Files
odysseus/src/agent_tools.py

141 lines
5.1 KiB
Python
Raw Normal View History

2026-05-31 23:58:26 +09:00
"""
agent_tools.py — Facade module.
Re-exports tool parsing, schemas, execution, and implementations
for backward compatibility. All importers continue to work unchanged.
Sub-modules:
- tool_parsing.py: regex patterns, parse/strip functions
- tool_schemas.py: FUNCTION_TOOL_SCHEMAS, function_call_to_tool_block
- tool_execution.py: execute_tool_block, format_tool_result, MCP helpers
- tool_implementations.py: all do_* tool functions
"""
import logging
from collections import namedtuple
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Constants (kept here — sub-modules import from here)
# ---------------------------------------------------------------------------
cookbook agent debug loop: persistent log files, auto-adopt orphan tmux, Codex/Claude skill parity Three converging fixes so the chat agent + external Codex/Claude skills can actually debug a crashed serve instead of staring at a post-crash neofetch banner: * Serves now `tee` to /tmp/odysseus-tmux/SESSION.log on the host running them. Runner saves fds 3/4 before the tee and restores them right before `exec ${SHELL}`, so the post-crash interactive zsh banner does NOT pollute the log file. * `tail_serve_output` (chat agent) and `/api/codex/cookbook/output/{sid}` (Codex+Claude skills) both prefer the persistent log file over the tmux pane. Pane is fallback for sessions predating the tee runner. Default tail bumped 150 -> 400. * `list_served_models` "recent log" snippet seeks to the Traceback line instead of showing the last 6 lines (which was always the bash prompt). Cookbook auto-adoption sweep on `/api/cookbook/tasks/status`: every 20s (rate-limited) the cookbook SSHes each configured server, finds `serve-*` / `cookbook-*` tmux sessions running an actual model process (vllm/python/llama-server/etc., filtered via `pane_current_command`), and writes them into state.tasks. So when the agent falls back to raw ssh+tmux, the session appears in the Cookbook UI on the next poll. `serve_model` error path now reads `data["detail"]` in addition to `data["error"]` so the FastAPI HTTPException message ("Invalid characters in cmd") actually reaches the agent instead of being swallowed as a generic "Serve failed". Tool description updated to warn against `cd …`/`source …`/`&&` prefixes. Intent-without-action supervisor in agent_loop: when the model writes "Let me tail the output" / "I'll check the logs" / "Let me investigate" and ends the turn without emitting a tool call, the loop injects a sharp system nudge ("You said you would X — DO IT NOW") and continues. Capped at 2 nudges per chat so a model that genuinely cannot use the tool does not pin the loop. Codex/Claude skill parity: adds `/cookbook/cached`, `/cookbook/presets`, `/cookbook/preset/{name}`, `/cookbook/adopt` so external agents have the same surface as the chat agent. SKILL.md docs + odysseus_api.py wrapper updated for both bundles. `adopt_served_model` promoted to the always-on tool set so the agent has a documented fallback when serve_model rejects a cmd. Also various cookbook UI tweaks accumulated alongside the above (cookbook.js, cookbookRunning.js, cookbookServe.js, cookbook-diagnosis.js, settings.js, style.css).
2026-06-04 23:27:18 +09:00
MAX_AGENT_ROUNDS = 50
2026-05-31 23:58:26 +09:00
SHELL_TIMEOUT = 60
PYTHON_TIMEOUT = 30
MAX_OUTPUT_CHARS = 10_000
MAX_READ_CHARS = 20_000
# Tool types that trigger execution
TOOL_TAGS = {"bash", "python", "web_search", "web_fetch", "read_file", "write_file", "edit_file",
"grep", "glob", "ls",
2026-05-31 23:58:26 +09:00
"create_document", "update_document", "edit_document",
"search_chats",
"chat_with_model", "create_session", "list_sessions",
"send_to_session",
"pipeline",
"manage_session", "manage_memory", "list_models",
Add ask_user tool: agent-posed multiple-choice questions (#2111) Let the agent pause and ask the user a multiple-choice question when a task is genuinely ambiguous and the answer changes what it does next — choosing between approaches, confirming an assumption, picking a target — instead of guessing. Modeled on the existing `ui_control` marker pattern: the `ask_user` tool returns an `ask_user` payload that the agent loop emits as an SSE event and then ends the turn. The frontend renders the question with clickable option buttons, a free-text "Other" input, and an x to dismiss; the user's choice is sent as the next message and the agent resumes with it in context. - src/tool_execution.py: `ask_user` handler — pure UI marker, no I/O. Validates a non-empty question + 2..6 options, normalizes string/object options, returns the payload. - src/agent_loop.py: emit the `ask_user` event and break the round loop so the turn ends and waits for the user's selection. Stream the question as assistant text so it persists/replays (prevents a re-ask loop). - Registration: TOOL_TAGS, ALWAYS_AVAILABLE, BUILTIN_TOOL_DESCRIPTIONS, FUNCTION_TOOL_SCHEMAS, the system-prompt blurb. Not admin-gated (any user can be asked); the structured args serialize via the default json.dumps path. - routes/chat_routes.py: relay the `ask_user` event to the client. - static/js/chat.js + static/style.css: render the question card (options + free-text Other + dismiss x; removed once answered). Reuses CSS vars and the .modal-close button; emoji go through the monochrome-SVG pipeline. Bump chat.js cache pin. - tests/test_ask_user_tool.py: payload, multi flag, string options, option cap, validation errors, serializer round-trip, registration.
2026-06-05 11:49:11 +02:00
"ui_control", "generate_image", "ask_user",
2026-05-31 23:58:26 +09:00
"manage_tasks", "api_call", "ask_teacher", "manage_skills",
"suggest_document",
"manage_endpoints", "manage_mcp", "manage_webhooks",
"manage_tokens", "manage_documents", "manage_settings",
"manage_notes", "manage_calendar",
"resolve_contact", "manage_contact", "list_email_accounts", "send_email", "list_emails",
"read_email", "reply_to_email", "bulk_email", "archive_email",
"delete_email", "mark_email_read",
# Cookbook tools (LLM serving + downloads). Without these
# entries, native function calls to e.g. list_served_models
# are rejected as "Unknown function call" before reaching
# the dispatcher — silent failure for the whole cookbook
# surface.
"download_model", "serve_model",
"list_served_models", "stop_served_model",
"list_downloads", "cancel_download",
"search_hf_models", "list_cached_models",
"list_serve_presets", "serve_preset", "adopt_served_model",
"list_cookbook_servers",
# Other tools the agent reaches for that were also missing.
"edit_image", "trigger_research", "manage_research",
# Generic loopback to any UI-button endpoint (cookbook,
# gallery, email folders, etc.) — agent uses this when
# there's no named tool wrapper for the action.
"app_api"}
ToolBlock = namedtuple("ToolBlock", ["tool_type", "content"])
# ---------------------------------------------------------------------------
# MCP Manager (kept here — used by execution and agent_loop)
# ---------------------------------------------------------------------------
_mcp_manager = None
def set_mcp_manager(manager):
"""Set the global MCP manager instance."""
global _mcp_manager
_mcp_manager = manager
def get_mcp_manager():
"""Get the global MCP manager instance."""
return _mcp_manager
# ---------------------------------------------------------------------------
# Helpers (kept here — used by sub-modules)
# ---------------------------------------------------------------------------
def _truncate(text: str, limit: int = MAX_OUTPUT_CHARS) -> str:
# Callers treat the result as text, so always return a string: coerce a
# non-string (None -> "", otherwise str(...)) instead of returning it raw,
# which would just move the crash downstream.
if not isinstance(text, str):
text = "" if text is None else str(text)
2026-05-31 23:58:26 +09:00
if len(text) > limit:
return text[:limit] + f"\n... (truncated, {len(text)} chars total)"
return text
# ---------------------------------------------------------------------------
# Re-exports from sub-modules
# ---------------------------------------------------------------------------
# Parsing
from src.tool_parsing import ( # noqa: E402, F401
parse_tool_blocks,
strip_tool_blocks,
_TOOL_NAME_MAP,
_TOOL_BLOCK_RE,
_TOOL_CALL_RE,
_XML_TOOL_CALL_RE,
_XML_INVOKE_RE,
_XML_PARAM_RE,
)
# Schemas
from src.tool_schemas import ( # noqa: E402, F401
FUNCTION_TOOL_SCHEMAS,
function_call_to_tool_block,
)
# Execution
from src.tool_execution import ( # noqa: E402, F401
execute_tool_block,
format_tool_result,
)
# Implementations
from src.tool_implementations import ( # noqa: E402, F401
set_active_document,
set_active_model,
get_active_document,
do_create_document,
do_update_document,
do_edit_document,
do_suggest_document,
do_search_chats,
do_manage_skills,
do_manage_tasks,
do_manage_endpoints,
do_manage_mcp,
do_manage_webhooks,
do_manage_tokens,
do_manage_documents,
do_manage_settings,
do_api_call,
)