    encoding: "utf8",
+    timeout: 1e4,
+    stdio: ["ignore", "pipe", "pipe"]
+  }).trim();
+  const files = execSync2("git diff --name-only", {
+    cwd,
+    encoding: "utf8",
+    timeout: 1e4,
+    stdio: ["ignore", "pipe", "pipe"]
+  }).split(`
+`).map((line) => line.trim()).filter(Boolean).slice(0, maxFiles);
+  if (files.length === 0) {
+    throw new Error("Reviewer startup blocked: git diff is empty. No patch context to review.");
+  }
+  const hunks = files.map((file) => {
+    const diff = execSync2(`git diff -- ${shellQuote(file)}`, {
+      cwd,
+      encoding: "utf8",
+      timeout: 1e4,
+      stdio: ["ignore", "pipe", "pipe"]
+    }).trim();
+    return diff ? `### ${file}
+${diff}` : `### ${file}
+(no hunks)`;
+  }).join(`
+
+`);
+  return { stat: stat2, files, hunks };
+}
+function buildReviewerDiffInstruction(context) {
+  return `
+
+---
+## Reviewer Diff Context
+Review only patch below. Ignore unrelated files, repo-wide exploration, and filesystem hunting.
+If patch context is empty, stop and fail fast.
+
+Diff stat:
+${context.stat || "(no stat)"}
+
+Changed files:
+${context.files.map((file) => `- ${file}`).join(`
+`)}
+
+Diff hunks:
+${context.hunks}
+---
+`;
+}
 function tryParseJson(input) {
   try {
     return { value: JSON.parse(input) };
@@ -21340,6 +21470,10 @@ ${summaries.join(`
         }
       })
     });
+    if (metadata.name === "reviewer" && options.reusedFromJobId) {
+      const reviewerDiffContext = buildReviewerDiffContext(runCwd);
+      agentsMd += buildReviewerDiffInstruction(reviewerDiffContext);
+    }
     const responseFormat = execution.response_format ?? "text";
     const outputType = execution.output_type ?? "custom";
     const specialistOutputSchema = prompt.output_schema;
@@ -21939,6 +22073,13 @@ function mapCallbackEventToTimelineEvent(callbackEvent, context) {
         ...context.extensionError?.extension ? { extension: context.extensionError.extension } : {},
         ...context.extensionError?.errorMessage ? { error_message: context.extensionError.errorMessage } : {}
       };
+    case "api_error":
+      return {
+        t,
+        type: TIMELINE_EVENT_TYPES.ERROR,
+        source: context.apiError?.source ?? "rpc",
+        error_message: context.apiError?.errorMessage ?? "Unknown API error"
+      };
     case "memory_injection":
       return {
         t,
@@ -22124,6 +22265,7 @@ var init_timeline_events = __esm(() => {
     RETRY: "retry",
     MODEL_CHANGE: "model_change",
     EXTENSION_ERROR: "extension_error",
+    ERROR: "error",
     AUTO_COMMIT_SUCCESS: "auto_commit_success",
     AUTO_COMMIT_SKIPPED: "auto_commit_skipped",
     AUTO_COMMIT_FAILED: "auto_commit_failed",
@@ -23725,6 +23867,16 @@ ${appendError}
           appendTimelineEvent(createFinishReasonEvent(metricEvent.finish_reason, metricEvent.source));
           return;
         }
+        if (metricEvent.type === "api_error") {
+          mergeRunMetrics({ api_error: metricEvent.errorMessage });
+          appendTimelineEvent({
+            t: Date.now(),
+            type: TIMELINE_EVENT_TYPES.ERROR,
+            source: metricEvent.source,
+            error_message: metricEvent.errorMessage
+          });
+          return;
+        }
         if (metricEvent.type === "turn_summary") {
           mergeRunMetrics({
             turns: metricEvent.turn_index,
@@ -27579,6 +27731,9 @@ function formatEventLine(event, options) {
     detailParts.push(`backend=${event.backend}`);
   } else if (event.type === "tool") {
     detail = formatToolDetail(event);
+  } else if (event.type === "error") {
+    detailParts.push(`source=${event.source}`);
+    detailParts.push(`error=${event.error_message}`);
   } else if (event.type === "run_complete") {
     detailParts.push(`status=${event.status}`);
     detailParts.push(`elapsed=${formatElapsed(event.elapsed_s)}`);
@@ -27668,6 +27823,8 @@ function formatEventInline(event) {
     }
     case "stale_warning":
       return yellow10(`[warning] ${event.reason}: ${Math.round(event.silence_ms / 1000)}s silent`);
+    case "error":
+      return red2(`[error] ${event.source}: ${event.error_message}`);
     default:
       return null;
   }
@@ -27701,7 +27858,7 @@ var init_format_helpers = __esm(() => {
     turn_summary: "TURN+",
     compaction: "CMPCT",
     retry: "RETRY",
-    error: "ERR"
+    error: "ERROR"
   };
 });
 
@@ -28046,7 +28203,7 @@ function formatFooterModel(backend, model) {
     return model;
   return model.startsWith(`${backend}/`) ? model : `${backend}/${model}`;
 }
-function shellQuote(value) {
+function shellQuote2(value) {
   return `'${value.replace(/'/g, `'\\''`)}'`;
 }
 function extractReviewedJobIdOverride(prompt) {
@@ -28098,7 +28255,7 @@ async function run13() {
     })();
     const cwd = process.cwd();
     const innerArgs = process.argv.slice(2).filter((a) => a !== "--background");
-    const cmd = `${process.execPath} ${process.argv[1]} ${innerArgs.map(shellQuote).join(" ")}`;
+    const cmd = `${process.execPath} ${process.argv[1]} ${innerArgs.map(shellQuote2).join(" ")}`;
     let childPid;
     if (isTmuxAvailable()) {
       const suffix = randomBytes(3).toString("hex");
@@ -31505,12 +31662,16 @@ function syncEpicState(sqlite, epicId, apply) {
     stale_redirect_markers: epicRun && hasRedirectMarkers(epicRun.status_json) ? [epicId] : []
   };
   let deadJobsMarkedError = [];
+  let staleChainRefsPruned = [];
   let readinessResynced = false;
   let redirectMarkersCleared = false;
   if (apply) {
     if (drift.dead_jobs_blocking_readiness.length > 0) {
       deadJobsMarkedError = markDeadJobsAsError(sqlite, jobs);
     }
+    if (drift.stale_chain_refs.length > 0) {
+      staleChainRefsPruned = sqlite.deleteEpicChainMembership(epicId, drift.stale_chain_refs);
+    }
     const readinessNext = loadEpicReadinessSummary(sqlite, epicId);
     const synced = syncEpicStateFromReadiness(sqlite, readinessNext);
     readinessResynced = synced.status !== readinessNext.persisted_state;
@@ -31533,6 +31694,7 @@ function syncEpicState(sqlite, epicId, apply) {
     drift,
     repairs: {
       dead_jobs_marked_error: deadJobsMarkedError,
+      stale_chain_refs_pruned: staleChainRefsPruned,
       readiness_resynced: readinessResynced,
       redirect_markers_cleared: redirectMarkersCleared
     },
@@ -31732,7 +31894,7 @@ function parseSyncOptions(argv) {
   return { epicId, apply, json };
 }
 function parseAbandonOptions(argv) {
-  const epicId = parseEpicId(argv);
+  let epicId = "";
   let reason = "";
   let force = false;
   let json = false;
@@ -31755,9 +31917,16 @@ function parseAbandonOptions(argv) {
       index += 1;
       continue;
     }
-    if (argument.startsWith("-") && argument !== "--force" && argument !== "--json") {
+    if (argument.startsWith("-")) {
       throw new Error(`Unknown option: ${argument}`);
     }
+    if (epicId.length > 0) {
+      throw new Error("Only one epic ID is supported");
+    }
+    epicId = argument;
+  }
+  if (!epicId) {
+    throw new Error("Missing epic ID");
   }
   if (reason.length === 0) {
     throw new Error("Missing required --reason <text>");
@@ -32161,6 +32330,7 @@ async function handleEpicSyncCommand(argv) {
     console.log(`  stale_redirect_markers: ${result.drift.stale_redirect_markers.length}`);
     if (result.apply) {
       console.log(`  repaired_dead_jobs: ${result.repairs.dead_jobs_marked_error.length}`);
+      console.log(`  stale_chain_refs_pruned: ${result.repairs.stale_chain_refs_pruned.length}`);
       console.log(`  readiness_resynced: ${result.repairs.readiness_resynced}`);
       console.log(`  redirect_markers_cleared: ${result.repairs.redirect_markers_cleared}`);
     }
@@ -33709,6 +33879,10 @@ function deriveStartupSnapshot(status, events) {
     merged.branch = status.branch;
   return Object.keys(merged).length > 0 ? merged : null;
 }
+function deriveApiError(events) {
+  const errorEvent = [...events].reverse().find((event) => event.type === "error");
+  return errorEvent?.error_message ?? null;
+}
 function formatStartupSnapshot(snapshot) {
   if (!snapshot)
     return null;
@@ -33829,20 +34003,25 @@ async function run16() {
           process.exit(1);
         }
         if (status2.status === "done") {
-          const startupContext2 = deriveStartupSnapshot(status2, readTimelineEventsForResult(sqliteClient, jobsDir, jobId));
+          const events2 = readTimelineEventsForResult(sqliteClient, jobsDir, jobId);
+          const startupContext2 = deriveStartupSnapshot(status2, events2);
+          const apiError2 = status2.error ?? deriveApiError(events2);
           const output3 = readResultOutput();
           if (!output3) {
+            const message = apiError2 ? `Job ${jobId} failed: ${apiError2}` : `Result not found for job ${jobId}`;
             if (args.json) {
