maestro-flow 0.4.17 → 0.4.19

package/.codex/skills/spec-map/SKILL.md

@@ -61,10 +61,10 @@ $spec-map --continue "20260318-map-auth"
 
 ```csv
 id,title,description,focus_area,output_file,deps,context_from,wave,status,findings,error
-"1","Tech Stack Analysis","Analyze languages, frameworks, dependencies, build system, package managers, runtime configuration. Scan package.json, build configs, CI/CD files.","full","tech-stack.md","","","1","","",""
-"2","Architecture Analysis","Analyze project structure, module boundaries, layer architecture, data flow patterns, entry points, API surface. Map directory tree and import graph.","full","architecture.md","","","1","","",""
-"3","Features Analysis","Inventory user-facing capabilities, API endpoints, CLI commands, UI components, background jobs, integrations. Map to source locations.","full","features.md","","","1","","",""
-"4","Cross-cutting Concerns","Analyze error handling patterns, logging strategy, authentication/authorization, configuration management, testing approach, observability.","full","concerns.md","","","1","","",""
+"1","Tech Stack Analysis","Analyze languages, frameworks, dependencies, build system, package managers, runtime configuration. Scan package.json, build configs, CI/CD files.","full","tech-stack.md","","","1","pending","",""
+"2","Architecture Analysis","Analyze project structure, module boundaries, layer architecture, data flow patterns, entry points, API surface. Map directory tree and import graph.","full","architecture.md","","","1","pending","",""
+"3","Features Analysis","Inventory user-facing capabilities, API endpoints, CLI commands, UI components, background jobs, integrations. Map to source locations.","full","features.md","","","1","pending","",""
+"4","Cross-cutting Concerns","Analyze error handling patterns, logging strategy, authentication/authorization, configuration management, testing approach, observability.","full","concerns.md","","","1","pending","",""
 ```
 
 **Columns**:
@@ -79,9 +79,11 @@ id,title,description,focus_area,output_file,deps,context_from,wave,status,findin
 | `deps` | Input | Empty (all independent) |
 | `context_from` | Input | Empty (no cross-task context) |
 | `wave` | Computed | Always 1 (single wave) |
-| `status` | Output | pending/completed/failed/skipped |
-| `findings` | Output | Analysis summary (max 500 chars) |
-| `error` | Output | Error if failed |
+| `status` | Lifecycle | `pending` (initial) → `completed`/`failed`/`skipped` (set by merge step from worker's `result_status`) |
+| `findings` | Lifecycle | Analysis summary (max 500 chars; merged from worker output) |
+| `error` | Lifecycle | Error if failed (merged) |
+
+**Column separation rule**: Wave CSV (input to `spawn_agents_on_csv`) contains Input columns only. Workers return Output columns exclusively via `output_schema` using `result_status` (NOT `status`). Merge maps `result_status` → master `status`.
 
 </csv_schema>
 
@@ -106,7 +108,62 @@ Generate 4 mapper rows. If focus area specified, scope descriptions to that area
 
 ### Phase 2: Wave Execution
 
-Single wave -- all 4 mappers via `spawn_agents_on_csv` (max_concurrency: 4, 3600s timeout). Each agent returns: id, status (completed/failed), findings, error.
+Single wave -- all 4 mappers via `spawn_agents_on_csv`:
+
+```javascript
+spawn_agents_on_csv({
+  csv_path: `${sessionFolder}/wave-1.csv`,       // only rows where status == "pending"
+  id_column: "id",
+  instruction: MAPPER_INSTRUCTION,                // see "Mapper Worker Contract" below
+  max_concurrency: 4,
+  max_runtime_seconds: 3600,
+  output_csv_path: `${sessionFolder}/wave-1-results.csv`,
+  output_schema: {
+    type: "object",
+    properties: {
+      id:            { type: "string" },
+      result_status: { type: "string", enum: ["completed", "failed"] },
+      findings:      { type: "string", maxLength: 500 },
+      error:         { type: "string" }
+    },
+    required: ["id", "result_status", "findings"]
+  }
+})
+```
+
+Merge: write `master.status = result_status`, copy `findings` and `error`. Delete `wave-1.csv` and `wave-1-results.csv`.
+
+#### Mapper Worker Contract (MAPPER_INSTRUCTION)
+
+```
+You are a codebase mapper for ONE dimension. Your assigned focus_area, description, and output_file come from your CSV row.
+
+REQUIRED STEPS:
+  1. Read shared discoveries: {sessionFolder}/discoveries.ndjson (may be empty)
+  2. Scan codebase using Read/Grep/Glob within your focus_area
+  3. Synthesize findings into the analysis sections required by your description
+  4. Append reusable discoveries (tech_stack / code_pattern / integration_point / convention) to discoveries.ndjson
+  5. Call report_agent_job_result EXACTLY ONCE
+
+TERMINATION CONTRACT (mandatory — NO worker may end without calling report_agent_job_result):
+  - Success path → result_status = completed
+  - Timeout path → if approaching max_runtime_seconds, STOP and report failed with error="timeout (partial findings)"
+  - Failure path → on unrecoverable error, report failed with error message
+  - NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+OUTPUT (return via report_agent_job_result; must match output_schema):
+  {
+    "id": "<your row id>",
+    "result_status": "completed" | "failed",
+    "findings": "<analysis summary, max 500 chars — orchestrator uses this to write {output_file}>",
+    "error": "<message if failed, else empty>"
+  }
+
+CONSTRAINTS:
+  - Read-only. Do NOT write to .workflow/codebase/ — orchestrator writes output files from your findings in Phase 3.
+  - Do NOT write to tasks.csv, wave-*.csv, or results.csv.
+  - Do NOT call spawn_agents_on_csv (no recursion).
+```
 
 ### Phase 3: Write Output Files
 

package/.codex/skills/team-coordinate/SKILL.md

@@ -303,18 +303,22 @@ Extract qualifying rows from master CSV. Add `prev_context` column.
 
 ```javascript
 spawn_agents_on_csv({
-  csv_path: `${sessionFolder}/wave-${N}.csv`,
+  csv_path: `${sessionFolder}/wave-${N}.csv`,    // only rows where wave==N AND status=="pending"
   id_column: "id",
-  instruction: /* see Instruction Builder section below */,
+  instruction: TEAM_COORDINATE_INSTRUCTION,       // see "Instruction Builder" section below
   max_concurrency: maxConcurrency,
   max_runtime_seconds: 3600,
   output_csv_path: `${sessionFolder}/wave-${N}-results.csv`,
   output_schema: {
-    id,              // mandatory: links to master CSV
-    result_status,   // mandatory: completed | failed | blocked
-    findings,        // key findings (max 500 chars)
-    files_modified,  // semicolon-separated paths
-    error            // error message if not completed
+    type: "object",
+    properties: {
+      id:             { type: "string" },
+      result_status:  { type: "string", enum: ["completed", "failed", "blocked"] },
+      findings:       { type: "string", maxLength: 500 },
+      files_modified: { type: "string", description: "Semicolon-separated paths" },
+      error:          { type: "string" }
+    },
+    required: ["id", "result_status", "findings"]
   }
 })
 ```
@@ -409,12 +413,25 @@ Append findings as NDJSON lines:
 {"ts":"<ISO>","worker":"<TASK-ID>","type":"<TYPE>","data":{...}}
 Types: code_pattern, integration_point, convention, blocker, key_finding, decision
 
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success path → result_status=completed after verification passes
+- Failure path → unrecoverable error (build fails, scope unclear, contract violation) → result_status=failed with error message
+- Blocked path → cannot proceed without upstream fix → result_status=blocked with error explaining what is needed
+- Timeout path → approaching max_runtime_seconds → revert partial unsafe work, report blocked with error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
 ## Output
-Return via output_schema:
-- result_status: completed | failed | blocked
+Return via output_schema (matches schema declared in spawn call):
+- id: your CSV row id (mandatory)
+- result_status: completed | failed | blocked (mandatory)
 - findings: key findings summary (max 500 chars, be specific and actionable)
-- files_modified: semicolon-separated paths of created/modified files
-- error: error message if result_status is not completed
+- files_modified: semicolon-separated paths of created/modified files (empty if none)
+- error: error message if result_status is not completed (empty otherwise)
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
 ```
 
 </actions>

package/.codex/skills/team-coordinate/specs/role-catalog.md

@@ -80,6 +80,26 @@ All agents — regardless of dynamically assigned role — MUST follow these tra
 - 2 retries exhausted → report `failed` with evidence
 - NEVER skip verification and report completed
 
+### Termination Contract (MANDATORY)
+
+Every spawned worker MUST call `report_agent_job_result` EXACTLY ONCE before exiting. NO exceptions:
+
+| Path | Action |
+|------|--------|
+| Success | `result_status=completed` after verification passes |
+| Failure | `result_status=failed` with error message (build error, file write failure, unrecoverable tool error) |
+| Blocked | `result_status=blocked` when upstream missing OR retries exhausted |
+| Timeout | Approaching `max_runtime_seconds` → revert partial unsafe work → `result_status=blocked` with error="timeout" |
+
+- NEVER continue indefinitely.
+- NEVER exit silently.
+- NEVER omit `report_agent_job_result`.
+
+### Hard Constraints
+
+- Do NOT write to `tasks.csv`, `wave-*.csv`, `results.csv` — orchestrator owns those.
+- Do NOT call `spawn_agents_on_csv` (no recursion).
+
 ## 6. Quality Scoring
 
 | Result | Score | Action |

package/.codex/skills/team-lifecycle-v4/SKILL.md

@@ -302,19 +302,23 @@ Extract wave N rows + add `prev_context` column.
 
 ```javascript
 spawn_agents_on_csv({
-  csv_path: `${sessionFolder}/wave-${N}.csv`,
+  csv_path: `${sessionFolder}/wave-${N}.csv`,    // only rows where wave==N AND status=="pending"
   id_column: "id",
   instruction: buildLifecycleInstruction(sessionFolder, skillRoot),
   max_concurrency: maxConcurrency,
   max_runtime_seconds: 3600,
   output_csv_path: `${sessionFolder}/wave-${N}-results.csv`,
   output_schema: {
-    id,
-    result_status,    // completed | failed | blocked
-    findings,         // key findings (max 500 chars)
-    files_modified,   // semicolon-separated paths
-    quality_score,    // 0-100
-    error             // error message
+    type: "object",
+    properties: {
+      id:             { type: "string" },
+      result_status:  { type: "string", enum: ["completed", "failed", "blocked"] },
+      findings:       { type: "string", maxLength: 500 },
+      files_modified: { type: "string", description: "Semicolon-separated paths" },
+      quality_score:  { type: "string", description: "0-100" },
+      error:          { type: "string" }
+    },
+    required: ["id", "result_status", "findings"]
   }
 })
 ```
@@ -363,6 +367,18 @@ For roles with commands/ subdirectory, load the relevant command file based on y
 3. Retry on verification failure (max 2 retries)
 4. Report blocked if still failing after retries
 
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success → result_status=completed after all verifications pass
+- Failure → result_status=failed with error message (build error, file write fail)
+- Blocked → result_status=blocked when upstream missing OR after retries exhausted
+- Timeout → near max_runtime_seconds → revert partial unsafe work → result_status=blocked, error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
+
 ## Discovery Protocol
 Write task output to {sessionFolder}/discoveries/{task_id}.json:
 {

package/.codex/skills/team-lifecycle-v4/instructions/agent-instruction.md

@@ -811,6 +811,24 @@ All roles read/write `{session}/discoveries.ndjson`:
 
 ---
 
+## Termination Contract (MANDATORY for ALL roles)
+
+Every spawned worker — regardless of role — MUST call `report_agent_job_result` EXACTLY ONCE before exiting. NO exceptions:
+
+| Path | Action |
+|------|--------|
+| Success | `status=completed` after verification passes |
+| Failure | `status=failed` with error message (unrecoverable error) |
+| Blocked | `status=failed` (no separate "blocked" enum here — use error message to explain blockage) |
+| Timeout | Approaching `max_runtime_seconds` → revert partial unsafe work → `status=failed` with error="timeout" |
+
+Rules:
+- NEVER continue indefinitely.
+- NEVER exit silently.
+- NEVER omit `report_agent_job_result`.
+- Do NOT write to tasks.csv, wave-*.csv, results.csv — orchestrator owns those.
+- Do NOT call `spawn_agents_on_csv` (no recursion).
+
 ## Output Format
 
 All roles use `report_agent_job_result` with this schema:
@@ -825,3 +843,5 @@ All roles use `report_agent_job_result` with this schema:
   "error": ""
 }
 ```
+
+Note: spawn output_schema in SKILL.md uses `result_status` (not `status`). The orchestrator's merge step maps `result_status` → master `status`. Workers report via `report_agent_job_result` which the harness converts to the CSV result row — the field key here (`status`) is the worker-facing field name documented for this skill family.

package/.codex/skills/team-quality-assurance/SKILL.md

@@ -178,10 +178,48 @@ Session: {sessionFolder}
 Discovery board: {sessionFolder}/discoveries.ndjson
 Previous context: 'prev_context' column
 
-## Output
-result_status, findings, files_modified, coverage_score (QARUN only), error
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success → result_status=completed
+- Failure → result_status=failed with error message
+- Blocked → result_status=blocked when upstream missing
+- Timeout → near max_runtime_seconds → result_status=blocked, error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+## Output (must match output_schema)
+{
+  "id": "<your CSV row id>",
+  "result_status": "completed" | "failed" | "blocked",
+  "findings": "<key findings, max 500 chars>",
+  "files_modified": "<semicolon-separated paths or empty>",
+  "coverage_score": "<0-100 or empty>" (QARUN only),
+  "error": "<message if not completed>"
+}
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
 ```
 
+### Spawn output_schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "id":             { "type": "string" },
+    "result_status":  { "type": "string", "enum": ["completed", "failed", "blocked"] },
+    "findings":       { "type": "string", "maxLength": 500 },
+    "files_modified": { "type": "string" },
+    "coverage_score": { "type": "string" },
+    "error":          { "type": "string" }
+  },
+  "required": ["id", "result_status", "findings"]
+}
+```
+
+Merge maps `result_status` → master `status`.
+
 </actions>
 </state_machine>
 

package/.codex/skills/team-review/SKILL.md

@@ -172,10 +172,50 @@ Discovery board: {sessionFolder}/discoveries.ndjson
 Previous context: 'prev_context' column
 Dimensions: {skillRoot}/specs/dimensions.md
 
-## Output
-result_status, findings, files_modified, finding_count, verdict (REV only), error
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success → result_status=completed after scan/review/fix completes
+- Failure → result_status=failed with error message
+- Blocked → result_status=blocked when upstream missing
+- Timeout → near max_runtime_seconds → result_status=blocked, error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+## Output (must match output_schema)
+{
+  "id": "<your CSV row id>",
+  "result_status": "completed" | "failed" | "blocked",
+  "findings": "<key findings, max 500 chars>",
+  "files_modified": "<semicolon-separated paths or empty>",
+  "finding_count": "<integer or empty>",
+  "verdict": "PASS" | "WARN" | "BLOCK" | "" (REV only),
+  "error": "<message if not completed>"
+}
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
 ```
 
+### Spawn output_schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "id":             { "type": "string" },
+    "result_status":  { "type": "string", "enum": ["completed", "failed", "blocked"] },
+    "findings":       { "type": "string", "maxLength": 500 },
+    "files_modified": { "type": "string" },
+    "finding_count":  { "type": "string" },
+    "verdict":        { "type": "string", "enum": ["PASS", "WARN", "BLOCK", ""] },
+    "error":          { "type": "string" }
+  },
+  "required": ["id", "result_status", "findings"]
+}
+```
+
+Merge maps `result_status` → master `status`.
+
 </actions>
 </state_machine>
 

package/.codex/skills/team-tech-debt/SKILL.md

@@ -187,10 +187,53 @@ Session: {sessionFolder}
 Discovery board: {sessionFolder}/discoveries.ndjson
 Previous context: 'prev_context' column
 
