fix(honcho): bug-fix consolidation — 7 upstream PRs, preserved authorship

agent/memory_manager.py

@@ -63,15 +63,124 @@ def sanitize_context(text: str) -> str:
     return text
 
 
-def build_memory_context_block(raw_context: str) -> str:
-    """Wrap prefetched memory in a fenced block with system note.
-
-    The fence prevents the model from treating recalled context as user
-    discourse.  Injected at API-call time only — never persisted.
+class StreamingContextScrubber:
+    """Stateful scrubber for streaming text that may contain split memory-context spans.
+
+    The one-shot ``sanitize_context`` regex cannot survive chunk boundaries:
+    a ``<memory-context>`` opened in one delta and closed in a later delta
+    leaks its payload to the UI because the non-greedy block regex needs
+    both tags in one string.  This scrubber runs a small state machine
+    across deltas, holding back partial-tag tails and discarding
+    everything inside a span (including the system-note line).
+
+    Usage::
+
+        scrubber = StreamingContextScrubber()
+        for delta in stream:
+            visible = scrubber.feed(delta)
+            if visible:
+                emit(visible)
+        trailing = scrubber.flush()  # at end of stream
+        if trailing:
+            emit(trailing)
+
+    The scrubber is re-entrant per agent instance.  Callers building new
+    top-level responses (new turn) should create a fresh scrubber or call
+    ``reset()``.
     """
+
+    _OPEN_TAG = "<memory-context>"
+    _CLOSE_TAG = "</memory-context>"
+
+    def __init__(self) -> None:
+        self._in_span: bool = False
+        self._buf: str = ""
+
+    def reset(self) -> None:
+        self._in_span = False
+        self._buf = ""
+
+    def feed(self, text: str) -> str:
+        """Return the visible portion of ``text`` after scrubbing.
+
+        Any trailing fragment that could be the start of an open/close tag
+        is held back in the internal buffer and surfaced on the next
+        ``feed()`` call or discarded/emitted by ``flush()``.
+        """
+        if not text:
+            return ""
+        buf = self._buf + text
+        self._buf = ""
+        out: list[str] = []
+
+        while buf:
+            if self._in_span:
+                idx = buf.lower().find(self._CLOSE_TAG)
+                if idx == -1:
+                    # Hold back a potential partial close tag; drop the rest
+                    held = self._max_partial_suffix(buf, self._CLOSE_TAG)
+                    self._buf = buf[-held:] if held else ""
+                    return "".join(out)
+                # Found close — skip span content + tag, continue
+                buf = buf[idx + len(self._CLOSE_TAG):]
+                self._in_span = False
+            else:
+                idx = buf.lower().find(self._OPEN_TAG)
+                if idx == -1:
+                    # No open tag — hold back a potential partial open tag
+                    held = self._max_partial_suffix(buf, self._OPEN_TAG)
+                    if held:
+                        out.append(buf[:-held])
+                        self._buf = buf[-held:]
+                    else:
+                        out.append(buf)
+                    return "".join(out)
+                # Emit text before the tag, enter span
+                if idx > 0:
+                    out.append(buf[:idx])
+                buf = buf[idx + len(self._OPEN_TAG):]
+                self._in_span = True
+
+        return "".join(out)
+
+    def flush(self) -> str:
+        """Emit any held-back buffer at end-of-stream.
+
+        If we're still inside an unterminated span the remaining content is
+        discarded (safer: leaking partial memory context is worse than a
+        truncated answer).  Otherwise the held-back partial-tag tail is
+        emitted verbatim (it turned out not to be a real tag).
+        """
+        if self._in_span:
+            self._buf = ""
+            self._in_span = False
+            return ""
+        tail = self._buf
+        self._buf = ""
+        return tail
+
+    @staticmethod
+    def _max_partial_suffix(buf: str, tag: str) -> int:
+        """Return the length of the longest buf-suffix that is a tag-prefix.
+
+        Case-insensitive.  Returns 0 if no suffix could start the tag.
+        """
+        tag_lower = tag.lower()
+        buf_lower = buf.lower()
+        max_check = min(len(buf_lower), len(tag_lower) - 1)
+        for i in range(max_check, 0, -1):
+            if tag_lower.startswith(buf_lower[-i:]):
+                return i
+        return 0
+
+
+def build_memory_context_block(raw_context: str) -> str:
+    """Wrap prefetched memory in a fenced block with system note."""
     if not raw_context or not raw_context.strip():
         return ""
     clean = sanitize_context(raw_context)
+    if clean != raw_context:
+        logger.warning("memory provider returned pre-wrapped context; stripped")
     return (
         "<memory-context>\n"
         "[System note: The following is recalled memory context, "

gateway/run.py

@@ -8483,6 +8483,7 @@ async def _enrich_message_with_vision(
             The enriched message string with vision descriptions prepended.
         """
         from tools.vision_tools import vision_analyze_tool
+        from agent.memory_manager import sanitize_context
 
         analysis_prompt = (
             "Describe everything visible in this image in thorough detail. "
@@ -8501,6 +8502,7 @@ async def _enrich_message_with_vision(
                 result = json.loads(result_json)
                 if result.get("success"):
                     description = result.get("analysis", "")
+                    description = sanitize_context(description)
                     enriched_parts.append(
                         f"[The user sent an image~ Here's what I can see:\n{description}]\n"
                         f"[If you need a closer look, use vision_analyze with "

hermes_state.py

@@ -22,6 +22,8 @@
 import threading
 import time
 from pathlib import Path
+
+from agent.memory_manager import sanitize_context
 from hermes_constants import get_hermes_home
 from typing import Any, Callable, Dict, List, Optional, TypeVar
 
@@ -1155,7 +1157,10 @@ def get_messages_as_conversation(
 
         messages = []
         for row in rows:
-            msg = {"role": row["role"], "content": row["content"]}
+            content = row["content"]
+            if row["role"] in {"user", "assistant"} and isinstance(content, str):
+                content = sanitize_context(content).strip()
+            msg = {"role": row["role"], "content": content}
             if row["tool_call_id"]:
                 msg["tool_call_id"] = row["tool_call_id"]
             if row["tool_name"]:

plugins/memory/honcho/__init__.py

@@ -22,6 +22,7 @@
 import time
 from typing import Any, Dict, List, Optional
 
+from agent.memory_manager import sanitize_context
 from agent.memory_provider import MemoryProvider
 from tools.registry import tool_error
 
@@ -37,7 +38,10 @@
     "description": (
         "Retrieve or update a peer card from Honcho — a curated list of key facts "
         "about that peer (name, role, preferences, communication style, patterns). "
-        "Pass `card` to update; omit `card` to read."
+        "Pass `card` to update; omit `card` to read.  If the card is empty, the "
+        "result includes a `hint` field explaining why (observation disabled, "
+        "fresh peer, dialectic layer still warming up, etc.) — this is NOT an "
+        "error.  Peer cards accumulate over time from observed conversation."
     ),
     "parameters": {
         "type": "object",
@@ -1056,6 +1060,63 @@ def _chunk_message(content: str, limit: int) -> list[str]:
 
         return chunks
 
+    def _empty_profile_hint(self, peer: str) -> Dict[str, Any]:
+        """Build a diagnostic hint when honcho_profile returns an empty card.
+
+        A literal "No profile facts available yet." tells the model nothing
+        about WHY.  The model then often surfaces it to the user as a cryptic
+        error.  This hint enumerates the likely causes so the model can
+        explain the situation (or retry with a different peer).
+
+        Ordered by likelihood for a typical deployment:
+          1. Observation is disabled for this peer
+          2. Card hasn't accumulated yet (fresh peer, not enough dialectic
+             cycles — dialectic cadence runs every N turns)
+          3. Self-hosted Honcho backend doesn't support peer cards
+             (honcho-ai server < 3.x)
+        """
+        cfg = self._config
+        reasons: List[str] = []
+
+        if cfg is not None:
+            if peer == "user":
+                observe_me = bool(getattr(cfg, "user_observe_me", True))
+                observe_others = bool(getattr(cfg, "user_observe_others", True))
+            else:
+                observe_me = bool(getattr(cfg, "ai_observe_me", True))
+                observe_others = bool(getattr(cfg, "ai_observe_others", True))
+            if not (observe_me or observe_others):
+                reasons.append(
+                    f"observation is disabled for peer '{peer}' "
+                    f"(user_observe_me/ai_observe_me in config)"
+                )
+
+        cadence = getattr(self, "_dialectic_cadence", 1)
+        turn = getattr(self, "_turn_count", 0)
+        if turn < max(2, cadence):
+            reasons.append(
+                f"this session has only {turn} turn(s); peer cards accumulate "
+                f"as the dialectic layer reasons over conversation history "
+                f"(cadence every {cadence} turn(s))"
+            )
+
+        if not reasons:
+            reasons.append(
+                "peer card has no facts yet — Honcho's dialectic layer builds "
+                "this over time from observed turns; self-hosted Honcho < 3.x "
+                "does not support peer cards at all"
+            )
+
+        return {
+            "result": "No profile facts available yet.",
+            "hint": (
+                "This is not an error.  "
+                + "; ".join(reasons)
+                + ".  Try honcho_reasoning for a synthesized answer, or "
+                "honcho_search to query raw conversation excerpts."
+            ),
+        }
+
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         """Record the conversation turn in Honcho (non-blocking).
 
@@ -1068,13 +1129,15 @@ def sync_turn(self, user_content: str, assistant_content: str, *, session_id: st
             return
 
         msg_limit = self._config.message_max_chars if self._config else 25000
+        clean_user_content = sanitize_context(user_content or "").strip()
+        clean_assistant_content = sanitize_context(assistant_content or "").strip()
 
         def _sync():
             try:
                 session = self._manager.get_or_create(self._session_key)
-                for chunk in self._chunk_message(user_content, msg_limit):
+                for chunk in self._chunk_message(clean_user_content, msg_limit):
                     session.add_message("user", chunk)
-                for chunk in self._chunk_message(assistant_content, msg_limit):
+                for chunk in self._chunk_message(clean_assistant_content, msg_limit):
                     session.add_message("assistant", chunk)
                 self._manager._flush_session(session)
             except Exception as e:
@@ -1087,8 +1150,20 @@ def _sync():
         )
         self._sync_thread.start()
 
-    def on_memory_write(self, action: str, target: str, content: str) -> None:
-        """Mirror built-in user profile writes as Honcho conclusions."""
+    def on_memory_write(
+        self,
+        action: str,
+        target: str,
+        content: str,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        """Mirror built-in user profile writes as Honcho conclusions.
+
+        ``metadata`` is accepted for compatibility with the write-origin
+        work landed in main (commit 6a957a74); it's not yet threaded into
+        the Honcho conclusion payload.  Left as a follow-up so this PR
+        stays focused on the 7-PR consolidation and its review follow-ups.
+        """
         if action != "add" or target != "user" or not content:
             return
         if self._cron_skipped:
@@ -1154,7 +1229,7 @@ def handle_tool_call(self, tool_name: str, args: dict, **kwargs) -> str:
                     return json.dumps({"result": f"Peer card updated ({len(result)} facts).", "card": result})
                 card = self._manager.get_peer_card(self._session_key, peer=peer)
                 if not card:
-                    return json.dumps({"result": "No profile facts available yet."})
+                    return json.dumps(self._empty_profile_hint(peer))
                 return json.dumps({"result": card})
 
             elif tool_name == "honcho_search":

plugins/memory/honcho/cli.py

@@ -273,9 +273,38 @@ def _write_config(cfg: dict, path: Path | None = None) -> None:
 
 
 def _resolve_api_key(cfg: dict) -> str:
-    """Resolve API key with host -> root -> env fallback."""
+    """Resolve API key with host -> root -> env fallback.
+
+    For self-hosted instances configured with ``baseUrl`` instead of an API
+    key, returns ``"local"`` so that credential guards throughout the CLI
+    don't reject a valid configuration.  The ``baseUrl`` is scheme-validated
+    (http/https only) so that a typo like ``baseUrl: true`` can't silently
+    pass the guard.  Schemeless strings that look like host:port (legacy
+    config shapes, e.g. ``localhost:8000``) still pass — the Honcho SDK
+    will reject them itself with a clearer error than ours.
+    """
     host_key = ((cfg.get("hosts") or {}).get(_host_key()) or {}).get("apiKey")
-    return host_key or cfg.get("apiKey", "") or os.environ.get("HONCHO_API_KEY", "")
+    key = host_key or cfg.get("apiKey", "") or os.environ.get("HONCHO_API_KEY", "")
+    if not key:
+        base_url = cfg.get("baseUrl") or cfg.get("base_url") or os.environ.get("HONCHO_BASE_URL", "")
+        base_url = (base_url or "").strip()
+        if base_url:
+            from urllib.parse import urlparse
+            try:
+                parsed = urlparse(base_url)
+            except (TypeError, ValueError):
+                parsed = None
+            if parsed and parsed.scheme in ("http", "https") and parsed.netloc:
+                return "local"
+            # Schemeless but looks like a host (contains '.' or ':' and isn't
+            # a boolean literal): let it through so legacy configs don't
+            # regress into "no API key configured" when they previously worked.
+            lowered = base_url.lower()
+            if lowered not in ("true", "false", "none", "null") and any(
+                c in base_url for c in ".:"
+            ) and not base_url.isdigit():
+                return "local"
+    return key
 
 
 def _prompt(label: str, default: str | None = None, secret: bool = False) -> str: