Merge pull request 'fix: [QE E2E Test] Failure: E2E Pipeline: IR rules=[] — 0功能规则生成 - Closes #15' (#19) from dev/issue-15-fix-empty-ir-pipeline into main

skills/ir_generation_skill/config.py

@@ -34,12 +34,21 @@ def set_input_file(path: str) -> None:
     global INPUT_JSON
     INPUT_JSON = path
 
-# Secrets file (shared with workspace-document-analyzer)
+# Secrets file — searched in order of priority:
-# .openclaw/workspace/skills/ir_generation_new_skill -> .openclaw/workspace-document-analyzer
+#   1. IR_SECRETS_PATH env var
-OPENCLAW_HOME = os.path.dirname(os.path.dirname(WORKSPACE_DIR))
+#   2. ~/.openclaw/config/secrets.yaml
-SECRETS_YAML = os.path.join(
+#   3. ~/.openclaw/workspace-document-analyzer/config/secrets.yaml
-    OPENCLAW_HOME, "workspace-document-analyzer", "config", "secrets.yaml",
+_SECRETS_CANDIDATES = [
-)
+    os.path.join(os.path.expanduser("~"), ".openclaw", "config", "secrets.yaml"),
+    os.path.join(os.path.expanduser("~"), ".openclaw", "workspace-document-analyzer",
+                 "config", "secrets.yaml"),
+]
+
+_SECRETS_PATH = os.environ.get("IR_SECRETS_PATH", "")
+if _SECRETS_PATH:
+    _SECRETS_CANDIDATES.insert(0, _SECRETS_PATH)
+
+SECRETS_YAML = _SECRETS_CANDIDATES[0]  # primary path (backward compat)
 
 # Intermediate outputs (all under PROJECT_OUTPUT/ir/)
 SEMANTIC_INDEX_R1_JSON = os.path.join(IR_OUTPUT, "semantic_index_r1.json")
@@ -84,10 +93,14 @@ ENSEMBLE_TEMPERATURES = [
 def _load_secrets() -> dict[str, dict[str, str]]:
     """Load provider credentials from secrets.yaml.
 
+    Tries paths in order: IR_SECRETS_PATH env var → ~/.openclaw/config/ →
+    ~/.openclaw/workspace-document-analyzer/config/.
+
     Returns a dict like: {"deepseek": {"apiKey": "...", "baseUrl": "..."}, ...}
     """
-    if os.path.isfile(SECRETS_YAML):
+    for p in _SECRETS_CANDIDATES:
-        with open(SECRETS_YAML, "r", encoding="utf-8") as f:
+        if os.path.isfile(p):
+            with open(p, "r", encoding="utf-8") as f:
                 return yaml.safe_load(f) or {}
     return {}
 
@@ -108,9 +121,11 @@ def _get_provider_config(provider: str) -> dict[str, str]:
     )
 
     if not api_key:
+        tried_paths = "\n  ".join(_SECRETS_CANDIDATES)
         raise RuntimeError(
-            f"No API key found for provider '{provider}'. "
+            f"No API key found for provider '{provider}'.\n"
-            f"Check {SECRETS_YAML} or set {env_prefix}_API_KEY."
+            f"Tried secrets.yaml paths:\n  {tried_paths}\n"
+            f"Or set {env_prefix}_API_KEY environment variable."
         )
     return {"apiKey": api_key, "baseUrl": base_url}
 

skills/ir_generation_skill/step1_semantic_index.py

@@ -548,11 +548,20 @@ def call_llm(prompt: str, max_retries: int = 2,
     Args:
         temperature: Override config.TEMPERATURE. If None, uses config default.
     """
+    import sys as _sys
+
+    try:
         client = config.llm_client()
+    except Exception as e:
+        print(f"  LLM 客户端初始化失败: {e}", file=_sys.stderr)
+        print(f"  请检查: IR_PROVIDER={config.LLM_PROVIDER}, secrets.yaml 或环境变量", file=_sys.stderr)
+        raise
+
     temp = temperature if temperature is not None else config.TEMPERATURE
 
     for attempt in range(max_retries + 1):
-        print(f"  LLM 调用 T={temp} (尝试 {attempt + 1}/{max_retries + 1})...", flush=True)
+        print(f"  LLM 调用 model={config.MODEL_NAME} T={temp} "
+              f"(尝试 {attempt + 1}/{max_retries + 1})...", flush=True)
         try:
             resp = client.chat.completions.create(
                 model=config.MODEL_NAME,
@@ -568,17 +577,31 @@ def call_llm(prompt: str, max_retries: int = 2,
             )
             content = resp.choices[0].message.content
             if content is None:
-                raise RuntimeError("LLM returned empty response")
+                raise RuntimeError(
+                    "LLM 返回空响应 (content=None)。可能是 API 配额不足或模型不可用。"
+                )
+
+            # Log response length and first characters for diagnostics
+            print(f"  响应长度: {len(content)} 字符", flush=True)
 
             json_str = extract_json_from_response(content)
-            return json.loads(json_str)
+            result = json.loads(json_str)
+            n_units = len(result.get("function_units", []))
+            n_concepts = len(result.get("concepts", []))
+            print(f"  提取: {n_concepts} 概念, {n_units} 功能单元", flush=True)
+            return result
 
         except (json.JSONDecodeError, ValueError) as e:
-            print(f"  JSON 解析失败: {e}")
+            print(f"  JSON 解析失败: {e}", file=_sys.stderr)
+            # Show a snippet of what the LLM returned for diagnosis
+            print(f"  LLM 返回内容前 500 字符: {content[:500] if content else '(None)'}", file=_sys.stderr)
             if attempt < max_retries:
                 time.sleep(2)
 
-    raise RuntimeError("无法从 LLM 响应中解析 JSON")
+    raise RuntimeError(
+        f"无法从 LLM 响应中解析 JSON（{max_retries + 1} 次尝试均失败）。"
+        f"最后返回内容前 500 字符: {content[:500] if content else '(None)'}"
+    )
 
 
 # ---- Ensemble Orchestration ----