conductor(plan): Finalize checkpoint for track 'api_vendor_alignment_20260223'

ai_client.py

@@ -18,7 +18,8 @@ import datetime
 from pathlib import Path
 import file_cache
 import mcp_client
-import google.genai
+import anthropic
+from google import genai
 from google.genai import types
 from events import EventEmitter
 
@@ -155,7 +156,7 @@ class ProviderError(Exception):
 
 def _classify_anthropic_error(exc: Exception) -> ProviderError:
     try:
-        import anthropic
+
         if isinstance(exc, anthropic.RateLimitError):
             return ProviderError("rate_limit", "anthropic", exc)
         if isinstance(exc, anthropic.AuthenticationError):
@@ -276,9 +277,9 @@ def list_models(provider: str) -> list[str]:
 
 
 def _list_gemini_models(api_key: str) -> list[str]:
-    # from google import genai # Removed
+
     try:
-        client = google.genai.Client(api_key=api_key)
+        client = genai.Client(api_key=api_key)
         models = []
         for m in client.models.list():
             name = m.name
@@ -292,7 +293,7 @@ def _list_gemini_models(api_key: str) -> list[str]:
 
 
 def _list_anthropic_models() -> list[str]:
-    import anthropic
+
     try:
         creds = _load_credentials()
         client = anthropic.Anthropic(api_key=creds["anthropic"]["api_key"])
@@ -370,7 +371,7 @@ def _get_anthropic_tools() -> list[dict]:
 
 
 def _gemini_tool_declaration():
-    # from google.genai import types # Removed
+
 
     declarations = []
 
@@ -380,15 +381,17 @@ def _gemini_tool_declaration():
             continue
         props = {}
         for pname, pdef in spec["parameters"].get("properties", {}).items():
-            props[pname] = google.genai.types.Schema(
-                type=google.genai.types.Type.STRING,
+            ptype_str = pdef.get("type", "string").upper()
+            ptype = getattr(types.Type, ptype_str, types.Type.STRING)
+            props[pname] = types.Schema(
+                type=ptype,
                 description=pdef.get("description", ""),
             )
-        declarations.append(google.genai.types.FunctionDeclaration(
+        declarations.append(types.FunctionDeclaration(
             name=spec["name"],
             description=spec["description"],
-            parameters=google.genai.types.Schema(
-                type=google.genai.types.Type.OBJECT,
+            parameters=types.Schema(
+                type=types.Type.OBJECT,
                 properties=props,
                 required=spec["parameters"].get("required", []),
             ),
@@ -396,7 +399,7 @@ def _gemini_tool_declaration():
 
     # PowerShell tool
     if _agent_tools.get(TOOL_NAME, True):
-        declarations.append(google.genai.types.FunctionDeclaration(
+        declarations.append(types.FunctionDeclaration(
             name=TOOL_NAME,
             description=(
                 "Run a PowerShell script within the project base_dir. "
@@ -404,11 +407,11 @@ def _gemini_tool_declaration():
                 "The working directory is set to base_dir automatically. "
                 "stdout and stderr are returned to you as the result."
             ),
-            parameters=google.genai.types.Schema(
-                type=google.genai.types.Type.OBJECT,
+            parameters=types.Schema(
+                type=types.Type.OBJECT,
                 properties={
-                    "script": google.genai.types.Schema(
-                        type=google.genai.types.Type.STRING,
+                    "script": types.Schema(
+                        type=types.Type.STRING,
                         description="The PowerShell script to execute."
                     )
                 },
@@ -416,7 +419,7 @@ def _gemini_tool_declaration():
             ),
         ))
 
-    return google.genai.types.Tool(function_declarations=declarations) if declarations else None
+    return types.Tool(function_declarations=declarations) if declarations else None
 
 
 def _run_script(script: str, base_dir: str) -> str:
@@ -511,9 +514,8 @@ def _content_block_to_dict(block) -> dict:
 def _ensure_gemini_client():
     global _gemini_client
     if _gemini_client is None:
-        # from google import genai # Removed
         creds = _load_credentials()
-        _gemini_client = google.genai.Client(api_key=creds["gemini"]["api_key"])
+        _gemini_client = genai.Client(api_key=creds["gemini"]["api_key"])
 
 
 
@@ -530,7 +532,7 @@ def _get_gemini_history_list(chat):
 
 def _send_gemini(md_content: str, user_message: str, base_dir: str, file_items: list[dict] | None = None) -> str:
     global _gemini_chat, _gemini_cache, _gemini_cache_md_hash, _gemini_cache_created_at
-    # from google.genai import types # Removed
+
     try:
         _ensure_gemini_client(); mcp_client.configure(file_items or [], [base_dir])
         sys_instr = f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"
@@ -563,29 +565,29 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str, file_items:
                 _append_comms("OUT", "request", {"message": f"[CACHE TTL] Rebuilding cache (expired after {int(elapsed)}s)..."})
 
         if not _gemini_chat:
-            chat_config = google.genai.types.GenerateContentConfig(
+            chat_config = types.GenerateContentConfig(
                 system_instruction=sys_instr,
                 tools=tools_decl,
                 temperature=_temperature,
                 max_output_tokens=_max_tokens,
-                safety_settings=[google.genai.types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
+                safety_settings=[types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
             )
             try:
                 # Gemini requires 1024 (Flash) or 4096 (Pro) tokens to cache.
                 _gemini_cache = _gemini_client.caches.create(
                     model=_model,
-                    config=google.genai.types.CreateCachedContentConfig(
+                    config=types.CreateCachedContentConfig(
                         system_instruction=sys_instr,
                         tools=tools_decl,
                         ttl=f"{_GEMINI_CACHE_TTL}s",
                     )
                 )
                 _gemini_cache_created_at = time.time()
-                chat_config = google.genai.types.GenerateContentConfig(
+                chat_config = types.GenerateContentConfig(
                     cached_content=_gemini_cache.name,
                     temperature=_temperature,
                     max_output_tokens=_max_tokens,
-                    safety_settings=[google.genai.types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
+                    safety_settings=[types.SafetySetting(category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="BLOCK_ONLY_HIGH")]
                 )
                 _append_comms("OUT", "request", {"message": f"[CACHE CREATED] {_gemini_cache.name}"})
             except Exception as e:
@@ -857,9 +859,12 @@ def _trim_anthropic_history(system_blocks: list[dict], history: list[dict]):
 def _ensure_anthropic_client():
     global _anthropic_client
     if _anthropic_client is None:
-        import anthropic
         creds = _load_credentials()
-        _anthropic_client = anthropic.Anthropic(api_key=creds["anthropic"]["api_key"])
+        # Enable prompt caching beta
+        _anthropic_client = anthropic.Anthropic(
+            api_key=creds["anthropic"]["api_key"],
+            default_headers={"anthropic-beta": "prompt-caching-2024-07-31"}
+        )
 
 
 def _chunk_text(text: str, chunk_size: int) -> list[str]:
@@ -1187,9 +1192,27 @@ def get_history_bleed_stats() -> dict:
             "percentage": percentage,
         }
     elif _provider == "gemini":
-        # For Gemini, token estimation is complex and handled by the server.
-        # We don't have a reliable client-side estimate, so we return a
-        # "not implemented" state for now.
+        if _gemini_chat:
+            try:
+                _ensure_gemini_client()
+                history = _get_gemini_history_list(_gemini_chat)
+                if history:
+                    resp = _gemini_client.models.count_tokens(
+                        model=_model,
+                        contents=history
+                    )
+                    current_tokens = resp.total_tokens
+                    limit_tokens = _GEMINI_MAX_INPUT_TOKENS
+                    percentage = (current_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
+                    return {
+                        "provider": "gemini",
+                        "limit": limit_tokens,
+                        "current": current_tokens,
+                        "percentage": percentage,
+                    }
+            except Exception:
+                pass
+        
         return {
             "provider": "gemini",
             "limit": _GEMINI_MAX_INPUT_TOKENS,

conductor/tracks.md

@@ -9,7 +9,7 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 ---
 
-- [ ] **Track: Review project codebase, documentation related to project, and make sure agenti vendor apis are being used as properly stated by offical documentation from google for gemini and anthropic for claude.**
+- [x] **Track: Review project codebase, documentation related to project, and make sure agenti vendor apis are being used as properly stated by offical documentation from google for gemini and anthropic for claude.**
 *Link: [./tracks/api_vendor_alignment_20260223/](./tracks/api_vendor_alignment_20260223/)*
 
 ---

conductor/tracks/api_vendor_alignment_20260223/plan.md

@@ -1,56 +1,56 @@
 # Implementation Plan: API Usage Audit and Alignment
 
-## Phase 1: Research and Comprehensive Audit
+## Phase 1: Research and Comprehensive Audit [checkpoint: 5ec4283]
 Identify all points of interaction with AI SDKs and compare them with latest official documentation.
 
-- [ ] Task: List and categorize all AI SDK usage in the project.
-    - [ ] Search for all imports of `google.genai` and `anthropic`.
-    - [ ] Document specific functions and methods being called.
-- [ ] Task: Research latest official documentation for `google-genai` and `anthropic` Python SDKs.
-    - [ ] Verify latest patterns for Client initialization.
-    - [ ] Verify latest patterns for Context/Prompt caching.
-    - [ ] Verify latest patterns for Tool/Function calling.
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: Research and Comprehensive Audit' (Protocol in workflow.md)
+- [x] Task: List and categorize all AI SDK usage in the project.
+    - [x] Search for all imports of `google.genai` and `anthropic`.
+    - [x] Document specific functions and methods being called.
+- [x] Task: Research latest official documentation for `google-genai` and `anthropic` Python SDKs.
+    - [x] Verify latest patterns for Client initialization.
+    - [x] Verify latest patterns for Context/Prompt caching.
+    - [x] Verify latest patterns for Tool/Function calling.
+- [x] Task: Conductor - User Manual Verification 'Phase 1: Research and Comprehensive Audit' (Protocol in workflow.md)
 
-## Phase 2: Gemini (google-genai) Alignment
+## Phase 2: Gemini (google-genai) Alignment [checkpoint: 842bfc4]
 Align Gemini integration with documented best practices.
 
-- [ ] Task: Refactor Gemini Client and Chat initialization if needed.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Optimize Gemini Context Caching.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Align Gemini Tool Declaration and handling.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: Gemini (google-genai) Alignment' (Protocol in workflow.md)
+- [x] Task: Refactor Gemini Client and Chat initialization if needed.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Optimize Gemini Context Caching.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Align Gemini Tool Declaration and handling.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Conductor - User Manual Verification 'Phase 2: Gemini (google-genai) Alignment' (Protocol in workflow.md)
 
-## Phase 3: Anthropic Alignment
+## Phase 3: Anthropic Alignment [checkpoint: f0eb538]
 Align Anthropic integration with documented best practices.
 
-- [ ] Task: Refactor Anthropic Client and Message creation if needed.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Optimize Anthropic Prompt Caching (`cache_control`).
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Align Anthropic Tool Declaration and handling.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: Anthropic Alignment' (Protocol in workflow.md)
+- [x] Task: Refactor Anthropic Client and Message creation if needed.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Optimize Anthropic Prompt Caching (`cache_control`).
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Align Anthropic Tool Declaration and handling.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Conductor - User Manual Verification 'Phase 3: Anthropic Alignment' (Protocol in workflow.md)
 
-## Phase 4: History and Token Management
+## Phase 4: History and Token Management [checkpoint: 0f9f235]
 Ensure accurate token estimation and robust history handling.
 
-- [ ] Task: Review and align token estimation logic for both providers.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Audit message history truncation and context window management.
-    - [ ] Write Tests
-    - [ ] Implement Feature
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: History and Token Management' (Protocol in workflow.md)
+- [x] Task: Review and align token estimation logic for both providers.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Audit message history truncation and context window management.
+    - [x] Write Tests
+    - [x] Implement Feature
+- [x] Task: Conductor - User Manual Verification 'Phase 4: History and Token Management' (Protocol in workflow.md)
 
-## Phase 5: Final Validation and Cleanup
-- [ ] Task: Perform a full test run using `run_tests.py` to ensure 100% pass rate.
-- [ ] Task: Conductor - User Manual Verification 'Phase 5: Final Validation and Cleanup' (Protocol in workflow.md)
+## Phase 5: Final Validation and Cleanup [checkpoint: e9126b4]
+- [x] Task: Perform a full test run using `run_tests.py` to ensure 100% pass rate.
+- [x] Task: Conductor - User Manual Verification 'Phase 5: Final Validation and Cleanup' (Protocol in workflow.md)