-## Output
-result_status, findings, files_modified, debt_count, regression_detected (TDVAL), error
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success → result_status=completed after verification
+- Failure → result_status=failed with error message
+- Blocked → cannot proceed without upstream fix → result_status=blocked
+- Timeout → near max_runtime_seconds → revert partial unsafe work → result_status=blocked, error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+## Output (must match output_schema)
+Return JSON:
+{
+  "id": "<your CSV row id>",
+  "result_status": "completed" | "failed" | "blocked",
+  "findings": "<key findings, max 500 chars>",
+  "files_modified": "<semicolon-separated paths or empty>",
+  "debt_count": <integer or empty>,
+  "regression_detected": "true" | "false" | "" (TDVAL only),
+  "error": "<message if not completed>"
+}
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
 ```
 
+### Spawn output_schema
+
+When the coordinator dispatches a wave via `spawn_agents_on_csv`, it MUST use the strict JSON Schema:
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "id":                  { "type": "string" },
+    "result_status":       { "type": "string", "enum": ["completed", "failed", "blocked"] },
+    "findings":            { "type": "string", "maxLength": 500 },
+    "files_modified":      { "type": "string" },
+    "debt_count":          { "type": "string" },
+    "regression_detected": { "type": "string", "enum": ["true", "false", ""] },
+    "error":               { "type": "string" }
+  },
+  "required": ["id", "result_status", "findings"]
+}
+```
+
+Merge maps `result_status` → master `status`.
+
 </actions>
 </state_machine>
 

package/.codex/skills/team-testing/SKILL.md

@@ -183,10 +183,50 @@ Session: {sessionFolder}
 Discovery board: {sessionFolder}/discoveries.ndjson
 Previous context: 'prev_context' column
 
-## Output
-result_status, findings, files_modified, pass_rate (TESTRUN), coverage_score (TESTRUN), error
+## Termination Contract (MANDATORY)
+You MUST call report_agent_job_result EXACTLY ONCE before exiting. NO exceptions.
+- Success → result_status=completed after tests run / coverage measured
+- Failure → result_status=failed with error message
+- Blocked → cannot proceed without upstream fix → result_status=blocked
+- Timeout → near max_runtime_seconds → result_status=blocked, error="timeout"
+- NEVER continue indefinitely. NEVER exit silently. NEVER omit the call.
+
+## Output (must match output_schema)
+{
+  "id": "<your CSV row id>",
+  "result_status": "completed" | "failed" | "blocked",
+  "findings": "<key findings, max 500 chars>",
+  "files_modified": "<semicolon-separated paths or empty>",
+  "pass_rate": "<0-100 or empty>" (TESTRUN only),
+  "coverage_score": "<0-100 or empty>" (TESTRUN only),
+  "error": "<message if not completed>"
+}
+
+## Hard Constraints
+- Do NOT write to tasks.csv, wave-*.csv, results.csv (orchestrator owns those).
+- Do NOT call spawn_agents_on_csv (no recursion).
 ```
 
+### Spawn output_schema
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "id":             { "type": "string" },
+    "result_status":  { "type": "string", "enum": ["completed", "failed", "blocked"] },
+    "findings":       { "type": "string", "maxLength": 500 },
+    "files_modified": { "type": "string" },
+    "pass_rate":      { "type": "string" },
+    "coverage_score": { "type": "string" },
+    "error":          { "type": "string" }
+  },
+  "required": ["id", "result_status", "findings"]
+}
+```
+
+Merge maps `result_status` → master `status`.
+
 </actions>
 </state_machine>
 

package/dashboard/dist-server/dashboard/src/server/wiki/search.d.ts

@@ -14,11 +14,13 @@ export interface SearchResult {
     score: number;
 }
 /**
- * Tokenize into lowercase terms. Strips non-word chars, drops tokens shorter
- * than 2 characters, and filters a tiny English stop-word set.
+ * Tokenize into lowercase terms. Strategy:
+ *   1. Lowercase, split on non-word chars (\p{L}\p{N})
+ *   2. For each chunk: if contains CJK → emit 2/3-char n-grams; otherwise
+ *      keep the chunk if it passes length + stop-word filters.
  *
- * CJK characters are not split by this regex; callers searching Chinese
- * corpora should feed substrings directly — ranking is approximate then.
+ * Query and document use the same function so n-grams from both sides
+ * intersect in the inverted index → BM25 ranking works for CJK corpora.
  */
 export declare function tokenize(text: string): string[];
 export declare function buildInvertedIndex(entries: WikiEntry[]): InvertedIndex;

package/dashboard/dist-server/dashboard/src/server/wiki/search.js

@@ -9,12 +9,36 @@ const STOP_WORDS = new Set([
     'is', 'it', 'with', 'as', 'at', 'by', 'be', 'are', 'was', 'were',
     'this', 'that', 'from', 'but', 'not',
 ]);
+// CJK character range: CJK Unified Ideographs + CJK Extension A.
+// Used to detect runs that need n-gram splitting (BM25 can't match
+// otherwise — a single 4-char Chinese term would never overlap a 2-char
+// query substring). Hiragana/katakana/hangul are out of scope for now.
+const CJK_RUN = /[一-鿿㐀-䶿]+/g;
+const HAS_CJK = /[一-鿿㐀-䶿]/;
 /**
- * Tokenize into lowercase terms. Strips non-word chars, drops tokens shorter
- * than 2 characters, and filters a tiny English stop-word set.
+ * Extract 2- and 3-char n-grams from a CJK run. 2/3 covers the majority of
+ * Chinese terms while keeping the inverted index size bounded; 4+ grams
+ * explode postings without proportional recall gain.
+ */
+function cjkNgrams(run) {
+    const out = [];
+    for (let n = 2; n <= 3; n++) {
+        if (run.length < n)
+            break;
+        for (let i = 0; i <= run.length - n; i++) {
+            out.push(run.substring(i, i + n));
+        }
+    }
+    return out;
+}
+/**
+ * Tokenize into lowercase terms. Strategy:
+ *   1. Lowercase, split on non-word chars (\p{L}\p{N})
+ *   2. For each chunk: if contains CJK → emit 2/3-char n-grams; otherwise
+ *      keep the chunk if it passes length + stop-word filters.
  *
- * CJK characters are not split by this regex; callers searching Chinese
- * corpora should feed substrings directly — ranking is approximate then.
+ * Query and document use the same function so n-grams from both sides
+ * intersect in the inverted index → BM25 ranking works for CJK corpora.
  */
 export function tokenize(text) {
     if (!text)
@@ -22,11 +46,29 @@ export function tokenize(text) {
     const out = [];
     const parts = text.toLowerCase().split(/[^\p{L}\p{N}]+/u);
     for (const p of parts) {
-        if (p.length < 2)
-            continue;
-        if (STOP_WORDS.has(p))
+        if (!p)
             continue;
-        out.push(p);
+        if (HAS_CJK.test(p)) {
+            // A chunk may mix CJK and Latin (e.g. "用户auth"); slice each CJK run
+            // for n-gram emission and keep any Latin remainder as its own token.
+            const cjkRuns = p.match(CJK_RUN) ?? [];
+            for (const run of cjkRuns) {
+                for (const g of cjkNgrams(run))
+                    out.push(g);
+            }
+            const latinRemainder = p.replace(CJK_RUN, ' ').split(/\s+/).filter(Boolean);
+            for (const lr of latinRemainder) {
+                if (lr.length >= 2 && !STOP_WORDS.has(lr))
+                    out.push(lr);
+            }
+        }
+        else {
+            if (p.length < 2)
+                continue;
+            if (STOP_WORDS.has(p))
+                continue;
+            out.push(p);
+        }
     }
     return out;
 }

package/dashboard/dist-server/dashboard/src/server/wiki/search.js.map

@@ -1 +1 @@
-{"version":3,"file":"search.js","sourceRoot":"","sources":["../../../../../src/server/wiki/search.ts"],"names":[],"mappings":"AAEA;;;GAGG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AACpB,MAAM,MAAM,GAAG,IAAI,CAAC;AAEpB,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC;IACzB,KAAK,EAAE,GAAG,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK;IAC5D,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM;IAChE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK;CACrC,CAAC,CAAC;AAmBH;;;;;;GAMG;AACH,MAAM,UAAU,QAAQ,CAAC,IAAY;IACnC,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IACrB,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,KAAK,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,iBAAiB,CAAC,CAAC;IAC1D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;YAAE,SAAS;QAC3B,IAAI,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC;YAAE,SAAS;QAChC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACd,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,KAAgB;IACpC,OAAO;QACL,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,KAAK,EAAG,kBAAkB;QAC1D,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAG,iBAAiB;QAC9D,KAAK,CAAC,QAAQ,IAAI,EAAE;QACpB,KAAK,CAAC,IAAI;KACX,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AACd,CAAC;AAED,MAAM,UAAU,kBAAkB,CAAC,OAAoB;IACrD,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAqB,CAAC;IAC9C,MAAM,UAAU,GAAG,IAAI,GAAG,EAAkB,CAAC;IAC7C,IAAI,WAAW,GAAG,CAAC,CAAC;IAEpB,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,MAAM,MAAM,GAAG,QAAQ,CAAC,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC;QAC7C,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC;QACxC,WAAW,IAAI,MAAM,CAAC,MAAM,CAAC;QAE7B,MAAM,UAAU,GAAG,IAAI,GAAG,EAAkB,CAAC;QAC7C,KAAK,MAAM,CAAC,IAAI,MAAM;YAAE,UAAU,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAExE,KAAK,MAAM,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,UAAU,EAAE,CAAC;YACpC,IAAI,IAAI,GAAG,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YAC9B,IAAI,CAAC,IAAI,EAAE,CAAC;gBACV,IAAI,GAAG,EAAE,CAAC;gBACV,QAAQ,CAAC,GAAG,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;YAC3B,CAAC;YACD,IAAI,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IAED,MAAM,SAAS,GAAG,OAAO,CAAC,MAAM,CAAC;IACjC,MAAM,YAAY,GAAG,SAAS,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,WAAW,GAAG,SAAS,CAAC;IAEnE,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,YAAY,EAAE,SAAS,EAAE,CAAC;AAC3D,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,UAAU,CACxB,KAAoB,EACpB,KAAa,EACb,KAAK,GAAG,EAAE;IAEV,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;IAC9B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,IAAI,KAAK,CAAC,SAAS,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IAE3D,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IACzC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QAC1C,IAAI,CAAC,QAAQ,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC;YAAE,SAAS;QAEjD,gDAAgD;QAChD,MAAM,EAAE,GAAG,QAAQ,CAAC,MAAM,CAAC;QAC3B,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,SAAS,GAAG,EAAE,GAAG,GAAG,CAAC,GAAG,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC;QAEpE,KAAK,MAAM,EAAE,KAAK,EAAE,EAAE,EAAE,IAAI,QAAQ,EAAE,CAAC;YACrC,MAAM,EAAE,GAAG,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YAC5C,MAAM,KAAK,GAAG,EAAE,GAAG,OAAO,GAAG,CAAC,CAAC,GAAG,MAAM,GAAG,CAAC,MAAM,GAAG,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,CAAC;YACtF,MAAM,SAAS,GAAG,GAAG,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,OAAO,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC;YAC9D,MAAM,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,SAAS,CAAC,CAAC;QAC1D,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAmB,EAAE,CAAC;IAClC,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,MAAM;QAAE,MAAM,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC,CAAC;IACnE,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3E,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;AAChC,CAAC"}
+{"version":3,"file":"search.js","sourceRoot":"","sources":["../../../../../src/server/wiki/search.ts"],"names":[],"mappings":"AAEA;;;GAGG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AACpB,MAAM,MAAM,GAAG,IAAI,CAAC;AAEpB,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC;IACzB,KAAK,EAAE,GAAG,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK;IAC5D,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM;IAChE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK;CACrC,CAAC,CAAC;AAmBH,iEAAiE;AACjE,mEAAmE;AACnE,wEAAwE;AACxE,uEAAuE;AACvE,MAAM,OAAO,GAAG,YAAY,CAAC;AAC7B,MAAM,OAAO,GAAG,UAAU,CAAC;AAE3B;;;;GAIG;AACH,SAAS,SAAS,CAAC,GAAW;IAC5B,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;QAC5B,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC;YAAE,MAAM;QAC1B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;YACzC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;QACpC,CAAC;IACH,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,UAAU,QAAQ,CAAC,IAAY;IACnC,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IACrB,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,KAAK,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,iBAAiB,CAAC,CAAC;IAC1D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,IAAI,CAAC,CAAC;YAAE,SAAS;QACjB,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACpB,oEAAoE;YACpE,qEAAqE;YACrE,MAAM,OAAO,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;YACvC,KAAK,MAAM,GAAG,IAAI,OAAO,EAAE,CAAC;gBAC1B,KAAK,MAAM,CAAC,IAAI,SAAS,CAAC,GAAG,CAAC;oBAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YAC9C,CAAC;YACD,MAAM,cAAc,GAAG,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;YAC5E,KAAK,MAAM,EAAE,IAAI,cAAc,EAAE,CAAC;gBAChC,IAAI,EAAE,CAAC,MAAM,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;oBAAE,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YAC1D,CAAC;QACH,CAAC;aAAM,CAAC;YACN,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;gBAAE,SAAS;YAC3B,IAAI,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC;gBAAE,SAAS;YAChC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,KAAgB;IACpC,OAAO;QACL,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,KAAK,EAAG,kBAAkB;QAC1D,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAG,iBAAiB;QAC9D,KAAK,CAAC,QAAQ,IAAI,EAAE;QACpB,KAAK,CAAC,IAAI;KACX,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AACd,CAAC;AAED,MAAM,UAAU,kBAAkB,CAAC,OAAoB;IACrD,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAqB,CAAC;IAC9C,MAAM,UAAU,GAAG,IAAI,GAAG,EAAkB,CAAC;IAC7C,IAAI,WAAW,GAAG,CAAC,CAAC;IAEpB,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,MAAM,MAAM,GAAG,QAAQ,CAAC,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC;QAC7C,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC;QACxC,WAAW,IAAI,MAAM,CAAC,MAAM,CAAC;QAE7B,MAAM,UAAU,GAAG,IAAI,GAAG,EAAkB,CAAC;QAC7C,KAAK,MAAM,CAAC,IAAI,MAAM;YAAE,UAAU,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAExE,KAAK,MAAM,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,UAAU,EAAE,CAAC;YACpC,IAAI,IAAI,GAAG,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YAC9B,IAAI,CAAC,IAAI,EAAE,CAAC;gBACV,IAAI,GAAG,EAAE,CAAC;gBACV,QAAQ,CAAC,GAAG,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;YAC3B,CAAC;YACD,IAAI,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IAED,MAAM,SAAS,GAAG,OAAO,CAAC,MAAM,CAAC;IACjC,MAAM,YAAY,GAAG,SAAS,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,WAAW,GAAG,SAAS,CAAC;IAEnE,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,YAAY,EAAE,SAAS,EAAE,CAAC;AAC3D,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,UAAU,CACxB,KAAoB,EACpB,KAAa,EACb,KAAK,GAAG,EAAE;IAEV,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;IAC9B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,IAAI,KAAK,CAAC,SAAS,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IAE3D,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IACzC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QAC1C,IAAI,CAAC,QAAQ,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC;YAAE,SAAS;QAEjD,gDAAgD;QAChD,MAAM,EAAE,GAAG,QAAQ,CAAC,MAAM,CAAC;QAC3B,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,SAAS,GAAG,EAAE,GAAG,GAAG,CAAC,GAAG,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC;QAEpE,KAAK,MAAM,EAAE,KAAK,EAAE,EAAE,EAAE,IAAI,QAAQ,EAAE,CAAC;YACrC,MAAM,EAAE,GAAG,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YAC5C,MAAM,KAAK,GAAG,EAAE,GAAG,OAAO,GAAG,CAAC,CAAC,GAAG,MAAM,GAAG,CAAC,MAAM,GAAG,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,CAAC;YACtF,MAAM,SAAS,GAAG,GAAG,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,OAAO,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC;YAC9D,MAAM,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,SAAS,CAAC,CAAC;QAC1D,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAmB,EAAE,CAAC;IAClC,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,MAAM;QAAE,MAAM,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC,CAAC;IACnE,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3E,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;AAChC,CAAC"}

package/dashboard/dist-server/dashboard/src/server/wiki/virtual-wiki-adapters.d.ts

@@ -1,3 +1,35 @@
 import type { WikiEntry } from './wiki-types.js';
 export declare function adaptIssueRow(row: unknown, sourcePath: string, line: number): WikiEntry | null;
 export declare function loadVirtualEntries(absPath: string, adapter: (row: unknown, sourcePath: string, line: number) => WikiEntry | null, relPath: string): Promise<WikiEntry[]>;
+export declare function loadVirtualJsonEntries(absPath: string, adapter: (parsed: unknown, sourcePath: string) => WikiEntry[], relPath: string): Promise<WikiEntry[]>;
+export declare function adaptCodebaseDocIndex(parsed: unknown, sourcePath: string): WikiEntry[];
+interface ContextPackageInsight {
+    role?: string;
+    area?: string;
+    summary?: string;
+}
+interface ContextPackageConstraint {
+    area?: string;
+}
+interface ContextPackagePeek {
+    insights?: ContextPackageInsight[];
+    constraints?: ContextPackageConstraint[];
+    open_questions?: unknown[];
+    requirements?: unknown[];
+    domain?: {
+        problem_statement?: string;
+    };
+}
+/**
+ * Adapter for session archive.json files. Returns the lazy reader pattern:
+ * pass `peekContextPackage` to enrich summary/tags from context-package.json
+ * sibling. If unavailable, archive metadata alone is used.
+ */
+export declare function adaptSessionArchive(parsed: unknown, sourcePath: string, peek?: ContextPackagePeek | null): WikiEntry[];
+/**
+ * Reads archive.json + optional sibling context-package.json (for summary
+ * enrichment) and returns adapted WikiEntries. Tolerates missing/malformed
+ * context-package — only archive.json is required.
+ */
+export declare function loadSessionArchiveEntries(archiveAbsPath: string, archiveRelPath: string): Promise<WikiEntry[]>;
+export {};