Merge branch 'main' into bb/gui

agent/agent_init.py

@@ -901,7 +901,19 @@ def init_agent(
     hermes_home = get_hermes_home()
     agent.logs_dir = hermes_home / "sessions"
     agent.logs_dir.mkdir(parents=True, exist_ok=True)
-    agent.session_log_file = agent.logs_dir / f"session_{agent.session_id}.json"
+    # Per-session JSON snapshot writer (~/.hermes/sessions/session_{sid}.json)
+    # is opt-in via sessions.write_json_snapshots (default False).  state.db
+    # is canonical — the snapshot is only useful for external tooling that
+    # reads the JSON files directly.  See run_agent._save_session_log.
+    agent._session_json_enabled = False
+    try:
+        from hermes_cli.config import load_config as _load_sess_cfg
+        _sess_cfg = (_load_sess_cfg().get("sessions") or {})
+        agent._session_json_enabled = bool(_sess_cfg.get("write_json_snapshots", False))
+    except Exception:
+        pass
+    # logs_dir is retained unconditionally for request_dump_*.json (debug
+    # breadcrumb path written by agent_runtime_helpers.dump_api_request_debug).
     
     # Track conversation messages for session logging
     agent._session_messages: List[Dict[str, Any]] = []

agent/conversation_compression.py

@@ -387,8 +387,6 @@ def compress_context(
                 _SESSION_ID.set(agent.session_id)
             except Exception:
                 pass
-            # Update session_log_file to point to the new session's JSON file
-            agent.session_log_file = agent.logs_dir / f"session_{agent.session_id}.json"
             agent._session_db_created = False
             agent._session_db.create_session(
                 session_id=agent.session_id,

agent/conversation_loop.py

@@ -1454,7 +1454,6 @@ def run_conversation(
                                 }
                                 messages.append(continue_msg)
                                 agent._session_messages = messages
-                                agent._save_session_log(messages)
                                 restart_with_length_continuation = True
                                 break
 
@@ -3086,7 +3085,6 @@ def run_conversation(
                     if not agent.quiet_mode:
                         agent._vprint(f"{agent.log_prefix}↻ Codex response incomplete; continuing turn ({agent._codex_incomplete_retries}/3)")
                     agent._session_messages = messages
-                    agent._save_session_log(messages)
                     continue
 
                 agent._codex_incomplete_retries = 0
@@ -3411,7 +3409,6 @@ def run_conversation(
                 
                 # Save session log incrementally (so progress is visible even if interrupted)
                 agent._session_messages = messages
-                agent._save_session_log(messages)
                 
                 # Continue loop for next response
                 continue
@@ -3578,7 +3575,6 @@ def run_conversation(
                         interim_msg["_thinking_prefill"] = True
                         messages.append(interim_msg)
                         agent._session_messages = messages
-                        agent._save_session_log(messages)
                         continue
 
                     # ── Empty response retry ──────────────────────
@@ -3712,7 +3708,6 @@ def run_conversation(
                     }
                     messages.append(continue_msg)
                     agent._session_messages = messages
-                    agent._save_session_log(messages)
                     continue
 
                 codex_ack_continuations = 0

agent/transports/chat_completions.py

@@ -112,17 +112,31 @@ class ChatCompletionsTransport(ProviderTransport):
     def convert_messages(
         self, messages: list[dict[str, Any]], **kwargs
     ) -> list[dict[str, Any]]:
-        """Messages are already in OpenAI format — sanitize Codex leaks only.
+        """Messages are already in OpenAI format — strip internal fields
+        that strict chat-completions providers reject with HTTP 400/422.
 
-        Strips Codex Responses API fields (``codex_reasoning_items`` /
-        ``codex_message_items`` on the message, ``call_id``/``response_item_id``
-        on tool_calls) that strict chat-completions providers reject with 400/422.
+        Strips:
+
+        - Codex Responses API fields: ``codex_reasoning_items`` /
+          ``codex_message_items`` on the message, ``call_id`` /
+          ``response_item_id`` on ``tool_calls`` entries.
+        - ``tool_name`` on tool-result messages — written by
+          ``make_tool_result_message()`` for the SQLite FTS index, but not
+          part of the Chat Completions schema. Strict providers (Fireworks,
+          Moonshot/Kimi) reject any payload containing it with
+          ``Extra inputs are not permitted, field: 'messages[N].tool_name'``.
+          Permissive providers (OpenRouter, MiniMax) silently ignore the
+          field, which masked the bug for months.
         """
         needs_sanitize = False
         for msg in messages:
             if not isinstance(msg, dict):
                 continue
-            if "codex_reasoning_items" in msg or "codex_message_items" in msg:
+            if (
+                "codex_reasoning_items" in msg
+                or "codex_message_items" in msg
+                or "tool_name" in msg
+            ):
                 needs_sanitize = True
                 break
             tool_calls = msg.get("tool_calls")
@@ -145,6 +159,7 @@ class ChatCompletionsTransport(ProviderTransport):
                 continue
             msg.pop("codex_reasoning_items", None)
             msg.pop("codex_message_items", None)
+            msg.pop("tool_name", None)
             tool_calls = msg.get("tool_calls")
             if isinstance(tool_calls, list):
                 for tc in tool_calls: