refactor(ai_client): remove unused history management and bleed stats helpers

src/ai_client.py

@@ -12,7 +12,6 @@ For Gemini: injects the initial context directly into system_instruction
 during chat creation to avoid massive history bloat.
 """
 # ai_client.py
-# ai_client.py
 import tomllib
 import asyncio
 import json
@@ -53,7 +52,7 @@ events: EventEmitter = EventEmitter()
 def set_model_params(temp: float, max_tok: int, trunc_limit: int = 8000, top_p: float = 1.0) -> None:
  """
  Sets global generation parameters like temperature and max tokens.
-  [C: src/app_controller.py:AppController._handle_request_event, src/app_controller.py:AppController.generate, tests/test_history_management.py:test_get_history_bleed_stats_basic]
+  [C: src/app_controller.py:AppController._handle_request_event, src/app_controller.py:AppController.generate]
  """
  global _temperature, _max_tokens, _history_trunc_limit, _top_p
  _temperature = temp
@@ -61,13 +60,6 @@ def set_model_params(temp: float, max_tok: int, trunc_limit: int = 8000, top_p:
  _history_trunc_limit = trunc_limit
  _top_p = top_p
 
-def get_history_trunc_limit() -> int:
- return _history_trunc_limit
-
-def set_history_trunc_limit(val: int) -> None:
- global _history_trunc_limit
- _history_trunc_limit = val
-
 _gemini_client: Optional[genai.Client] = None
 _gemini_chat: Any = None
 _gemini_cache: Any = None
@@ -438,7 +430,7 @@ def _classify_minimax_error(exc: Exception) -> ProviderError:
 def set_provider(provider: str, model: str) -> None:
  """
  Updates the active LLM provider and model name.
-  [C: src/app_controller.py:AppController._handle_reset_session, src/app_controller.py:AppController._init_ai_and_hooks, src/app_controller.py:AppController.current_model, src/app_controller.py:AppController.current_provider, src/app_controller.py:AppController.do_fetch, src/multi_agent_conductor.py:run_worker_lifecycle, src/orchestrator_pm.py:generate_tracks, tests/conftest.py:reset_ai_client, tests/test_ai_cache_tracking.py:test_gemini_cache_tracking, tests/test_ai_client_cli.py:test_ai_client_send_gemini_cli, tests/test_api_events.py:test_send_emits_events_proper, tests/test_api_events.py:test_send_emits_tool_events, tests/test_deepseek_provider.py:test_deepseek_completion_logic, tests/test_deepseek_provider.py:test_deepseek_model_selection, tests/test_deepseek_provider.py:test_deepseek_payload_verification, tests/test_deepseek_provider.py:test_deepseek_reasoner_payload_verification, tests/test_deepseek_provider.py:test_deepseek_reasoning_logic, tests/test_deepseek_provider.py:test_deepseek_streaming, tests/test_deepseek_provider.py:test_deepseek_tool_calling, tests/test_gemini_cli_edge_cases.py:test_gemini_cli_loop_termination, tests/test_gemini_cli_integration.py:test_gemini_cli_full_integration, tests/test_gemini_cli_integration.py:test_gemini_cli_rejection_and_history, tests/test_gemini_cli_parity_regression.py:test_get_history_bleed_stats, tests/test_gemini_cli_parity_regression.py:test_send_invokes_adapter_send, tests/test_gui2_mcp.py:test_mcp_tool_call_is_dispatched, tests/test_history_management.py:test_get_history_bleed_stats_basic, tests/test_minimax_provider.py:test_minimax_default_model, tests/test_minimax_provider.py:test_minimax_history_bleed_stats, tests/test_minimax_provider.py:test_minimax_model_selection, tests/test_mma_agent_focus_phase1.py:test_append_comms_has_source_tier_key, tests/test_rag_integration.py:test_rag_integration, tests/test_tier4_interceptor.py:test_ai_client_passes_qa_callback, tests/test_tier4_interceptor.py:test_gemini_provider_passes_qa_callback_to_run_script, tests/test_token_usage.py:test_token_usage_tracking, tests/test_token_viz.py:test_get_history_bleed_stats_returns_all_keys_unknown_provider]
+  [C: src/app_controller.py:AppController._handle_reset_session, src/app_controller.py:AppController._init_ai_and_hooks, src/app_controller.py:AppController.current_model, src/app_controller.py:AppController.current_provider, src/app_controller.py:AppController.do_fetch, src/multi_agent_conductor.py:run_worker_lifecycle, src/orchestrator_pm.py:generate_tracks, tests/conftest.py:reset_ai_client, tests/test_ai_cache_tracking.py:test_gemini_cache_tracking, tests/test_ai_client_cli.py:test_ai_client_send_gemini_cli, tests/test_api_events.py:test_send_emits_events_proper, tests/test_api_events.py:test_send_emits_tool_events, tests/test_deepseek_provider.py:test_deepseek_completion_logic, tests/test_deepseek_provider.py:test_deepseek_model_selection, tests/test_deepseek_provider.py:test_deepseek_payload_verification, tests/test_deepseek_provider.py:test_deepseek_reasoner_payload_verification, tests/test_deepseek_provider.py:test_deepseek_reasoning_logic, tests/test_deepseek_provider.py:test_deepseek_streaming, tests/test_deepseek_provider.py:test_deepseek_tool_calling, tests/test_gemini_cli_edge_cases.py:test_gemini_cli_loop_termination, tests/test_gemini_cli_integration.py:test_gemini_cli_full_integration, tests/test_gemini_cli_integration.py:test_gemini_cli_rejection_and_history, tests/test_gemini_cli_parity_regression.py:test_send_invokes_adapter_send, tests/test_gui2_mcp.py:test_mcp_tool_call_is_dispatched, tests/test_minimax_provider.py:test_minimax_default_model, tests/test_minimax_provider.py:test_minimax_model_selection, tests/test_mma_agent_focus_phase1.py:test_append_comms_has_source_tier_key, tests/test_rag_integration.py:test_rag_integration, tests/test_tier4_interceptor.py:test_ai_client_passes_qa_callback, tests/test_tier4_interceptor.py:test_gemini_provider_passes_qa_callback_to_run_script, tests/test_token_usage.py:test_token_usage_tracking]
  """
  global _provider, _model
  _provider = provider
@@ -2444,165 +2436,12 @@ def _add_bleed_derived(d: dict[str, Any], sys_tok: int = 0, tool_tok: int = 0) -
 if os.environ.get("SLOP_TOOL_PRESET"):
  try:
   set_tool_preset(os.environ["SLOP_TOOL_PRESET"])
- except Exception as _e:
+ except Exception:
   pass
 
-def get_history_bleed_stats(md_content: Optional[str] = None) -> dict[str, Any]:
- """
- [C: tests/test_gemini_cli_parity_regression.py:test_get_history_bleed_stats, tests/test_history_management.py:test_get_history_bleed_stats_basic, tests/test_minimax_provider.py:test_minimax_history_bleed_stats, tests/test_token_viz.py:test_get_history_bleed_stats_returns_all_keys_unknown_provider]
- """
- if _provider == "anthropic":
-  with _anthropic_history_lock:
-   history_snapshot = list(_anthropic_history)
-  sys_tok = max(1, int(len(md_content) / _CHARS_PER_TOKEN)) if md_content else 0
-  current_tokens = _estimate_prompt_tokens([], history_snapshot)
-  if md_content:
-   current_tokens += max(1, int(len(md_content) / _CHARS_PER_TOKEN))
-  limit_tokens = _ANTHROPIC_MAX_PROMPT_TOKENS
-  percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
-  return _add_bleed_derived({
-   "provider": "anthropic",
-   "limit": limit_tokens,
-   "current": current_tokens,
-   "percentage": percentage,
-  }, sys_tok=sys_tok, tool_tok=2500)
- elif _provider == "gemini":
-  effective_limit = _history_trunc_limit if _history_trunc_limit > 0 else _GEMINI_MAX_INPUT_TOKENS
-  if _gemini_chat:
-   try:
-    _ensure_gemini_client()
-    if _gemini_client:
-     raw_history = list(_get_gemini_history_list(_gemini_chat))
-     history: list[types.Content] = []
-     for c in raw_history:
-      role = "model" if c.role in ["assistant", "model"] else "user"
-      history.append(types.Content(role=role, parts=c.parts))
-     if md_content:
-      history.insert(0, types.Content(role="user", parts=[types.Part(text=md_content)]))
-     if not history:
-      return _add_bleed_derived({
-       "provider": "gemini",
-       "limit": effective_limit,
-       "current": 0,
-       "percentage": 0,
-      })
-     resp = _gemini_client.models.count_tokens(
-      model=_model,
-      contents=history
-     )
-     current_tokens = cast(int, resp.total_tokens)
-     percentage = (current_tokens / effective_limit) * 100 if effective_limit > 0 else 0
-     return _add_bleed_derived({
-      "provider": "gemini",
-      "limit": effective_limit,
-      "current": current_tokens,
-      "percentage": percentage,
-     }, sys_tok=0, tool_tok=0)
-   except Exception:
-    pass
-  elif md_content:
-   try:
-    _ensure_gemini_client()
-    if _gemini_client:
-     resp = _gemini_client.models.count_tokens(
-      model=_model,
-      contents=[types.Content(role="user", parts=[types.Part(text=md_content)])]
-     )
-     current_tokens = cast(int, resp.total_tokens)
-     percentage = (current_tokens / effective_limit) * 100 if effective_limit > 0 else 0
-     return _add_bleed_derived({
-      "provider": "gemini",
-      "limit": effective_limit,
-      "current": current_tokens,
-      "percentage": percentage,
-     })
-   except Exception:
-    pass
-  return _add_bleed_derived({
-   "provider": "gemini",
-   "limit": effective_limit,
-   "current": 0,
-   "percentage": 0,
-  })
- elif _provider == "gemini_cli":
-  effective_limit = _history_trunc_limit if _history_trunc_limit > 0 else _GEMINI_MAX_INPUT_TOKENS
-  limit_tokens = effective_limit
-  current_tokens = 0
-  if _gemini_cli_adapter and _gemini_cli_adapter.last_usage:
-   u = _gemini_cli_adapter.last_usage
-   current_tokens = cast(int, u.get("input_tokens") or u.get("input", 0))
-  percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
-  return _add_bleed_derived({
-   "provider": "gemini_cli",
-   "limit": limit_tokens,
-   "current": current_tokens,
-   "percentage": percentage,
-  })
- elif _provider == "deepseek":
-  limit_tokens = 64000
-  current_tokens = 0
-  with _deepseek_history_lock:
-   for msg in _deepseek_history:
-    content = msg.get("content", "")
-    if isinstance(content, str):
-     current_tokens += len(content)
-    elif isinstance(content, list):
-     for block in content:
-      if isinstance(block, dict):
-       text = block.get("text", "")
-       if isinstance(text, str):
-        current_tokens += len(text)
-       inp = block.get("input")
-       if isinstance(inp, dict):
-        import json as _json
-        current_tokens += len(_json.dumps(inp, ensure_ascii=False))
-  if md_content: current_tokens += len(md_content)
-  current_tokens = max(1, int(current_tokens / _CHARS_PER_TOKEN))
-  percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
-  return _add_bleed_derived({
-   "provider": "deepseek",
-   "limit": limit_tokens,
-   "current": current_tokens,
-   "percentage": percentage,
-  })
- elif _provider == "minimax":
-  limit_tokens = 204800
-  current_tokens = 0
-  with _minimax_history_lock:
-   for msg in _minimax_history:
-    content = msg.get("content", "")
-    if isinstance(content, str):
-     current_tokens += len(content)
-    elif isinstance(content, list):
-     for block in content:
-      if isinstance(block, dict):
-       text = block.get("text", "")
-       if isinstance(text, str):
-        current_tokens += len(text)
-       inp = block.get("input")
-       if isinstance(inp, dict):
-        import json as _json
-        current_tokens += len(_json.dumps(inp, ensure_ascii=False))
-  if md_content: current_tokens += len(md_content)
-  current_tokens = max(1, int(current_tokens / _CHARS_PER_TOKEN))
-  percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
-  return _add_bleed_derived({
-   "provider": "minimax",
-   "limit": limit_tokens,
-   "current": current_tokens,
-   "percentage": percentage,
-  })
- return _add_bleed_derived({
-  "provider": _provider,
-  "limit": 0,
-  "current": 0,
-  "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.
+ Performs a stateless summarization request using a sub-agent prompt.  [C: src/summarize.py:summarise_file, tests/test_subagent_summarization.py:test_run_subagent_summarization_anthropic, tests/test_subagent_summarization.py:test_run_subagent_summarization_gemini]
-  [C: src/summarize.py:summarise_file, tests/test_subagent_summarization.py:test_run_subagent_summarization_anthropic, tests/test_subagent_summarization.py:test_run_subagent_summarization_gemini]
  """
  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)

tests/test_gemini_cli_parity_regression.py

@@ -11,16 +11,3 @@ def test_send_invokes_adapter_send() -> None:
   ai_client.set_provider("gemini_cli", "gemini-2.0-flash")
   res = ai_client.send("context", "msg")
   assert res == "Hello from mock adapter"
-
-def test_get_history_bleed_stats() -> None:
- import src.ai_client as ai_client
- ai_client._gemini_cli_adapter = None
- with patch('src.gemini_cli_adapter.subprocess.Popen') as mock_popen:
-  mock_process = MagicMock()
-  mock_process.communicate.return_value = ('{"type": "message", "content": "txt"}', '')
-  mock_process.returncode = 0
-  mock_popen.return_value = mock_process
-  ai_client.set_provider("gemini_cli", "gemini-2.0-flash")
-  ai_client.send("context", "msg")
-  stats = ai_client.get_history_bleed_stats()
-  assert stats["provider"] == "gemini_cli"

tests/test_history_management.py

@@ -112,22 +112,4 @@ def test_history_persistence_across_turns(tmp_path: Path) -> None:
  reloaded = project_manager.load_project(str(project_path))
  active_disc = reloaded["discussion"]["active"]
  h2 = reloaded["discussion"]["discussions"][active_disc]["history"]
- assert len(h2) >= 2
+ assert len(h2) >= 2
-
-def test_get_history_bleed_stats_basic() -> None:
- """Tests basic retrieval of history bleed statistics from the AI client."""
- ai_client.set_provider("gemini", "gemini-2.5-flash-lite")
- # Before any message, it might be 0 or based on an empty context
- stats = ai_client.get_history_bleed_stats()
- assert "provider" in stats
- assert stats["provider"] == "gemini"
- assert "current" in stats
- assert "limit" in stats, "Stats dictionary should contain 'limit'"
- 
- # Test with a different limit
- ai_client.set_model_params(0.0, 8192, 500)
- stats = ai_client.get_history_bleed_stats()
- assert "current" in stats, "Stats dictionary should contain 'current' token usage"
- assert 'limit' in stats, "Stats dictionary should contain 'limit'"
- assert stats['limit'] == 500
- assert isinstance(stats['current'], int) and stats['current'] >= 0

tests/test_minimax_provider.py

@@ -18,13 +18,6 @@ def test_minimax_list_models() -> None:
  assert "MiniMax-M2.1" in models
  assert "MiniMax-M2" in models
 
-def test_minimax_history_bleed_stats() -> None:
- ai_client.set_provider("minimax", "MiniMax-M2.5")
- ai_client.reset_session()
- stats = ai_client.get_history_bleed_stats(md_content="Test context")
- assert stats["provider"] == "minimax"
- assert stats["limit"] == 204800
-
 def test_minimax_in_providers_list() -> None:
  from src.models import PROVIDERS
  assert "minimax" in PROVIDERS

tests/test_token_viz.py

@@ -47,13 +47,6 @@ def test_add_bleed_derived_headroom_clamped_to_zero() -> None:
  result = ai_client._add_bleed_derived(d)
  assert result["headroom"] == 0
 
-def test_get_history_bleed_stats_returns_all_keys_unknown_provider() -> None:
- """get_history_bleed_stats must return a valid dict even if provider is unknown."""
- ai_client.set_provider("unknown", "unknown")
- stats = ai_client.get_history_bleed_stats()
- for key in ["provider", "limit", "current", "percentage", "estimated_prompt_tokens", "headroom", "would_trim", "sys_tokens", "tool_tokens", "history_tokens"]:
-  assert key in stats
-
 def test_app_token_stats_initialized_empty(app_instance: Any) -> None:
  """App._token_stats should start empty."""
  assert app_instance.controller._token_stats == {}