feat(aggregation): Implement sub-agent summarization pass

src/ai_client.py

@@ -2450,3 +2450,52 @@ def get_history_bleed_stats(md_content: Optional[str] = None) -> dict[str, Any]:
   "percentage": 0,
  })
 
+def run_subagent_summarization(file_path: str, content: str, is_code: bool, outline: str) -> str:
+ """Performs a stateless summarization request using a sub-agent prompt."""
+ prompt_tmpl = mma_prompts.TIER4_SUMMARIZE_CODE_PROMPT if is_code else mma_prompts.TIER4_SUMMARIZE_TEXT_PROMPT
+ prompt = prompt_tmpl.format(file_path=file_path, outline=outline, content=content)
+ if _provider == "gemini":
+  _ensure_gemini_client()
+  if _gemini_client:
+   resp = _gemini_client.models.generate_content(
+    model=_model,
+    contents=prompt,
+    config=types.GenerateContentConfig(
+     temperature=0.0,
+     max_output_tokens=1024,
+    )
+   )
+   return resp.text or ""
+ elif _provider == "anthropic":
+  _ensure_anthropic_client()
+  if _anthropic_client:
+   resp = _anthropic_client.messages.create(
+    model=_model,
+    max_tokens=1024,
+    messages=[{"role": "user", "content": prompt}]
+   )
+   return "".join([b.text for b in resp.content if hasattr(b, "text") and b.text])
+ elif _provider == "deepseek":
+  creds = _load_credentials()
+  api_key = creds.get("deepseek", {}).get("api_key")
+  if not api_key: return "ERROR: DeepSeek API key missing"
+  headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
+  payload = {
+   "model": _model,
+   "messages": [{"role": "user", "content": prompt}],
+   "temperature": 0.0,
+  }
+  try:
+   r = requests.post("https://api.deepseek.com/chat/completions", headers=headers, json=payload, timeout=60)
+   r.raise_for_status()
+   return r.json()["choices"][0]["message"]["content"]
+  except Exception as e:
+   return f"ERROR: DeepSeek summarization failed: {e}"
+ elif _provider == "gemini_cli":
+  # Using the adapter for a one-off call
+  from src.gemini_cli_adapter import GeminiCliAdapter
+  adapter = GeminiCliAdapter(binary_path="gemini")
+  resp_data = adapter.send(prompt, model=_model)
+  return resp_data.get("text", "")
+ return "ERROR: Unsupported provider for sub-agent summarization"
+

src/mma_prompts.py

@@ -179,3 +179,32 @@ RULES:
 Analyze this error and generate the patch:
 """
 
+TIER4_SUMMARIZE_CODE_PROMPT: str = """You are a Tier 4 QA Agent specializing in code summarization.
+Your goal is to provide a concise, high-signal summary of the provided code file.
+Focus on the primary responsibility of the module and its key architectural components.
+
+INPUT:
+- File Path: {file_path}
+- Heuristic Outline: {outline}
+- Raw Content:
+{content}
+
+OUTPUT REQUIREMENT:
+Provide a 1-2 sentence high-level summary followed by a brief bulleted list of key features or responsibilities.
+Keep it extremely concise. Do NOT repeat the outline.
+"""
+
+TIER4_SUMMARIZE_TEXT_PROMPT: str = """You are a Tier 4 QA Agent specializing in document summarization.
+Your goal is to provide a concise, high-signal summary of the provided text/markdown file.
+
+INPUT:
+- File Path: {file_path}
+- Heuristic Outline: {outline}
+- Raw Content:
+{content}
+
+OUTPUT REQUIREMENT:
+Provide a 1-2 sentence high-level summary of the document's purpose and key takeaways.
+Keep it extremely concise.
+"""
+

src/summarize.py

@@ -153,9 +153,9 @@ _SUMMARISERS: dict[str, Callable[[Path, str], str]] = {
 
 def summarise_file(path: Path, content: str) -> str:
  """
-    Return a compact markdown summary string for a single file.
-    `content` is the already-read file text (or an error string).
-    """
+ Return a compact markdown summary string for a single file.
+ `content` is the already-read file text (or an error string).
+ """
  content_hash = get_file_hash(content)
  cached = _summary_cache.get_summary(str(path), content_hash)
  if cached:
@@ -164,7 +164,25 @@ def summarise_file(path: Path, content: str) -> str:
  suffix = path.suffix.lower() if hasattr(path, "suffix") else ""
  fn = _SUMMARISERS.get(suffix, _summarise_generic)
  try:
-  summary = fn(path, content)
+  heuristic_outline = fn(path, content)
+  
+  # Smart AI Summarization
+  is_code = suffix in [".py", ".ps1", ".js", ".ts", ".cpp", ".c", ".h", ".cs", ".go", ".rs", ".lua"]
+  try:
+   from src import ai_client
+   smart_summary = ai_client.run_subagent_summarization(
+    file_path=str(path),
+    content=content[:10000], # Cap content to 10k chars for summarization
+    is_code=is_code,
+    outline=heuristic_outline
+   )
+   if smart_summary and not smart_summary.startswith("ERROR:"):
+    summary = f"{smart_summary}\n\n**Outline:**\n{heuristic_outline}"
+   else:
+    summary = heuristic_outline
+  except Exception:
+   summary = heuristic_outline # Fallback
+  
   _summary_cache.set_summary(str(path), content_hash, summary)
   return summary
  except Exception as e: