Compare commits
2 Commits
burn/1143-
...
queue/1336
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0aa9bd541f | ||
|
|
bd78d71dfb |
21
agent/__init__.py
Normal file
21
agent/__init__.py
Normal file
@@ -0,0 +1,21 @@
|
||||
"""
|
||||
agent — Cross-session agent memory and lifecycle hooks.
|
||||
|
||||
Provides persistent memory for agents via MemPalace integration.
|
||||
Agents recall context at session start and write diary entries at session end.
|
||||
|
||||
Modules:
|
||||
memory.py — AgentMemory class (recall, remember, diary)
|
||||
memory_hooks.py — Session lifecycle hooks (drop-in integration)
|
||||
"""
|
||||
|
||||
from agent.memory import AgentMemory, MemoryContext, SessionTranscript, create_agent_memory
|
||||
from agent.memory_hooks import MemoryHooks
|
||||
|
||||
__all__ = [
|
||||
"AgentMemory",
|
||||
"MemoryContext",
|
||||
"MemoryHooks",
|
||||
"SessionTranscript",
|
||||
"create_agent_memory",
|
||||
]
|
||||
396
agent/memory.py
Normal file
396
agent/memory.py
Normal file
@@ -0,0 +1,396 @@
|
||||
"""
|
||||
agent.memory — Cross-session agent memory via MemPalace.
|
||||
|
||||
Gives agents persistent memory across sessions. On wake-up, agents
|
||||
recall relevant context from past sessions. On session end, they
|
||||
write a diary entry summarizing what happened.
|
||||
|
||||
Architecture:
|
||||
Session Start → memory.recall_context() → inject L0/L1 into prompt
|
||||
During Session → memory.remember() → store important facts
|
||||
Session End → memory.write_diary() → summarize session
|
||||
|
||||
All operations degrade gracefully — if MemPalace is unavailable,
|
||||
the agent continues without memory and logs a warning.
|
||||
|
||||
Usage:
|
||||
from agent.memory import AgentMemory
|
||||
|
||||
mem = AgentMemory(agent_name="bezalel", wing="wing_bezalel")
|
||||
|
||||
# Session start — load context
|
||||
context = mem.recall_context("What was I working on last time?")
|
||||
|
||||
# During session — store important decisions
|
||||
mem.remember("Switched CI runner from GitHub Actions to self-hosted", room="forge")
|
||||
|
||||
# Session end — write diary
|
||||
mem.write_diary("Fixed PR #1386, reconciled fleet registry locations")
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
logger = logging.getLogger("agent.memory")
|
||||
|
||||
|
||||
@dataclass
|
||||
class MemoryContext:
|
||||
"""Context loaded at session start from MemPalace."""
|
||||
relevant_memories: list[dict] = field(default_factory=list)
|
||||
recent_diaries: list[dict] = field(default_factory=list)
|
||||
facts: list[dict] = field(default_factory=list)
|
||||
loaded: bool = False
|
||||
error: Optional[str] = None
|
||||
|
||||
def to_prompt_block(self) -> str:
|
||||
"""Format context as a text block to inject into the agent prompt."""
|
||||
if not self.loaded:
|
||||
return ""
|
||||
|
||||
parts = []
|
||||
|
||||
if self.recent_diaries:
|
||||
parts.append("=== Recent Session Summaries ===")
|
||||
for d in self.recent_diaries[:3]:
|
||||
ts = d.get("timestamp", "")
|
||||
text = d.get("text", "")
|
||||
parts.append(f"[{ts}] {text[:500]}")
|
||||
|
||||
if self.facts:
|
||||
parts.append("\n=== Known Facts ===")
|
||||
for f in self.facts[:10]:
|
||||
text = f.get("text", "")
|
||||
parts.append(f"- {text[:200]}")
|
||||
|
||||
if self.relevant_memories:
|
||||
parts.append("\n=== Relevant Past Memories ===")
|
||||
for m in self.relevant_memories[:5]:
|
||||
text = m.get("text", "")
|
||||
score = m.get("score", 0)
|
||||
parts.append(f"[{score:.2f}] {text[:300]}")
|
||||
|
||||
if not parts:
|
||||
return ""
|
||||
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
@dataclass
|
||||
class SessionTranscript:
|
||||
"""A running log of the current session for diary writing."""
|
||||
agent_name: str
|
||||
wing: str
|
||||
started_at: str = field(
|
||||
default_factory=lambda: datetime.now(timezone.utc).isoformat()
|
||||
)
|
||||
entries: list[dict] = field(default_factory=list)
|
||||
|
||||
def add_user_turn(self, text: str):
|
||||
self.entries.append({
|
||||
"role": "user",
|
||||
"text": text[:2000],
|
||||
"ts": time.time(),
|
||||
})
|
||||
|
||||
def add_agent_turn(self, text: str):
|
||||
self.entries.append({
|
||||
"role": "agent",
|
||||
"text": text[:2000],
|
||||
"ts": time.time(),
|
||||
})
|
||||
|
||||
def add_tool_call(self, tool: str, args: str, result_summary: str):
|
||||
self.entries.append({
|
||||
"role": "tool",
|
||||
"tool": tool,
|
||||
"args": args[:500],
|
||||
"result": result_summary[:500],
|
||||
"ts": time.time(),
|
||||
})
|
||||
|
||||
def summary(self) -> str:
|
||||
"""Generate a compact transcript summary."""
|
||||
if not self.entries:
|
||||
return "Empty session."
|
||||
|
||||
turns = []
|
||||
for e in self.entries[-20:]: # last 20 entries
|
||||
role = e["role"]
|
||||
if role == "user":
|
||||
turns.append(f"USER: {e['text'][:200]}")
|
||||
elif role == "agent":
|
||||
turns.append(f"AGENT: {e['text'][:200]}")
|
||||
elif role == "tool":
|
||||
turns.append(f"TOOL({e.get('tool','')}): {e.get('result','')[:150]}")
|
||||
|
||||
return "\n".join(turns)
|
||||
|
||||
|
||||
class AgentMemory:
|
||||
"""
|
||||
Cross-session memory for an agent.
|
||||
|
||||
Wraps MemPalace with agent-specific conventions:
|
||||
- Each agent has a wing (e.g., "wing_bezalel")
|
||||
- Session summaries go in the "hermes" room
|
||||
- Important decisions go in room-specific closets
|
||||
- Facts go in the "nexus" room
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
agent_name: str,
|
||||
wing: Optional[str] = None,
|
||||
palace_path: Optional[Path] = None,
|
||||
):
|
||||
self.agent_name = agent_name
|
||||
self.wing = wing or f"wing_{agent_name}"
|
||||
self.palace_path = palace_path
|
||||
self._transcript: Optional[SessionTranscript] = None
|
||||
self._available: Optional[bool] = None
|
||||
|
||||
def _check_available(self) -> bool:
|
||||
"""Check if MemPalace is accessible."""
|
||||
if self._available is not None:
|
||||
return self._available
|
||||
|
||||
try:
|
||||
from nexus.mempalace.searcher import search_memories, add_memory, _get_client
|
||||
from nexus.mempalace.config import MEMPALACE_PATH
|
||||
|
||||
path = self.palace_path or MEMPALACE_PATH
|
||||
_get_client(path)
|
||||
self._available = True
|
||||
logger.info(f"MemPalace available at {path}")
|
||||
except Exception as e:
|
||||
self._available = False
|
||||
logger.warning(f"MemPalace unavailable: {e}")
|
||||
|
||||
return self._available
|
||||
|
||||
def recall_context(
|
||||
self,
|
||||
query: Optional[str] = None,
|
||||
n_results: int = 5,
|
||||
) -> MemoryContext:
|
||||
"""
|
||||
Load relevant context from past sessions.
|
||||
|
||||
Called at session start to inject L0/L1 memory into the prompt.
|
||||
|
||||
Args:
|
||||
query: What to search for. If None, loads recent diary entries.
|
||||
n_results: Max memories to recall.
|
||||
"""
|
||||
ctx = MemoryContext()
|
||||
|
||||
if not self._check_available():
|
||||
ctx.error = "MemPalace unavailable"
|
||||
return ctx
|
||||
|
||||
try:
|
||||
from nexus.mempalace.searcher import search_memories
|
||||
|
||||
# Load recent diary entries (session summaries)
|
||||
ctx.recent_diaries = [
|
||||
{"text": r.text, "score": r.score, "timestamp": r.metadata.get("timestamp", "")}
|
||||
for r in search_memories(
|
||||
"session summary",
|
||||
palace_path=self.palace_path,
|
||||
wing=self.wing,
|
||||
room="hermes",
|
||||
n_results=3,
|
||||
)
|
||||
]
|
||||
|
||||
# Load known facts
|
||||
ctx.facts = [
|
||||
{"text": r.text, "score": r.score}
|
||||
for r in search_memories(
|
||||
"important facts decisions",
|
||||
palace_path=self.palace_path,
|
||||
wing=self.wing,
|
||||
room="nexus",
|
||||
n_results=5,
|
||||
)
|
||||
]
|
||||
|
||||
# Search for relevant memories if query provided
|
||||
if query:
|
||||
ctx.relevant_memories = [
|
||||
{"text": r.text, "score": r.score, "room": r.room}
|
||||
for r in search_memories(
|
||||
query,
|
||||
palace_path=self.palace_path,
|
||||
wing=self.wing,
|
||||
n_results=n_results,
|
||||
)
|
||||
]
|
||||
|
||||
ctx.loaded = True
|
||||
|
||||
except Exception as e:
|
||||
ctx.error = str(e)
|
||||
logger.warning(f"Failed to recall context: {e}")
|
||||
|
||||
return ctx
|
||||
|
||||
def remember(
|
||||
self,
|
||||
text: str,
|
||||
room: str = "nexus",
|
||||
source_file: str = "",
|
||||
metadata: Optional[dict] = None,
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
Store a memory.
|
||||
|
||||
Args:
|
||||
text: The memory content.
|
||||
room: Target room (forge, hermes, nexus, issues, experiments).
|
||||
source_file: Optional source attribution.
|
||||
metadata: Extra metadata.
|
||||
|
||||
Returns:
|
||||
Document ID if stored, None if MemPalace unavailable.
|
||||
"""
|
||||
if not self._check_available():
|
||||
logger.warning("Cannot store memory — MemPalace unavailable")
|
||||
return None
|
||||
|
||||
try:
|
||||
from nexus.mempalace.searcher import add_memory
|
||||
|
||||
doc_id = add_memory(
|
||||
text=text,
|
||||
room=room,
|
||||
wing=self.wing,
|
||||
palace_path=self.palace_path,
|
||||
source_file=source_file,
|
||||
extra_metadata=metadata or {},
|
||||
)
|
||||
logger.debug(f"Stored memory in {room}: {text[:80]}...")
|
||||
return doc_id
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to store memory: {e}")
|
||||
return None
|
||||
|
||||
def write_diary(
|
||||
self,
|
||||
summary: Optional[str] = None,
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
Write a session diary entry to MemPalace.
|
||||
|
||||
Called at session end. If summary is None, auto-generates one
|
||||
from the session transcript.
|
||||
|
||||
Args:
|
||||
summary: Override summary text. If None, generates from transcript.
|
||||
|
||||
Returns:
|
||||
Document ID if stored, None if unavailable.
|
||||
"""
|
||||
if summary is None and self._transcript:
|
||||
summary = self._transcript.summary()
|
||||
|
||||
if not summary:
|
||||
return None
|
||||
|
||||
timestamp = datetime.now(timezone.utc).isoformat()
|
||||
diary_text = f"[{timestamp}] Session by {self.agent_name}:\n{summary}"
|
||||
|
||||
return self.remember(
|
||||
diary_text,
|
||||
room="hermes",
|
||||
metadata={
|
||||
"type": "session_diary",
|
||||
"agent": self.agent_name,
|
||||
"timestamp": timestamp,
|
||||
"entry_count": len(self._transcript.entries) if self._transcript else 0,
|
||||
},
|
||||
)
|
||||
|
||||
def start_session(self) -> SessionTranscript:
|
||||
"""
|
||||
Begin a new session transcript.
|
||||
|
||||
Returns the transcript object for recording turns.
|
||||
"""
|
||||
self._transcript = SessionTranscript(
|
||||
agent_name=self.agent_name,
|
||||
wing=self.wing,
|
||||
)
|
||||
logger.info(f"Session started for {self.agent_name}")
|
||||
return self._transcript
|
||||
|
||||
def end_session(self, diary_summary: Optional[str] = None) -> Optional[str]:
|
||||
"""
|
||||
End the current session, write diary, return diary doc ID.
|
||||
"""
|
||||
doc_id = self.write_diary(diary_summary)
|
||||
self._transcript = None
|
||||
logger.info(f"Session ended for {self.agent_name}")
|
||||
return doc_id
|
||||
|
||||
def search(
|
||||
self,
|
||||
query: str,
|
||||
room: Optional[str] = None,
|
||||
n_results: int = 5,
|
||||
) -> list[dict]:
|
||||
"""
|
||||
Search memories. Useful during a session for recall.
|
||||
|
||||
Returns list of {text, room, wing, score} dicts.
|
||||
"""
|
||||
if not self._check_available():
|
||||
return []
|
||||
|
||||
try:
|
||||
from nexus.mempalace.searcher import search_memories
|
||||
|
||||
results = search_memories(
|
||||
query,
|
||||
palace_path=self.palace_path,
|
||||
wing=self.wing,
|
||||
room=room,
|
||||
n_results=n_results,
|
||||
)
|
||||
return [
|
||||
{"text": r.text, "room": r.room, "wing": r.wing, "score": r.score}
|
||||
for r in results
|
||||
]
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Search failed: {e}")
|
||||
return []
|
||||
|
||||
|
||||
# --- Fleet-wide memory helpers ---
|
||||
|
||||
def create_agent_memory(
|
||||
agent_name: str,
|
||||
palace_path: Optional[Path] = None,
|
||||
) -> AgentMemory:
|
||||
"""
|
||||
Factory for creating AgentMemory with standard config.
|
||||
|
||||
Reads wing from MEMPALACE_WING env or defaults to wing_{agent_name}.
|
||||
"""
|
||||
wing = os.environ.get("MEMPALACE_WING", f"wing_{agent_name}")
|
||||
return AgentMemory(
|
||||
agent_name=agent_name,
|
||||
wing=wing,
|
||||
palace_path=palace_path,
|
||||
)
|
||||
183
agent/memory_hooks.py
Normal file
183
agent/memory_hooks.py
Normal file
@@ -0,0 +1,183 @@
|
||||
"""
|
||||
agent.memory_hooks — Session lifecycle hooks for agent memory.
|
||||
|
||||
Integrates AgentMemory into the agent session lifecycle:
|
||||
- on_session_start: Load context, inject into prompt
|
||||
- on_user_turn: Record user input
|
||||
- on_agent_turn: Record agent output
|
||||
- on_tool_call: Record tool usage
|
||||
- on_session_end: Write diary, clean up
|
||||
|
||||
These hooks are designed to be called from the Hermes harness or
|
||||
any agent framework. They're fire-and-forget — failures are logged
|
||||
but never crash the session.
|
||||
|
||||
Usage:
|
||||
from agent.memory_hooks import MemoryHooks
|
||||
|
||||
hooks = MemoryHooks(agent_name="bezalel")
|
||||
hooks.on_session_start() # loads context
|
||||
|
||||
# In your agent loop:
|
||||
hooks.on_user_turn("Check CI pipeline health")
|
||||
hooks.on_agent_turn("Running CI check...")
|
||||
hooks.on_tool_call("shell", "pytest tests/", "12 passed")
|
||||
|
||||
# End of session:
|
||||
hooks.on_session_end() # writes diary
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
from agent.memory import AgentMemory, MemoryContext, create_agent_memory
|
||||
|
||||
logger = logging.getLogger("agent.memory_hooks")
|
||||
|
||||
|
||||
class MemoryHooks:
|
||||
"""
|
||||
Drop-in session lifecycle hooks for agent memory.
|
||||
|
||||
Wraps AgentMemory with error boundaries — every hook catches
|
||||
exceptions and logs warnings so memory failures never crash
|
||||
the agent session.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
agent_name: str,
|
||||
palace_path=None,
|
||||
auto_diary: bool = True,
|
||||
):
|
||||
self.agent_name = agent_name
|
||||
self.auto_diary = auto_diary
|
||||
self._memory: Optional[AgentMemory] = None
|
||||
self._context: Optional[MemoryContext] = None
|
||||
self._active = False
|
||||
|
||||
@property
|
||||
def memory(self) -> AgentMemory:
|
||||
if self._memory is None:
|
||||
self._memory = create_agent_memory(
|
||||
self.agent_name,
|
||||
palace_path=getattr(self, '_palace_path', None),
|
||||
)
|
||||
return self._memory
|
||||
|
||||
def on_session_start(self, query: Optional[str] = None) -> str:
|
||||
"""
|
||||
Called at session start. Loads context from MemPalace.
|
||||
|
||||
Returns a prompt block to inject into the agent's context, or
|
||||
empty string if memory is unavailable.
|
||||
|
||||
Args:
|
||||
query: Optional recall query (e.g., "What was I working on?")
|
||||
"""
|
||||
try:
|
||||
self.memory.start_session()
|
||||
self._active = True
|
||||
|
||||
self._context = self.memory.recall_context(query=query)
|
||||
block = self._context.to_prompt_block()
|
||||
|
||||
if block:
|
||||
logger.info(
|
||||
f"Loaded {len(self._context.recent_diaries)} diaries, "
|
||||
f"{len(self._context.facts)} facts, "
|
||||
f"{len(self._context.relevant_memories)} relevant memories "
|
||||
f"for {self.agent_name}"
|
||||
)
|
||||
else:
|
||||
logger.info(f"No prior memory for {self.agent_name}")
|
||||
|
||||
return block
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Session start memory hook failed: {e}")
|
||||
return ""
|
||||
|
||||
def on_user_turn(self, text: str):
|
||||
"""Record a user message."""
|
||||
if not self._active:
|
||||
return
|
||||
try:
|
||||
if self.memory._transcript:
|
||||
self.memory._transcript.add_user_turn(text)
|
||||
except Exception as e:
|
||||
logger.debug(f"Failed to record user turn: {e}")
|
||||
|
||||
def on_agent_turn(self, text: str):
|
||||
"""Record an agent response."""
|
||||
if not self._active:
|
||||
return
|
||||
try:
|
||||
if self.memory._transcript:
|
||||
self.memory._transcript.add_agent_turn(text)
|
||||
except Exception as e:
|
||||
logger.debug(f"Failed to record agent turn: {e}")
|
||||
|
||||
def on_tool_call(self, tool: str, args: str, result_summary: str):
|
||||
"""Record a tool invocation."""
|
||||
if not self._active:
|
||||
return
|
||||
try:
|
||||
if self.memory._transcript:
|
||||
self.memory._transcript.add_tool_call(tool, args, result_summary)
|
||||
except Exception as e:
|
||||
logger.debug(f"Failed to record tool call: {e}")
|
||||
|
||||
def on_important_decision(self, text: str, room: str = "nexus"):
|
||||
"""
|
||||
Record an important decision or fact for long-term memory.
|
||||
|
||||
Use this when the agent makes a significant decision that
|
||||
should persist beyond the current session.
|
||||
"""
|
||||
try:
|
||||
self.memory.remember(text, room=room, metadata={"type": "decision"})
|
||||
logger.info(f"Remembered decision: {text[:80]}...")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to remember decision: {e}")
|
||||
|
||||
def on_session_end(self, summary: Optional[str] = None) -> Optional[str]:
|
||||
"""
|
||||
Called at session end. Writes diary entry.
|
||||
|
||||
Args:
|
||||
summary: Override diary text. If None, auto-generates.
|
||||
|
||||
Returns:
|
||||
Diary document ID, or None.
|
||||
"""
|
||||
if not self._active:
|
||||
return None
|
||||
|
||||
try:
|
||||
doc_id = self.memory.end_session(diary_summary=summary)
|
||||
self._active = False
|
||||
self._context = None
|
||||
return doc_id
|
||||
except Exception as e:
|
||||
logger.warning(f"Session end memory hook failed: {e}")
|
||||
self._active = False
|
||||
return None
|
||||
|
||||
def search(self, query: str, room: Optional[str] = None) -> list[dict]:
|
||||
"""
|
||||
Search memories during a session.
|
||||
|
||||
Returns list of {text, room, wing, score}.
|
||||
"""
|
||||
try:
|
||||
return self.memory.search(query, room=room)
|
||||
except Exception as e:
|
||||
logger.warning(f"Memory search failed: {e}")
|
||||
return []
|
||||
|
||||
@property
|
||||
def is_active(self) -> bool:
|
||||
return self._active
|
||||
32
app.js
32
app.js
@@ -995,8 +995,8 @@ function createBatcaveTerminal() {
|
||||
{ title: 'NEXUS COMMAND', color: NEXUS.colors.primary, rot: -0.4, x: -6, y: 3, lines: ['> STATUS: NOMINAL', '> UPTIME: 142.4h', '> HARNESS: STABLE', '> MODE: SOVEREIGN'] },
|
||||
{ title: 'DEV QUEUE', color: NEXUS.colors.gold, rot: -0.2, x: -3, y: 3, lines: ['> ISSUE #4: CORE', '> ISSUE #5: PORTAL', '> ISSUE #6: TERMINAL', '> ISSUE #7: TIMMY'] },
|
||||
{ title: 'METRICS', color: NEXUS.colors.secondary, rot: 0, x: 0, y: 3, lines: ['> CPU: 12% [||....]', '> MEM: 4.2GB', '> COMMITS: 842', '> ACTIVE LOOPS: 5'] },
|
||||
{ title: 'SOVEREIGNTY', color: NEXUS.colors.gold, rot: 0.2, x: 3, y: 3, lines: ['REPLIT: GRADE: A', 'PERPLEXITY: GRADE: A-', 'HERMES: GRADE: B+', 'KIMI: GRADE: B', 'GEMINI: GRADE: B+'] },
|
||||
{ title: 'AGENT STATUS', color: NEXUS.colors.primary, rot: 0.4, x: 6, y: 3, lines: ['> TIMMY: ● RUNNING', '> KIMI: ○ STANDBY', '> GEMINI: ○ STANDBY', '> PERPLEXITY: ○'] },
|
||||
{ title: 'SOVEREIGNTY', color: NEXUS.colors.gold, rot: 0.2, x: 3, y: 3, lines: ['REPLIT: GRADE: A', 'PERPLEXITY: GRADE: A-', 'HERMES: GRADE: B+', 'KIMI: GRADE: B', 'CLAUDE: GRADE: B+'] },
|
||||
{ title: 'AGENT STATUS', color: NEXUS.colors.primary, rot: 0.4, x: 6, y: 3, lines: ['> TIMMY: ● RUNNING', '> KIMI: ○ STANDBY', '> CLAUDE: ● ACTIVE', '> PERPLEXITY: ○'] },
|
||||
];
|
||||
|
||||
panelData.forEach(data => {
|
||||
@@ -1223,7 +1223,7 @@ function updateAgentStatus(issues) {
|
||||
const lines = [
|
||||
'> TIMMY: ● RUNNING',
|
||||
'> KIMI: ○ STANDBY',
|
||||
'> GEMINI: ○ STANDBY',
|
||||
'> CLAUDE: ● ACTIVE',
|
||||
`> PERPLEXITY: ${perplexityStatus}`
|
||||
];
|
||||
terminal.updatePanelText(lines);
|
||||
@@ -1323,7 +1323,7 @@ function createAgentPresences() {
|
||||
const agentData = [
|
||||
{ id: 'timmy', name: 'TIMMY', color: NEXUS.colors.primary, pos: { x: -4, z: -4 }, station: { x: -4, z: -4 } },
|
||||
{ id: 'kimi', name: 'KIMI', color: NEXUS.colors.secondary, pos: { x: 4, z: -4 }, station: { x: 4, z: -4 } },
|
||||
{ id: 'gemini', name: 'GEMINI', color: NEXUS.colors.gold, pos: { x: 0, z: -6 }, station: { x: 0, z: -6 } },
|
||||
{ id: 'claude', name: 'CLAUDE', color: NEXUS.colors.gold, pos: { x: 0, z: -6 }, station: { x: 0, z: -6 } },
|
||||
{ id: 'perplexity', name: 'PERPLEXITY', color: 0x4488ff, pos: { x: -6, z: -2 }, station: { x: -6, z: -2 } },
|
||||
];
|
||||
|
||||
@@ -2773,8 +2773,8 @@ function connectMemPalace() {
|
||||
}
|
||||
|
||||
// Initialize MCP server connection
|
||||
// Claude MCP bridge removed — Anthropic purged
|
||||
if (false && window.Claude) {
|
||||
if (window.Claude && window.Claude.mcp) {
|
||||
window.Claude.mcp.add('mempalace', {
|
||||
init: () => {
|
||||
return { status: 'active', version: '3.0.0' };
|
||||
},
|
||||
@@ -2951,7 +2951,7 @@ function addChatMessage(agent, text, shouldSave = true) {
|
||||
system: '[NEXUS]',
|
||||
error: '[ERROR]',
|
||||
kimi: '[KIMI]',
|
||||
gemini: '[GEMINI]',
|
||||
claude: '[CLAUDE]',
|
||||
perplexity: '[PERPLEXITY]'
|
||||
};
|
||||
|
||||
@@ -3562,7 +3562,7 @@ function onResize() {
|
||||
|
||||
// ═══ AGENT SIMULATION ═══
|
||||
function simulateAgentThought() {
|
||||
const agentIds = ['timmy', 'kimi', 'gemini', 'perplexity'];
|
||||
const agentIds = ['timmy', 'kimi', 'claude', 'perplexity'];
|
||||
const agentId = agentIds[Math.floor(Math.random() * agentIds.length)];
|
||||
const thoughts = {
|
||||
timmy: [
|
||||
@@ -3579,12 +3579,12 @@ function simulateAgentThought() {
|
||||
'Awaiting user prompt sequence.',
|
||||
'Neural weights adjusted.',
|
||||
],
|
||||
gemini: [
|
||||
'Multimodal reasoning engaged...',
|
||||
'Cross-referencing knowledge graph.',
|
||||
'Synthesizing across modalities...',
|
||||
'Pattern recognition complete.',
|
||||
'Gemini processing active.',
|
||||
claude: [
|
||||
'Reasoning through complex logic...',
|
||||
'Ethical guardrails verified.',
|
||||
'Refining thought architecture...',
|
||||
'Connecting disparate data points.',
|
||||
'Deep analysis in progress.',
|
||||
],
|
||||
perplexity: [
|
||||
'Searching global knowledge graph...',
|
||||
@@ -3873,8 +3873,8 @@ init().then(() => {
|
||||
}
|
||||
|
||||
// Initialize MCP server connection
|
||||
// Claude MCP bridge removed — Anthropic purged
|
||||
if (false && window.Claude) {
|
||||
if (window.Claude && window.Claude.mcp) {
|
||||
window.Claude.mcp.add('mempalace', {
|
||||
init: () => {
|
||||
return { status: 'active', version: '3.0.0' };
|
||||
},
|
||||
|
||||
258
bin/memory_mine.py
Normal file
258
bin/memory_mine.py
Normal file
@@ -0,0 +1,258 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
memory_mine.py — Mine session transcripts into MemPalace.
|
||||
|
||||
Reads Hermes session logs (JSONL format) and stores summaries
|
||||
in the palace. Supports batch mining, single-file processing,
|
||||
and live directory watching.
|
||||
|
||||
Usage:
|
||||
# Mine a single session file
|
||||
python3 bin/memory_mine.py ~/.hermes/sessions/2026-04-13.jsonl
|
||||
|
||||
# Mine all sessions from last 7 days
|
||||
python3 bin/memory_mine.py --days 7
|
||||
|
||||
# Mine a specific wing's sessions
|
||||
python3 bin/memory_mine.py --wing wing_bezalel --days 14
|
||||
|
||||
# Dry run — show what would be mined
|
||||
python3 bin/memory_mine.py --dry-run --days 7
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(message)s",
|
||||
datefmt="%Y-%m-%d %H:%M:%S",
|
||||
)
|
||||
logger = logging.getLogger("memory-mine")
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(REPO_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(REPO_ROOT))
|
||||
|
||||
|
||||
def parse_session_file(path: Path) -> list[dict]:
|
||||
"""
|
||||
Parse a JSONL session file into turns.
|
||||
|
||||
Each line is expected to be a JSON object with:
|
||||
- role: "user" | "assistant" | "system" | "tool"
|
||||
- content: text
|
||||
- timestamp: ISO string (optional)
|
||||
"""
|
||||
turns = []
|
||||
with open(path) as f:
|
||||
for i, line in enumerate(f):
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
turn = json.loads(line)
|
||||
turns.append(turn)
|
||||
except json.JSONDecodeError:
|
||||
logger.debug(f"Skipping malformed line {i+1} in {path}")
|
||||
return turns
|
||||
|
||||
|
||||
def summarize_session(turns: list[dict], agent_name: str = "unknown") -> str:
|
||||
"""
|
||||
Generate a compact summary of a session's turns.
|
||||
|
||||
Keeps user messages and key agent responses, strips noise.
|
||||
"""
|
||||
if not turns:
|
||||
return "Empty session."
|
||||
|
||||
user_msgs = []
|
||||
agent_msgs = []
|
||||
tool_calls = []
|
||||
|
||||
for turn in turns:
|
||||
role = turn.get("role", "")
|
||||
content = str(turn.get("content", ""))[:300]
|
||||
|
||||
if role == "user":
|
||||
user_msgs.append(content)
|
||||
elif role == "assistant":
|
||||
agent_msgs.append(content)
|
||||
elif role == "tool":
|
||||
tool_name = turn.get("name", turn.get("tool", "unknown"))
|
||||
tool_calls.append(f"{tool_name}: {content[:150]}")
|
||||
|
||||
parts = [f"Session by {agent_name}:"]
|
||||
|
||||
if user_msgs:
|
||||
parts.append(f"\nUser asked ({len(user_msgs)} messages):")
|
||||
for msg in user_msgs[:5]:
|
||||
parts.append(f" - {msg[:200]}")
|
||||
if len(user_msgs) > 5:
|
||||
parts.append(f" ... and {len(user_msgs) - 5} more")
|
||||
|
||||
if agent_msgs:
|
||||
parts.append(f"\nAgent responded ({len(agent_msgs)} messages):")
|
||||
for msg in agent_msgs[:3]:
|
||||
parts.append(f" - {msg[:200]}")
|
||||
|
||||
if tool_calls:
|
||||
parts.append(f"\nTools used ({len(tool_calls)} calls):")
|
||||
for tc in tool_calls[:5]:
|
||||
parts.append(f" - {tc}")
|
||||
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
def mine_session(
|
||||
path: Path,
|
||||
wing: str,
|
||||
palace_path: Optional[Path] = None,
|
||||
dry_run: bool = False,
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
Mine a single session file into MemPalace.
|
||||
|
||||
Returns the document ID if stored, None on failure or dry run.
|
||||
"""
|
||||
try:
|
||||
from agent.memory import AgentMemory
|
||||
except ImportError:
|
||||
logger.error("Cannot import agent.memory — is the repo in PYTHONPATH?")
|
||||
return None
|
||||
|
||||
turns = parse_session_file(path)
|
||||
if not turns:
|
||||
logger.debug(f"Empty session file: {path}")
|
||||
return None
|
||||
|
||||
agent_name = wing.replace("wing_", "")
|
||||
summary = summarize_session(turns, agent_name)
|
||||
|
||||
if dry_run:
|
||||
print(f"\n--- {path.name} ---")
|
||||
print(summary[:500])
|
||||
print(f"({len(turns)} turns)")
|
||||
return None
|
||||
|
||||
mem = AgentMemory(agent_name=agent_name, wing=wing, palace_path=palace_path)
|
||||
doc_id = mem.remember(
|
||||
summary,
|
||||
room="hermes",
|
||||
source_file=str(path),
|
||||
metadata={
|
||||
"type": "mined_session",
|
||||
"source": str(path),
|
||||
"turn_count": len(turns),
|
||||
"agent": agent_name,
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
},
|
||||
)
|
||||
|
||||
if doc_id:
|
||||
logger.info(f"Mined {path.name} → {doc_id} ({len(turns)} turns)")
|
||||
else:
|
||||
logger.warning(f"Failed to mine {path.name}")
|
||||
|
||||
return doc_id
|
||||
|
||||
|
||||
def find_session_files(
|
||||
sessions_dir: Path,
|
||||
days: int = 7,
|
||||
pattern: str = "*.jsonl",
|
||||
) -> list[Path]:
|
||||
"""
|
||||
Find session files from the last N days.
|
||||
"""
|
||||
cutoff = datetime.now() - timedelta(days=days)
|
||||
files = []
|
||||
|
||||
if not sessions_dir.exists():
|
||||
logger.warning(f"Sessions directory not found: {sessions_dir}")
|
||||
return files
|
||||
|
||||
for path in sorted(sessions_dir.glob(pattern)):
|
||||
# Use file modification time as proxy for session date
|
||||
mtime = datetime.fromtimestamp(path.stat().st_mtime)
|
||||
if mtime >= cutoff:
|
||||
files.append(path)
|
||||
|
||||
return files
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Mine session transcripts into MemPalace"
|
||||
)
|
||||
parser.add_argument(
|
||||
"files", nargs="*", help="Session files to mine (JSONL format)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--days", type=int, default=7,
|
||||
help="Mine sessions from last N days (default: 7)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--sessions-dir",
|
||||
default=str(Path.home() / ".hermes" / "sessions"),
|
||||
help="Directory containing session JSONL files"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--wing", default=None,
|
||||
help="Wing name (default: auto-detect from MEMPALACE_WING env or 'wing_timmy')"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--palace-path", default=None,
|
||||
help="Override palace path"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dry-run", action="store_true",
|
||||
help="Show what would be mined without storing"
|
||||
)
|
||||
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
wing = args.wing or os.environ.get("MEMPALACE_WING", "wing_timmy")
|
||||
palace_path = Path(args.palace_path) if args.palace_path else None
|
||||
|
||||
if args.files:
|
||||
files = [Path(f) for f in args.files]
|
||||
else:
|
||||
sessions_dir = Path(args.sessions_dir)
|
||||
files = find_session_files(sessions_dir, days=args.days)
|
||||
|
||||
if not files:
|
||||
logger.info("No session files found to mine.")
|
||||
return 0
|
||||
|
||||
logger.info(f"Mining {len(files)} session files (wing={wing})")
|
||||
|
||||
mined = 0
|
||||
failed = 0
|
||||
for path in files:
|
||||
result = mine_session(path, wing=wing, palace_path=palace_path, dry_run=args.dry_run)
|
||||
if result:
|
||||
mined += 1
|
||||
elif result is None and not args.dry_run:
|
||||
failed += 1
|
||||
|
||||
if args.dry_run:
|
||||
logger.info(f"Dry run complete — {len(files)} files would be mined")
|
||||
else:
|
||||
logger.info(f"Mining complete — {mined} mined, {failed} failed")
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -8,9 +8,12 @@
|
||||
# Primary: OpenRouter (recommended - access to multiple models)
|
||||
OPENROUTER_API_KEY=sk-or-v1-...
|
||||
DEEPDIVE_LLM_PROVIDER=openrouter
|
||||
DEEPDIVE_LLM_MODEL=google/gemini-2.5-pro
|
||||
DEEPDIVE_LLM_MODEL=anthropic/claude-sonnet-4
|
||||
|
||||
# Anthropic purged — Kimi/Gemini/Ollama only
|
||||
# Alternative: Anthropic direct
|
||||
# ANTHROPIC_API_KEY=sk-ant-...
|
||||
# DEEPDIVE_LLM_PROVIDER=anthropic
|
||||
# DEEPDIVE_LLM_MODEL=claude-3-5-sonnet-20241022
|
||||
|
||||
# Alternative: OpenAI
|
||||
# OPENAI_API_KEY=sk-...
|
||||
|
||||
@@ -169,7 +169,7 @@
|
||||
| P-04 | **Autonomous with Oversight** | Work via cron, report to father-messages. Escalate after 30 min. |
|
||||
| P-05 | **Musical Naming** | Names encode personality: Allegro=fast, Adagio=slow, Primus=first child. |
|
||||
| P-06 | **Immutable Inscription** | SOUL.md on-chain. Cannot be edited. The chain remembers everything. |
|
||||
| P-07 | **Fallback Chains** | Every provider: Kimi > Gemini > Ollama. Every operation: retry with backoff. |
|
||||
| P-07 | **Fallback Chains** | Every provider: Claude > Kimi > Ollama. Every operation: retry with backoff. |
|
||||
| P-08 | **Truth in Metrics** | No fakes. All numbers real, measured, verifiable. |
|
||||
|
||||
---
|
||||
|
||||
@@ -1,13 +1,9 @@
|
||||
{
|
||||
"version": 1,
|
||||
"generated": "2026-04-06",
|
||||
"refs": [
|
||||
"#836",
|
||||
"#204",
|
||||
"#195",
|
||||
"#196"
|
||||
],
|
||||
"refs": ["#836", "#204", "#195", "#196"],
|
||||
"description": "Canonical fleet routing table. Evaluated agents, routing verdicts, and dispatch rules for the Timmy Foundation task harness.",
|
||||
|
||||
"agents": [
|
||||
{
|
||||
"id": 27,
|
||||
@@ -50,14 +46,12 @@
|
||||
"location": "Bag End, The Shire (VPS)",
|
||||
"description": "Ollama on VPS. Speaks when spoken to. Prefers quiet. Not for delegated work.",
|
||||
"primary_role": "on-request-queries",
|
||||
"routing_verdict": "ROUTE TO: background monitoring, status checks, low-priority Q&A. Only on-request \u2014 do not delegate autonomously.",
|
||||
"routing_verdict": "ROUTE TO: background monitoring, status checks, low-priority Q&A. Only on-request — do not delegate autonomously.",
|
||||
"active": true,
|
||||
"do_not_route": false,
|
||||
"created": "2026-04-02",
|
||||
"repo_count": 1,
|
||||
"repos": [
|
||||
"bilbobagginshire/bilbo-adventures"
|
||||
]
|
||||
"repos": ["bilbobagginshire/bilbo-adventures"]
|
||||
},
|
||||
{
|
||||
"id": 24,
|
||||
@@ -66,12 +60,12 @@
|
||||
"model": "codex",
|
||||
"tier": "prepaid",
|
||||
"location": "The Harness",
|
||||
"description": "OpenClaw bridge. Protocol adapter layer \u2014 not a personality. Infrastructure, not a destination.",
|
||||
"description": "OpenClaw bridge. Protocol adapter layer — not a personality. Infrastructure, not a destination.",
|
||||
"primary_role": "protocol-bridge",
|
||||
"routing_verdict": "DO NOT ROUTE directly. claw-code is the bridge to external Codex agents, not an endpoint. Remove from routing cascade.",
|
||||
"active": true,
|
||||
"do_not_route": true,
|
||||
"do_not_route_reason": "Protocol layer, not an agent endpoint. See #836.",
|
||||
"do_not_route_reason": "Protocol layer, not an agent endpoint. See #836 evaluation.",
|
||||
"created": "2026-04-01",
|
||||
"repo_count": 0,
|
||||
"repos": []
|
||||
@@ -85,7 +79,7 @@
|
||||
"location": "Below the Surface",
|
||||
"description": "Infrastructure, deployments, bedrock services. Needs model assignment before activation.",
|
||||
"primary_role": "devops",
|
||||
"routing_verdict": "DO NOT ROUTE \u2014 no model assigned yet. Activate after Epic #196 (Local Model Fleet) assigns a model.",
|
||||
"routing_verdict": "DO NOT ROUTE — no model assigned yet. Activate after Epic #196 (Local Model Fleet) assigns a model.",
|
||||
"active": false,
|
||||
"do_not_route": true,
|
||||
"do_not_route_reason": "No model assigned. Blocked on Epic #196.",
|
||||
@@ -103,15 +97,13 @@
|
||||
"location": "The Archive",
|
||||
"description": "Original prototype. Museum piece. Preserved for historical reference only.",
|
||||
"primary_role": "inactive",
|
||||
"routing_verdict": "DO NOT ROUTE \u2014 retired from active duty. Preserved only.",
|
||||
"routing_verdict": "DO NOT ROUTE — retired from active duty. Preserved only.",
|
||||
"active": false,
|
||||
"do_not_route": true,
|
||||
"do_not_route_reason": "Retired prototype. Historical preservation only.",
|
||||
"created": "2026-03-31",
|
||||
"repo_count": 1,
|
||||
"repos": [
|
||||
"allegro-primus/first-steps"
|
||||
]
|
||||
"repos": ["allegro-primus/first-steps"]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
@@ -128,10 +120,7 @@
|
||||
"gap": "Agent description is empty in Gitea profile. Needs enrichment.",
|
||||
"created": "2026-03-14",
|
||||
"repo_count": 2,
|
||||
"repos": [
|
||||
"kimi/the-nexus-fork",
|
||||
"kimi/Timmy-time-dashboard"
|
||||
]
|
||||
"repos": ["kimi/the-nexus-fork", "kimi/Timmy-time-dashboard"]
|
||||
},
|
||||
{
|
||||
"id": 20,
|
||||
@@ -159,10 +148,10 @@
|
||||
"id": 19,
|
||||
"name": "ezra",
|
||||
"gitea_user": "ezra",
|
||||
"model": "google/gemini-2.5-pro",
|
||||
"model": "claude",
|
||||
"tier": "prepaid",
|
||||
"location": "Hermes VPS",
|
||||
"description": "Archivist. Sovereign-Hermes wizard. 9 repos owned \u2014 most in the fleet. Handles complex multi-file and cross-repo work.",
|
||||
"description": "Archivist. Claude-Hermes wizard. 9 repos owned — most in the fleet. Handles complex multi-file and cross-repo work.",
|
||||
"primary_role": "documentation",
|
||||
"routing_verdict": "ROUTE TO: docs, specs, architecture, complex multi-file work. Escalate here when breadth and precision both matter.",
|
||||
"active": true,
|
||||
@@ -187,7 +176,7 @@
|
||||
"gitea_user": "bezalel",
|
||||
"model": "groq",
|
||||
"tier": "free",
|
||||
"location": "TestBed VPS \u2014 The Forge",
|
||||
"location": "TestBed VPS — The Forge",
|
||||
"description": "Builder, debugger, testbed wizard. Groq-powered, free tier. Strong on PR review and CI.",
|
||||
"primary_role": "code-review",
|
||||
"routing_verdict": "ROUTE TO: PR review, test writing, debugging, CI fixes.",
|
||||
@@ -195,39 +184,29 @@
|
||||
"do_not_route": false,
|
||||
"created": "2026-03-29",
|
||||
"repo_count": 1,
|
||||
"repos": [
|
||||
"bezalel/forge-log"
|
||||
]
|
||||
"repos": ["bezalel/forge-log"]
|
||||
}
|
||||
],
|
||||
|
||||
"routing_cascade": {
|
||||
"description": "Cost-optimized routing cascade \u2014 cheapest capable agent first, escalate on complexity.",
|
||||
"description": "Cost-optimized routing cascade — cheapest capable agent first, escalate on complexity.",
|
||||
"tiers": [
|
||||
{
|
||||
"tier": 1,
|
||||
"label": "Free",
|
||||
"agents": [
|
||||
"fenrir",
|
||||
"bezalel",
|
||||
"carnice"
|
||||
],
|
||||
"agents": ["fenrir", "bezalel", "carnice"],
|
||||
"use_for": "Issue triage, code review, local code generation. Default lane for most tasks."
|
||||
},
|
||||
{
|
||||
"tier": 2,
|
||||
"label": "Cheap",
|
||||
"agents": [
|
||||
"kimi",
|
||||
"allegro"
|
||||
],
|
||||
"use_for": "Small scoped edits (kimi \u22643 files), triage decisions and routing (allegro)."
|
||||
"agents": ["kimi", "allegro"],
|
||||
"use_for": "Small scoped edits (kimi ≤3 files), triage decisions and routing (allegro)."
|
||||
},
|
||||
{
|
||||
"tier": 3,
|
||||
"label": "Premium / Escalate",
|
||||
"agents": [
|
||||
"ezra"
|
||||
],
|
||||
"agents": ["ezra"],
|
||||
"use_for": "Complex multi-file work, docs, architecture. Escalate only."
|
||||
}
|
||||
],
|
||||
@@ -238,48 +217,22 @@
|
||||
"allegro-primus: retired, do not route"
|
||||
]
|
||||
},
|
||||
|
||||
"task_type_map": {
|
||||
"issue-triage": [
|
||||
"fenrir",
|
||||
"allegro"
|
||||
],
|
||||
"code-generation": [
|
||||
"carnice",
|
||||
"ezra"
|
||||
],
|
||||
"code-review": [
|
||||
"bezalel"
|
||||
],
|
||||
"small-edit": [
|
||||
"kimi"
|
||||
],
|
||||
"debugging": [
|
||||
"bezalel",
|
||||
"carnice"
|
||||
],
|
||||
"documentation": [
|
||||
"ezra"
|
||||
],
|
||||
"architecture": [
|
||||
"ezra"
|
||||
],
|
||||
"ci-fixes": [
|
||||
"bezalel"
|
||||
],
|
||||
"pr-review": [
|
||||
"bezalel",
|
||||
"fenrir"
|
||||
],
|
||||
"triage-routing": [
|
||||
"allegro"
|
||||
],
|
||||
"devops": [
|
||||
"substratum"
|
||||
],
|
||||
"background-monitoring": [
|
||||
"bilbobagginshire"
|
||||
]
|
||||
"issue-triage": ["fenrir", "allegro"],
|
||||
"code-generation": ["carnice", "ezra"],
|
||||
"code-review": ["bezalel"],
|
||||
"small-edit": ["kimi"],
|
||||
"debugging": ["bezalel", "carnice"],
|
||||
"documentation": ["ezra"],
|
||||
"architecture": ["ezra"],
|
||||
"ci-fixes": ["bezalel"],
|
||||
"pr-review": ["bezalel", "fenrir"],
|
||||
"triage-routing": ["allegro"],
|
||||
"devops": ["substratum"],
|
||||
"background-monitoring": ["bilbobagginshire"]
|
||||
},
|
||||
|
||||
"gaps": [
|
||||
{
|
||||
"agent": "substratum",
|
||||
@@ -302,11 +255,12 @@
|
||||
"action": "Run wolf evaluation on active agents (#195) to replace vibes-based routing with data."
|
||||
}
|
||||
],
|
||||
|
||||
"next_actions": [
|
||||
"Assign model to substratum \u2014 Epic #196",
|
||||
"Run wolf evaluation on active agents \u2014 Issue #195",
|
||||
"Remove claw-code from routing cascade \u2014 it is infrastructure, not a destination",
|
||||
"Assign model to substratum — Epic #196",
|
||||
"Run wolf evaluation on active agents — Issue #195",
|
||||
"Remove claw-code from routing cascade — it is infrastructure, not a destination",
|
||||
"Enrich kimi's Gitea profile description",
|
||||
"Wire fleet-routing.json into workforce-manager.py \u2014 Epic #204"
|
||||
"Wire fleet-routing.json into workforce-manager.py — Epic #204"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,12 +1,3 @@
|
||||
# Hermes Trismegistus — DEPRECATED (Anthropic Purged)
|
||||
|
||||
> **This lane is inactive.** Anthropic has been removed from the fleet.
|
||||
> Hermes Trismegistus was Claude-native. She can be resurrected with
|
||||
> a sovereign provider (Kimi/Gemini/Ollama) if Alexander decides to
|
||||
> bring her back under a new identity.
|
||||
|
||||
---
|
||||
|
||||
# Hermes Trismegistus — Wizard Proposal
|
||||
|
||||
> **Status:** 🟡 DEFERRED
|
||||
@@ -22,15 +13,15 @@
|
||||
| Field | Value |
|
||||
|-------|-------|
|
||||
| **Name** | Hermes Trismegistus |
|
||||
| **Nature** | ~~Claude-native~~ DEPRECATED. Was "the daughter of Claude." Anthropic purged from fleet. |
|
||||
| **Purpose** | DEPRECATED. Was dedicated reasoning wizard. Can be resurrected under sovereign providers. |ns. |
|
||||
| **Nature** | Claude-native wizard. She knows she runs on Claude. She's "the daughter of Claude" and leans into that heritage. |
|
||||
| **Purpose** | Dedicated reasoning and architecture wizard. Only handles tasks where Claude's reasoning capability genuinely adds value — planning, novel problem-solving, complex architecture decisions. |
|
||||
| **Not** | A replacement for Timmy. Not competing for identity. Not doing monkey work. |
|
||||
|
||||
## Design Constraints
|
||||
|
||||
- ~~Free tier only from day one.~~ Anthropic purged — no active subscription.
|
||||
- **Free tier only from day one.** Alexander is not paying Anthropic beyond current subscription.
|
||||
- **Degrades gracefully.** Full capability when free tier is generous, reduced scope when constrained.
|
||||
- ~~Not locked to Claude.~~ Lane locked — Anthropic removed from fleet.
|
||||
- **Not locked to Claude.** If better free-tier providers emerge, she can route to them.
|
||||
- **Multi-provider capable.** Welcome to become multifaceted if team finds better options.
|
||||
|
||||
## Hardware
|
||||
@@ -53,13 +44,13 @@ All of the following must be true before implementation begins:
|
||||
- [ ] Deadman switch wired and proven
|
||||
- [ ] Config stable across fleet
|
||||
- [ ] Fleet proven reliable for 1+ week
|
||||
- [ ] DEPRECATED — Anthropic provider removed
|
||||
- [ ] Alexander provides a state-of-the-system KT to Claude for instantiation
|
||||
|
||||
## Acceptance Criteria
|
||||
|
||||
- [ ] Dedicated KT document written for Hermes instantiation
|
||||
- [ ] Hardware provisioned (shed laptop with power)
|
||||
- [ ] DEPRECATED — Anthropic provider removed
|
||||
- [ ] Hermes harness configured for Claude free tier
|
||||
- [ ] Lazerus registry entry with health endpoints
|
||||
- [ ] Fleet routing entry with role and routing verdict
|
||||
- [ ] SOUL.md inscription drafted and reviewed by Timmy
|
||||
@@ -69,7 +60,7 @@ All of the following must be true before implementation begins:
|
||||
## Proposed Lane
|
||||
|
||||
**Primary role:** Architecture reasoning
|
||||
**Routing verdict:** DO NOT ROUTE — lane deprecated. Anthropic purged from fleet.issue triage (use Fenrir), or operational tasks (use Bezalel).
|
||||
**Routing verdict:** ROUTE TO: complex architectural decisions, novel problem-solving, planning tasks that benefit from Claude's reasoning depth. Do NOT route to: code generation (use Timmy/Carnice), issue triage (use Fenrir), or operational tasks (use Bezalel).
|
||||
|
||||
## Dependencies
|
||||
|
||||
@@ -78,4 +69,4 @@ All of the following must be true before implementation begins:
|
||||
| Deadman switch | 🔴 Not done | Must be proven before unblocking |
|
||||
| Fleet stability | 🟡 In progress | 1+ week uptime needed |
|
||||
| Shed laptop power | 🔴 Not done | Alexander needs to wire power |
|
||||
| KT document | ⛔ DEPRECATED | Anthropic purged |
|
||||
| KT document | 🔴 Not drafted | Alexander provides to Claude at unblock time |
|
||||
|
||||
@@ -7,13 +7,13 @@
|
||||
|
||||
## Role
|
||||
|
||||
Dedicated reasoning and architecture wizard. DEPRECATED — Anthropic purged.
|
||||
Dedicated reasoning and architecture wizard. Claude-native.
|
||||
|
||||
## Routing
|
||||
|
||||
Route to Hermes Trismegistus when:
|
||||
- Task requires deep architectural reasoning
|
||||
- DEPRECATED: Anthropic provider removed from fleet
|
||||
- Novel problem-solving that benefits from Claude's reasoning depth
|
||||
- Planning and design decisions for the fleet
|
||||
- Complex multi-step analysis that goes beyond code generation
|
||||
|
||||
@@ -25,8 +25,8 @@ Do NOT route to Hermes for:
|
||||
|
||||
## Provider
|
||||
|
||||
- **Primary:** DEPRECATED — no active provider
|
||||
- **Fallback:** N/A — lane inactive
|
||||
- **Primary:** anthropic/claude (free tier)
|
||||
- **Fallback:** openrouter/free (Claude-class models)
|
||||
- **Degraded:** ollama/gemma4:12b (when free tier exhausted)
|
||||
|
||||
## Hardware
|
||||
|
||||
16
index.html
16
index.html
@@ -152,18 +152,18 @@
|
||||
|
||||
<!-- Top Right: Agent Log, Atlas & SOUL Toggle -->
|
||||
<div class="hud-top-right">
|
||||
<button id="atlas-toggle-btn" class="hud-icon-btn" title="World Directory">
|
||||
<button id="soul-toggle-btn" class="hud-icon-btn" title="Timmy's SOUL">
|
||||
<span class="hud-icon">✦</span>
|
||||
<span class="hud-btn-label">SOUL</span>
|
||||
<button id="mode-toggle-btn" class="hud-icon-btn mode-toggle" title="Toggle Mode">
|
||||
<span class="hud-icon">👁</span>
|
||||
<span class="hud-btn-label" id="mode-label">VISITOR</span>
|
||||
</button>
|
||||
<button id="atlas-toggle-btn" class="hud-icon-btn" title="Portal Atlas">
|
||||
<span class="hud-icon">🌐</span>
|
||||
<span class="hud-btn-label">WORLDS</span>
|
||||
</button>
|
||||
<button id="soul-toggle-btn" class="hud-icon-btn" title="Timmy's SOUL">
|
||||
<span class="hud-icon">✦</span>
|
||||
<span class="hud-btn-label">SOUL</span>
|
||||
</button>
|
||||
<button id="mode-toggle-btn" class="hud-icon-btn mode-toggle" title="Toggle Mode">
|
||||
<span class="hud-icon">👁</span>
|
||||
<span class="hud-btn-label" id="mode-label">VISITOR</span>
|
||||
</button>
|
||||
<div id="bannerlord-status" class="hud-status-item" title="Bannerlord Readiness">
|
||||
<span class="status-dot"></span>
|
||||
<span class="status-label">BANNERLORD</span>
|
||||
|
||||
@@ -152,7 +152,7 @@ curl http://localhost:4000/v1/models
|
||||
|
||||
If the endpoint is down, either:
|
||||
1. Start it: `llama-server -m model.gguf --port 4000 -ngl 999 --jinja`
|
||||
2. Or change `synthesis.llm_endpoint` in `config.yaml` to an alternative (e.g., OpenRouter, Kimi, Gemini).
|
||||
2. Or change `synthesis.llm_endpoint` in `config.yaml` to an alternative (e.g., OpenRouter, Kimi, Anthropic).
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
| arXiv cs.CL | http://export.arxiv.org/rss/cs.CL | RSS | Daily |
|
||||
| arXiv cs.LG | http://export.arxiv.org/rss/cs.LG | RSS | Daily |
|
||||
| OpenAI Blog | https://openai.com/blog/rss.xml | RSS | On-update |
|
||||
| Anthropic | https://www.anthropic.com/blog/rss.xml | RSS | On-update | (competitor monitoring, not provider) |
|
||||
| Anthropic | https://www.anthropic.com/blog/rss.xml | RSS | On-update |
|
||||
| DeepMind | https://deepmind.google/blog/rss.xml | RSS | On-update |
|
||||
| Import AI | https://importai.substack.com/feed | RSS | Daily |
|
||||
| TLDR AI | https://tldr.tech/ai/rss | RSS | Daily |
|
||||
|
||||
@@ -323,15 +323,15 @@
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Gemini — thinking -->
|
||||
<!-- Claude — thinking -->
|
||||
<div class="agent-row">
|
||||
<div class="agent-avatar thinking" style="color:#a08cff">C
|
||||
<div class="status-pip thinking"></div>
|
||||
</div>
|
||||
<div class="agent-info">
|
||||
<div class="agent-name">Gemini</div>
|
||||
<div class="agent-name">Claude</div>
|
||||
<div class="agent-location">
|
||||
<span class="loc-icon">⊕</span>Workshop — standby
|
||||
<span class="loc-icon">⊕</span>Workshop — claude/issue-749
|
||||
</div>
|
||||
<div class="agent-bark">"Building nexus/components/ ..."</div>
|
||||
</div>
|
||||
|
||||
@@ -349,7 +349,7 @@
|
||||
<div class="action-item">
|
||||
<div class="action-bullet bullet-normal">→</div>
|
||||
<div class="action-text">
|
||||
Gemini: Standby — no active tasks
|
||||
Claude: PR for #749 (Vibe Code components) awaiting review
|
||||
<span class="tag tag-pr">PR #52</span>
|
||||
</div>
|
||||
</div>
|
||||
@@ -378,7 +378,7 @@
|
||||
Hermes routed 214 messages, Archive wrote 88 new memories.
|
||||
Satflow hit a <strong>rate-limit wall</strong> at 03:14 UTC; queue is draining slowly.
|
||||
Gemini completed its sovereignty sweep; no critical findings.
|
||||
Gemini is on standby. No active sprints.
|
||||
Claude is mid-sprint on <strong>issue #749</strong> — component prototypes landing today.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
@@ -158,7 +158,7 @@
|
||||
}
|
||||
},
|
||||
"agents_present": [
|
||||
"gemini"
|
||||
"claude"
|
||||
],
|
||||
"interaction_ready": true
|
||||
},
|
||||
|
||||
@@ -8,8 +8,8 @@ TELEGRAM_BOT_TOKEN=your_bot_token_here
|
||||
TELEGRAM_CHANNEL_ID=-1001234567890
|
||||
|
||||
# Optional: LLM API for synthesis (defaults to local routing)
|
||||
# Anthropic purged — Kimi/Gemini/Ollama only
|
||||
# OPENROUTER_API_KEY=***
|
||||
# ANTHROPIC_API_KEY=sk-...
|
||||
# OPENROUTER_API_KEY=sk-...
|
||||
|
||||
# Optional: Custom paths
|
||||
# OUTPUT_DIR=./output
|
||||
|
||||
@@ -14,7 +14,7 @@ from typing import List, Optional
|
||||
@dataclass
|
||||
class BlogPost:
|
||||
title: str
|
||||
source: str # "openai", "anthropic", "deepmind", etc. — research sources, not providers
|
||||
source: str # "openai", "anthropic", "deepmind", etc.
|
||||
url: str
|
||||
published: datetime
|
||||
summary: str
|
||||
|
||||
@@ -24,7 +24,7 @@ Generate a structured briefing in this format:
|
||||
### 📊 Deep Dives (2-3 items)
|
||||
|
||||
#### [Most Relevant Item Title]
|
||||
**Source:** arXiv:XXXX.XXXXX / OpenAI Blog / DeepMind Research
|
||||
**Source:** arXiv:XXXX.XXXXX / OpenAI Blog / Anthropic Research
|
||||
**Why it matters:** 2-3 sentences on implications for agent architecture, tooling, or infrastructure
|
||||
**Key insight:** The core technical contribution or finding
|
||||
**Action for us:** Specific recommendation (e.g., "Evaluate for RAG pipeline", "Consider for RL environment")
|
||||
@@ -53,7 +53,7 @@ Brief synthesis of trends and how they affect:
|
||||
|
||||
## Context to Inject
|
||||
Hermes is an open-source AI agent framework with:
|
||||
- Multi-model support (Kimi, Gemini, local LLMs)
|
||||
- Multi-model support (Claude, GPT, local LLMs)
|
||||
- Rich tool ecosystem (terminal, file, web, browser, code execution)
|
||||
- Gateway architecture for messaging platforms (Telegram, Discord, Slack)
|
||||
- MCP (Model Context Protocol) integration
|
||||
|
||||
@@ -869,7 +869,7 @@ canvas#nexus-canvas {
|
||||
}
|
||||
.tag-timmy { color: var(--color-primary); }
|
||||
.tag-kimi { color: var(--color-secondary); }
|
||||
.tag-gemini { color: var(--color-gold); }
|
||||
.tag-claude { color: var(--color-gold); }
|
||||
.tag-perplexity { color: #4488ff; }
|
||||
.agent-log-text {
|
||||
color: var(--color-text-muted);
|
||||
@@ -1243,7 +1243,7 @@ canvas#nexus-canvas {
|
||||
font-weight: 700;
|
||||
}
|
||||
.chat-msg-kimi .chat-msg-prefix { color: var(--color-secondary); }
|
||||
.chat-msg-gemini .chat-msg-prefix { color: var(--color-gold); }
|
||||
.chat-msg-claude .chat-msg-prefix { color: var(--color-gold); }
|
||||
.chat-msg-perplexity .chat-msg-prefix { color: #4488ff; }
|
||||
|
||||
/* Tool Output Styling */
|
||||
|
||||
377
tests/test_agent_memory.py
Normal file
377
tests/test_agent_memory.py
Normal file
@@ -0,0 +1,377 @@
|
||||
"""
|
||||
Tests for agent memory — cross-session agent memory via MemPalace.
|
||||
|
||||
Tests the memory module, hooks, and session mining without requiring
|
||||
a live ChromaDB instance. Uses mocking for the MemPalace backend.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from agent.memory import (
|
||||
AgentMemory,
|
||||
MemoryContext,
|
||||
SessionTranscript,
|
||||
create_agent_memory,
|
||||
)
|
||||
from agent.memory_hooks import MemoryHooks
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# SessionTranscript tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestSessionTranscript:
|
||||
def test_create(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
assert t.agent_name == "test"
|
||||
assert t.wing == "wing_test"
|
||||
assert len(t.entries) == 0
|
||||
|
||||
def test_add_user_turn(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
t.add_user_turn("Hello")
|
||||
assert len(t.entries) == 1
|
||||
assert t.entries[0]["role"] == "user"
|
||||
assert t.entries[0]["text"] == "Hello"
|
||||
|
||||
def test_add_agent_turn(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
t.add_agent_turn("Response")
|
||||
assert t.entries[0]["role"] == "agent"
|
||||
|
||||
def test_add_tool_call(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
t.add_tool_call("shell", "ls", "file1 file2")
|
||||
assert t.entries[0]["role"] == "tool"
|
||||
assert t.entries[0]["tool"] == "shell"
|
||||
|
||||
def test_summary_empty(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
assert t.summary() == "Empty session."
|
||||
|
||||
def test_summary_with_entries(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
t.add_user_turn("Do something")
|
||||
t.add_agent_turn("Done")
|
||||
t.add_tool_call("shell", "ls", "ok")
|
||||
|
||||
summary = t.summary()
|
||||
assert "USER: Do something" in summary
|
||||
assert "AGENT: Done" in summary
|
||||
assert "TOOL(shell): ok" in summary
|
||||
|
||||
def test_text_truncation(self):
|
||||
t = SessionTranscript(agent_name="test", wing="wing_test")
|
||||
long_text = "x" * 5000
|
||||
t.add_user_turn(long_text)
|
||||
assert len(t.entries[0]["text"]) == 2000
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# MemoryContext tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestMemoryContext:
|
||||
def test_empty_context(self):
|
||||
ctx = MemoryContext()
|
||||
assert ctx.to_prompt_block() == ""
|
||||
|
||||
def test_unloaded_context(self):
|
||||
ctx = MemoryContext()
|
||||
ctx.loaded = False
|
||||
assert ctx.to_prompt_block() == ""
|
||||
|
||||
def test_loaded_with_data(self):
|
||||
ctx = MemoryContext()
|
||||
ctx.loaded = True
|
||||
ctx.recent_diaries = [
|
||||
{"text": "Fixed PR #1386", "timestamp": "2026-04-13T10:00:00Z"}
|
||||
]
|
||||
ctx.facts = [
|
||||
{"text": "Bezalel runs on VPS Beta", "score": 0.95}
|
||||
]
|
||||
ctx.relevant_memories = [
|
||||
{"text": "Changed CI runner", "score": 0.87}
|
||||
]
|
||||
|
||||
block = ctx.to_prompt_block()
|
||||
assert "Recent Session Summaries" in block
|
||||
assert "Fixed PR #1386" in block
|
||||
assert "Known Facts" in block
|
||||
assert "Bezalel runs on VPS Beta" in block
|
||||
assert "Relevant Past Memories" in block
|
||||
|
||||
def test_loaded_empty(self):
|
||||
ctx = MemoryContext()
|
||||
ctx.loaded = True
|
||||
# No data — should return empty string
|
||||
assert ctx.to_prompt_block() == ""
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# AgentMemory tests (with mocked MemPalace)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestAgentMemory:
|
||||
def test_create(self):
|
||||
mem = AgentMemory(agent_name="bezalel")
|
||||
assert mem.agent_name == "bezalel"
|
||||
assert mem.wing == "wing_bezalel"
|
||||
|
||||
def test_custom_wing(self):
|
||||
mem = AgentMemory(agent_name="bezalel", wing="custom_wing")
|
||||
assert mem.wing == "custom_wing"
|
||||
|
||||
def test_factory(self):
|
||||
mem = create_agent_memory("ezra")
|
||||
assert mem.agent_name == "ezra"
|
||||
assert mem.wing == "wing_ezra"
|
||||
|
||||
def test_unavailable_graceful(self):
|
||||
"""Test graceful degradation when MemPalace is unavailable."""
|
||||
mem = AgentMemory(agent_name="test")
|
||||
mem._available = False # Force unavailable
|
||||
|
||||
# Should not raise
|
||||
ctx = mem.recall_context("test query")
|
||||
assert ctx.loaded is False
|
||||
assert ctx.error == "MemPalace unavailable"
|
||||
|
||||
# remember returns None
|
||||
assert mem.remember("test") is None
|
||||
|
||||
# search returns empty
|
||||
assert mem.search("test") == []
|
||||
|
||||
def test_start_end_session(self):
|
||||
mem = AgentMemory(agent_name="test")
|
||||
mem._available = False
|
||||
|
||||
transcript = mem.start_session()
|
||||
assert isinstance(transcript, SessionTranscript)
|
||||
assert mem._transcript is not None
|
||||
|
||||
doc_id = mem.end_session()
|
||||
assert mem._transcript is None
|
||||
|
||||
def test_remember_graceful_when_unavailable(self):
|
||||
"""Test remember returns None when MemPalace is unavailable."""
|
||||
mem = AgentMemory(agent_name="test")
|
||||
mem._available = False
|
||||
|
||||
doc_id = mem.remember("some important fact")
|
||||
assert doc_id is None
|
||||
|
||||
def test_write_diary_from_transcript(self):
|
||||
mem = AgentMemory(agent_name="test")
|
||||
mem._available = False
|
||||
|
||||
transcript = mem.start_session()
|
||||
transcript.add_user_turn("Hello")
|
||||
transcript.add_agent_turn("Hi there")
|
||||
|
||||
# Write diary should handle unavailable gracefully
|
||||
doc_id = mem.write_diary()
|
||||
assert doc_id is None # MemPalace unavailable
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# MemoryHooks tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestMemoryHooks:
|
||||
def test_create(self):
|
||||
hooks = MemoryHooks(agent_name="bezalel")
|
||||
assert hooks.agent_name == "bezalel"
|
||||
assert hooks.is_active is False
|
||||
|
||||
def test_session_lifecycle(self):
|
||||
hooks = MemoryHooks(agent_name="test")
|
||||
|
||||
# Force memory unavailable
|
||||
hooks._memory = AgentMemory(agent_name="test")
|
||||
hooks._memory._available = False
|
||||
|
||||
# Start session
|
||||
block = hooks.on_session_start()
|
||||
assert hooks.is_active is True
|
||||
assert block == "" # No memory available
|
||||
|
||||
# Record turns
|
||||
hooks.on_user_turn("Hello")
|
||||
hooks.on_agent_turn("Hi")
|
||||
hooks.on_tool_call("shell", "ls", "ok")
|
||||
|
||||
# Record decision
|
||||
hooks.on_important_decision("Switched to self-hosted CI")
|
||||
|
||||
# End session
|
||||
doc_id = hooks.on_session_end()
|
||||
assert hooks.is_active is False
|
||||
|
||||
def test_hooks_before_session(self):
|
||||
"""Hooks before session start should be no-ops."""
|
||||
hooks = MemoryHooks(agent_name="test")
|
||||
hooks._memory = AgentMemory(agent_name="test")
|
||||
hooks._memory._available = False
|
||||
|
||||
# Should not raise
|
||||
hooks.on_user_turn("Hello")
|
||||
hooks.on_agent_turn("Response")
|
||||
|
||||
def test_hooks_after_session_end(self):
|
||||
"""Hooks after session end should be no-ops."""
|
||||
hooks = MemoryHooks(agent_name="test")
|
||||
hooks._memory = AgentMemory(agent_name="test")
|
||||
hooks._memory._available = False
|
||||
|
||||
hooks.on_session_start()
|
||||
hooks.on_session_end()
|
||||
|
||||
# Should not raise
|
||||
hooks.on_user_turn("Late message")
|
||||
doc_id = hooks.on_session_end()
|
||||
assert doc_id is None
|
||||
|
||||
def test_search_during_session(self):
|
||||
hooks = MemoryHooks(agent_name="test")
|
||||
hooks._memory = AgentMemory(agent_name="test")
|
||||
hooks._memory._available = False
|
||||
|
||||
results = hooks.search("some query")
|
||||
assert results == []
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Session mining tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestSessionMining:
|
||||
def test_parse_session_file(self):
|
||||
from bin.memory_mine import parse_session_file
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as f:
|
||||
f.write('{"role": "user", "content": "Hello"}\n')
|
||||
f.write('{"role": "assistant", "content": "Hi there"}\n')
|
||||
f.write('{"role": "tool", "name": "shell", "content": "ls output"}\n')
|
||||
f.write("\n") # blank line
|
||||
f.write("not json\n") # malformed
|
||||
path = Path(f.name)
|
||||
|
||||
turns = parse_session_file(path)
|
||||
assert len(turns) == 3
|
||||
assert turns[0]["role"] == "user"
|
||||
assert turns[1]["role"] == "assistant"
|
||||
assert turns[2]["role"] == "tool"
|
||||
path.unlink()
|
||||
|
||||
def test_summarize_session(self):
|
||||
from bin.memory_mine import summarize_session
|
||||
|
||||
turns = [
|
||||
{"role": "user", "content": "Check CI"},
|
||||
{"role": "assistant", "content": "Running CI check..."},
|
||||
{"role": "tool", "name": "shell", "content": "5 tests passed"},
|
||||
{"role": "assistant", "content": "CI is healthy"},
|
||||
]
|
||||
|
||||
summary = summarize_session(turns, "bezalel")
|
||||
assert "bezalel" in summary
|
||||
assert "Check CI" in summary
|
||||
assert "shell" in summary
|
||||
|
||||
def test_summarize_empty(self):
|
||||
from bin.memory_mine import summarize_session
|
||||
|
||||
assert summarize_session([], "test") == "Empty session."
|
||||
|
||||
def test_find_session_files(self, tmp_path):
|
||||
from bin.memory_mine import find_session_files
|
||||
|
||||
# Create some test files
|
||||
(tmp_path / "session1.jsonl").write_text("{}\n")
|
||||
(tmp_path / "session2.jsonl").write_text("{}\n")
|
||||
(tmp_path / "notes.txt").write_text("not a session")
|
||||
|
||||
files = find_session_files(tmp_path, days=365)
|
||||
assert len(files) == 2
|
||||
assert all(f.suffix == ".jsonl" for f in files)
|
||||
|
||||
def test_find_session_files_missing_dir(self):
|
||||
from bin.memory_mine import find_session_files
|
||||
|
||||
files = find_session_files(Path("/nonexistent/path"), days=7)
|
||||
assert files == []
|
||||
|
||||
def test_mine_session_dry_run(self, tmp_path):
|
||||
from bin.memory_mine import mine_session
|
||||
|
||||
session_file = tmp_path / "test.jsonl"
|
||||
session_file.write_text(
|
||||
'{"role": "user", "content": "Hello"}\n'
|
||||
'{"role": "assistant", "content": "Hi"}\n'
|
||||
)
|
||||
|
||||
result = mine_session(session_file, wing="wing_test", dry_run=True)
|
||||
assert result is None # dry run doesn't store
|
||||
|
||||
def test_mine_session_empty_file(self, tmp_path):
|
||||
from bin.memory_mine import mine_session
|
||||
|
||||
session_file = tmp_path / "empty.jsonl"
|
||||
session_file.write_text("")
|
||||
|
||||
result = mine_session(session_file, wing="wing_test")
|
||||
assert result is None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Integration test — full lifecycle
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestFullLifecycle:
|
||||
"""Test the full session lifecycle without a real MemPalace backend."""
|
||||
|
||||
def test_full_session_flow(self):
|
||||
hooks = MemoryHooks(agent_name="bezalel")
|
||||
|
||||
# Force memory unavailable
|
||||
hooks._memory = AgentMemory(agent_name="bezalel")
|
||||
hooks._memory._available = False
|
||||
|
||||
# 1. Session start
|
||||
context_block = hooks.on_session_start("What CI issues do I have?")
|
||||
assert isinstance(context_block, str)
|
||||
|
||||
# 2. User asks question
|
||||
hooks.on_user_turn("Check CI pipeline health")
|
||||
|
||||
# 3. Agent uses tool
|
||||
hooks.on_tool_call("shell", "pytest tests/", "12 passed")
|
||||
|
||||
# 4. Agent responds
|
||||
hooks.on_agent_turn("CI pipeline is healthy. All 12 tests passing.")
|
||||
|
||||
# 5. Important decision
|
||||
hooks.on_important_decision("Decided to keep current CI runner", room="forge")
|
||||
|
||||
# 6. More interaction
|
||||
hooks.on_user_turn("Good, check memory integration next")
|
||||
hooks.on_agent_turn("Will test agent.memory module")
|
||||
|
||||
# 7. Session end
|
||||
doc_id = hooks.on_session_end()
|
||||
assert hooks.is_active is False
|
||||
@@ -165,7 +165,7 @@
|
||||
"goal": "observe",
|
||||
"memory": []
|
||||
},
|
||||
"Gemini": {
|
||||
"Claude": {
|
||||
"personality": {
|
||||
"Threshold": 0.25,
|
||||
"Tower": 0.25,
|
||||
|
||||
Reference in New Issue
Block a user