-              emitJson(status2, null, `Result not found for job ${jobId}`);
+              emitJson(status2, null, message, startupContext2);
             } else {
-              console.error(`Result not found for job ${jobId}`);
+              process.stderr.write(`${red3(message)}
+`);
             }
             process.exit(1);
           }
+          const enrichedStatus2 = apiError2 && !status2.error ? { ...status2, error: apiError2 } : status2;
           if (args.json) {
-            emitJson(status2, output3, null, startupContext2);
+            emitJson(enrichedStatus2, output3, null, startupContext2);
           } else {
-            emitHumanResult(output3, status2, startupContext2);
+            emitHumanResult(output3, enrichedStatus2, startupContext2);
           }
           return;
         }
@@ -33929,31 +34108,37 @@ async function run16() {
       return;
     }
     if (status.status === "error") {
-      const startupContext2 = deriveStartupSnapshot(status, readTimelineEventsForResult(sqliteClient, jobsDir, jobId));
-      const message = `Job ${jobId} failed: ${status.error ?? "unknown error"}`;
+      const events2 = readTimelineEventsForResult(sqliteClient, jobsDir, jobId);
+      const startupContext2 = deriveStartupSnapshot(status, events2);
+      const message = `Job ${jobId} failed: ${status.error ?? deriveApiError(events2) ?? "unknown error"}`;
       if (args.json) {
         emitJson(status, null, message, startupContext2);
       } else {
-        process.stderr.write(`${red3(`Job ${jobId} failed:`)} ${status.error ?? "unknown error"}
+        process.stderr.write(`${red3(`Job ${jobId} failed:`)} ${status.error ?? deriveApiError(events2) ?? "unknown error"}
 `);
       }
       process.exit(1);
     }
+    const events = readTimelineEventsForResult(sqliteClient, jobsDir, jobId);
+    const apiError = status.error ?? deriveApiError(events);
     const output2 = readResultOutput();
     if (!output2) {
+      const message = apiError ? `Job ${jobId} failed: ${apiError}` : `Result not found for job ${jobId}`;
       if (args.json) {
-        emitJson(status, null, `Result not found for job ${jobId}`);
+        emitJson(status, null, message);
       } else {
-        console.error(`Result not found for job ${jobId}`);
+        process.stderr.write(`${red3(message)}
+`);
       }
       process.exit(1);
     }
-    const startupContext = deriveStartupSnapshot(status, readTimelineEventsForResult(sqliteClient, jobsDir, jobId));
+    const startupContext = deriveStartupSnapshot(status, events);
+    const enrichedStatus = apiError && !status.error ? { ...status, error: apiError } : status;
     if (args.json) {
-      emitJson(status, output2, null, startupContext);
+      emitJson(enrichedStatus, output2, null, startupContext);
       return;
     }
-    emitHumanResult(output2, status, startupContext);
+    emitHumanResult(output2, enrichedStatus, startupContext);
   } catch (error2) {
     const message = error2 instanceof Error ? error2.message : String(error2);
     if (args.json) {
@@ -34150,6 +34335,8 @@ function getHumanEventKey(event) {
       return `run_start:${event.specialist}:${event.bead_id ?? ""}`;
     case "run_complete":
       return `run_complete:${event.status}:${event.error ?? ""}`;
+    case "error":
+      return `error:${event.source}:${event.error_message}`;
     case "token_usage":
       return `token_usage:${event.token_usage.total_tokens ?? ""}:${event.source}`;
     case "finish_reason":
@@ -40305,7 +40492,7 @@ var AssertObjectSchema = custom2((v) => v !== null && (typeof v === "object" ||
 var ProgressTokenSchema = union([string2(), number2().int()]);
 var CursorSchema = string2();
 var TaskCreationParamsSchema = looseObject({
-  ttl: union([number2(), _null3()]).optional(),
+  ttl: number2().optional(),
   pollInterval: number2().optional()
 });
 var TaskMetadataSchema = object2({
@@ -40459,7 +40646,8 @@ var ClientCapabilitiesSchema = object2({
   roots: object2({
     listChanged: boolean2().optional()
   }).optional(),
-  tasks: ClientTasksCapabilitySchema.optional()
+  tasks: ClientTasksCapabilitySchema.optional(),
+  extensions: record(string2(), AssertObjectSchema).optional()
 });
 var InitializeRequestParamsSchema = BaseRequestParamsSchema.extend({
   protocolVersion: string2(),
@@ -40484,7 +40672,8 @@ var ServerCapabilitiesSchema = object2({
   tools: object2({
     listChanged: boolean2().optional()
   }).optional(),
-  tasks: ServerTasksCapabilitySchema.optional()
+  tasks: ServerTasksCapabilitySchema.optional(),
+  extensions: record(string2(), AssertObjectSchema).optional()
 });
 var InitializeResultSchema = ResultSchema.extend({
   protocolVersion: string2(),
@@ -40599,6 +40788,7 @@ var ResourceSchema = object2({
   uri: string2(),
   description: optional(string2()),
   mimeType: optional(string2()),
+  size: optional(number2()),
   annotations: AnnotationsSchema.optional(),
   _meta: optional(looseObject({}))
 });
@@ -42594,6 +42784,10 @@ class Protocol {
     this._progressHandlers.clear();
     this._taskProgressTokens.clear();
     this._pendingDebouncedNotifications.clear();
+    for (const info of this._timeoutInfo.values()) {
+      clearTimeout(info.timeoutId);
+    }
+    this._timeoutInfo.clear();
     for (const controller of this._requestHandlerAbortControllers.values()) {
       controller.abort();
     }
@@ -42724,7 +42918,9 @@ class Protocol {
         await capturedTransport?.send(errorResponse);
       }
     }).catch((error2) => this._onerror(new Error(`Failed to send response: ${error2}`))).finally(() => {
-      this._requestHandlerAbortControllers.delete(request.id);
+      if (this._requestHandlerAbortControllers.get(request.id) === abortController) {
+        this._requestHandlerAbortControllers.delete(request.id);
+      }
     });
   }
   _onprogress(notification) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jaggerxtrm/specialists",
-  "version": "3.6.11",
+  "version": "3.6.12",
   "description": "OmniSpecialist — 7-tool MCP orchestration layer powered by the Specialist System. Discover and execute .specialist.yaml files across project/user/system scopes via pi.",
   "main": "dist/index.js",
   "type": "module",
@@ -24,7 +24,8 @@
     "test:bun": "bun test tests/unit/specialist/observability-sqlite.test.ts tests/unit/specialist/observability-db.test.ts tests/unit/cli/db.test.ts",
     "test:watch": "bun --bun vitest",
     "test:coverage": "bun --bun vitest run --coverage",
-    "test:supervisor": "bun --bun vitest run tests/unit/specialist/supervisor.test.ts --no-file-parallelism"
+    "test:supervisor": "bun --bun vitest run tests/unit/specialist/supervisor.test.ts --no-file-parallelism",
+    "benchmark:executor": "node scripts/run-executor-benchmark.mjs"
   },
   "keywords": [
     "omnispecialist",

package/config/specialists/.serena/project.yml

@@ -1,151 +0,0 @@
-# the name by which the project can be referenced within Serena
-project_name: "specialists"
-
-
-# list of languages for which language servers are started; choose from:
-#   al                  bash                clojure             cpp                 csharp
-#   csharp_omnisharp    dart                elixir              elm                 erlang
-#   fortran             fsharp              go                  groovy              haskell
-#   java                julia               kotlin              lua                 markdown
-#   matlab              nix                 pascal              perl                php
-#   php_phpactor        powershell          python              python_jedi         r
-#   rego                ruby                ruby_solargraph     rust                scala
-#   swift               terraform           toml                typescript          typescript_vts
-#   vue                 yaml                zig
-#   (This list may be outdated. For the current list, see values of Language enum here:
-#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
-#   For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
-# Note:
-#   - For C, use cpp
-#   - For JavaScript, use typescript
-#   - For Free Pascal/Lazarus, use pascal
-# Special requirements:
-#   Some languages require additional setup/installations.
-#   See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
-# When using multiple languages, the first language server that supports a given file will be used for that file.
-# The first language is the default language and the respective language server will be used as a fallback.
-# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
-languages: []
-
-# the encoding used by text files in the project
-# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
-encoding: "utf-8"
-
-# line ending convention to use when writing source files.
-# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
-# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
-line_ending:
-
-# The language backend to use for this project.
-# If not set, the global setting from serena_config.yml is used.
-# Valid values: LSP, JetBrains
-# Note: the backend is fixed at startup. If a project with a different backend
-# is activated post-init, an error will be returned.
-language_backend:
-
-# whether to use project's .gitignore files to ignore files
-ignore_all_files_in_gitignore: true
-
-# advanced configuration option allowing to configure language server-specific options.
-# Maps the language key to the options.
-# Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available.
-# No documentation on options means no options are available.
-ls_specific_settings: {}
-
-# list of additional paths to ignore in this project.
-# Same syntax as gitignore, so you can use * and **.
-# Note: global ignored_paths from serena_config.yml are also applied additively.
-ignored_paths: []
-
-# whether the project is in read-only mode
-# If set to true, all editing tools will be disabled and attempts to use them will result in an error
-# Added on 2025-04-18
-read_only: false
-
-# list of tool names to exclude.
-# This extends the existing exclusions (e.g. from the global configuration)
-#
-# Below is the complete list of tools for convenience.
-# To make sure you have the latest list of tools, and to view their descriptions, 
-# execute `uv run scripts/print_tool_overview.py`.
-#
-#  * `activate_project`: Activates a project by name.
-#  * `check_onboarding_performed`: Checks whether project onboarding was already performed.
-#  * `create_text_file`: Creates/overwrites a file in the project directory.
-#  * `delete_lines`: Deletes a range of lines within a file.
-#  * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
-#  * `execute_shell_command`: Executes a shell command.
-#  * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
-#  * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
-#  * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
-#  * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
-#  * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
-#  * `initial_instructions`: Gets the initial instructions for the current project.
-#     Should only be used in settings where the system prompt cannot be set,
-#     e.g. in clients you have no control over, like Claude Desktop.
-#  * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
-#  * `insert_at_line`: Inserts content at a given line in a file.
-#  * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
-#  * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
-#  * `list_memories`: Lists memories in Serena's project-specific memory store.
-#  * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
-#  * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
-#  * `read_file`: Reads a file within the project directory.
-#  * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
-#  * `remove_project`: Removes a project from the Serena configuration.
-#  * `replace_lines`: Replaces a range of lines within a file with new content.
-#  * `replace_symbol_body`: Replaces the full definition of a symbol.
-#  * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
-#  * `search_for_pattern`: Performs a search for a pattern in the project.
-#  * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
-#  * `switch_modes`: Activates modes by providing a list of their names
-#  * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
-#  * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
-#  * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
-#  * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
-excluded_tools: []
-
-# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
-# This extends the existing inclusions (e.g. from the global configuration).
-included_optional_tools: []
-
-# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
-# This cannot be combined with non-empty excluded_tools or included_optional_tools.
-fixed_tools: []
-
-# list of mode names to that are always to be included in the set of active modes
-# The full set of modes to be activated is base_modes + default_modes.
-# If the setting is undefined, the base_modes from the global configuration (serena_config.yml) apply.
-# Otherwise, this setting overrides the global configuration.
-# Set this to [] to disable base modes for this project.
-# Set this to a list of mode names to always include the respective modes for this project.
-base_modes:
-
-# list of mode names that are to be activated by default.
-# The full set of modes to be activated is base_modes + default_modes.
-# If the setting is undefined, the default_modes from the global configuration (serena_config.yml) apply.
-# Otherwise, this overrides the setting from the global configuration (serena_config.yml).
-# This setting can, in turn, be overridden by CLI parameters (--mode).
-default_modes:
-
-# initial prompt for the project. It will always be given to the LLM upon activating the project
-# (contrary to the memories, which are loaded on demand).
-initial_prompt: ""
-
-# time budget (seconds) per tool call for the retrieval of additional symbol information
-# such as docstrings or parameter information.
-# This overrides the corresponding setting in the global configuration; see the documentation there.
-# If null or missing, use the setting from the global configuration.
-symbol_info_budget:
-
-# list of regex patterns which, when matched, mark a memory entry as read‑only.
-# Extends the list from the global configuration, merging the two lists.
-read_only_memory_patterns: []
-
-# list of regex patterns for memories to completely ignore.
-# Matching memories will not appear in list_memories or activate_project output
-# and cannot be accessed via read_memory or write_memory.
-# To access ignored memory files, use the read_file tool on the raw file path.
-# Extends the list from the global configuration, merging the two lists.
-# Example: ["_archive/.*", "_episodes/.*"]
-ignored_memory_patterns: []