Files
odysseus/src/tools/research.py
T
Tal.Yuan fc1351d0f8 refactor(tools): split tool_implementations.py into src/tools/ package (#4423)
* test(tools): add shim protection test for tool_implementations split

Covers all 48 top-level functions (33 do_* + 15 _helpers) extracted from
the original module. Guards the upcoming split: the shim must re-export
every symbol so existing 'from src.tool_implementations import X' imports
keep working. Passes on baseline (pre-split).

* refactor(tools): add src/tools/ package with shared _common

Slice 1 Task 2 (#4082/#4071). Adds the package skeleton and moves the
shared _parse_tool_args helper into src/tools/_common.py. Domain modules
will import from here. tool_implementations.py is untouched at this step.

* refactor(tools): extract system domain into src/tools/system.py

Slice 1 (#4082/#4071), Task 3: move the system-domain tool functions
(do_manage_skills/_skill_dump/do_manage_tasks/do_manage_endpoints/
do_manage_mcp/do_manage_webhooks/do_manage_tokens/do_manage_settings/
do_api_call/do_app_api) and the app_api blocklist constants out of
tool_implementations.py into a new src/tools/system.py module.

tool_implementations.py re-imports all of them so it stays a working
backward-compatible facade (shim test stays green).

- do_manage_mcp resolves get_mcp_manager via a function-local import
  from tool_implementations so the test that patches
  src.tool_implementations.get_mcp_manager still applies post-move.
- do_app_api imports _internal_headers and _INTERNAL_BASE (still in
  tool_implementations) function-locally to avoid a circular import.
- Repoint test_context_budget introspection assertion to the moved
  code's new home in src/tools/system.py.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* refactor(tools): extract cookbook domain into src/tools/cookbook.py

Moves the model-serving (cookbook) tool domain out of tool_implementations.py
into src/tools/cookbook.py as part of slice 1 (#4082/#4071):

- 13 do_* tools: download/serve/list/stop/tail/search/adopt/cached models,
  list downloads/cancel, list cookbook servers, serve presets
- 9 private helpers: _cookbook_servers, _resolve_cookbook_host,
  _cookbook_env_for_host, _infer_serve_{port,host}, _ensure_served_endpoint,
  _cookbook_register_task, _cookbook_apply_retry_suggestion,
  _scan_running_model_processes, _cookbook_kill_session
- _MODEL_PROCESS_PATTERNS constant (used only by _scan_running_model_processes)

tool_implementations.py stays a backward-compatible facade via a re-import
from src.tools.cookbook; src/tools/__init__ re-exports the same symbols.

_internal_headers and _INTERNAL_BASE stay in tool_implementations.py (shared
by system.py's do_app_api and many cookbook funcs). Each cookbook function
that needs them does a function-local import to avoid a top-level circular
dependency, matching the system-domain split.

Verified: compileall clean; shim test green; cookbook-touching suite
(652 passed, 1 skipped); full suite 3587 passed, 2 failed
(pre-existing test_api_chat_security, unrelated).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* refactor(tools): extract search domain into src/tools/search.py

* refactor(tools): extract notes domain into src/tools/notes.py

* refactor(tools): extract calendar domain into src/tools/calendar.py

Repoints tests/test_caldav_bidirectional_sync.py source-introspection
to src/tools/calendar.py (do_manage_calendar moved there).

* refactor(tools): extract image domain into src/tools/image.py

* refactor(tools): extract research domain into src/tools/research.py

* refactor(tools): extract contacts domain into src/tools/contacts.py

* refactor(tools): extract vault domain into src/tools/vault.py

Repoints tests/test_vault_password_not_in_argv.py source-introspection
to src/tools/vault.py (the vault do_* helpers moved there).

* refactor(tools): collapse tool_implementations to clean re-export shim

Move shared _INTERNAL_BASE/_internal_headers to src/tools/_common.py and
drop the duplicate _parse_tool_args (already in _common). tool_implementations.py
is now a pure re-export facade (+ 3 pre-existing email-context helpers, out of
scope). Domain files' function-local imports of these names still resolve via
the facade re-export.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tools): port upstream cookbook workflow changes to split module

Rebase onto dev dropped c504214 ("Cookbook model workflow fixes") edits
to do_serve_model / do_tail_serve_output: the extraction commit moved
the pre-edit bodies into src/tools/cookbook.py and git auto-accepted the
deletion from tool_implementations.py, losing dev's changes. Restore them
in their post-split home:

- do_serve_model: add where/log_path/next_tools and the expanded
  "Next required check" output message
- do_tail_serve_output: empty-output fallback message replacing
  "(empty pane)"

(do_manage_settings web_fetch alias edit was already applied to
src/tools/system.py during the system-extract conflict resolution.)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tools): break admin_tools circular import in split facade

After rebasing onto dev (#3629 moved the admin manage_* tools into
src/agent_tools/admin_tools), the facade re-exported them via a top-level
`from src.agent_tools.admin_tools import ...`. But src.agent_tools.__init__
imports this facade at top level, so the eager import re-entered the
partially-initialized agent_tools package and broke collection.

Re-export the admin symbols (do_manage_endpoints/mcp/webhooks/tokens/
settings, _MCP_DENIED_COMMANDS, _validate_mcp_command) lazily through
module __getattr__ instead, and drop them from src/tools/__init__ (they
no longer live in the src.tools package). system.py now holds only the
skills/tasks/api bridges; admin tools live solely in admin_tools.py,
matching upstream.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tools): re-export dropped helpers through the split shim

Address review finding from #4423: the compatibility facade claimed to
preserve every original top-level symbol but omitted three helpers the
old src.tool_implementations exposed. Re-export them and pin them in
the shim protection test:

- _string_arg, _validate_cookbook_ssh_target <- src/tools/cookbook.py
- _mcp_allowed_commands <- src/agent_tools/admin_tools.py (lazily via
  __getattr__, to keep the agent_tools.__init__ <-> facade import acyclic
  after the #3629 admin-tools migration)

All three added to tests/test_tool_implementations_shim.py _EXPECTED so
the test contract now matches its "every original top-level function"
comment.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* test(tools): self-verify shim re-exports every domain do_*

The hand-maintained _EXPECTED list in the shim protection test can drift
silently when a new tool is added to a domain module but not re-exported
by the facade — exactly the omission a reviewer flagged post-split.
Add an auto-discovering test that enumerates every do_* from the domain
modules (incl. admin_tools) and asserts reachability through the shim,
so a forgotten re-export fails the build automatically.

Uses hasattr (not dir(ti)) because the admin symbols are re-exported
lazily via module __getattr__ and don't appear in dir(ti).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* test(tools): self-verify every in-repo facade import resolves

RaresKeY's P3 on the shim test was a claim-vs-reality gap: the docstring
said it protected "every from src.tool_implementations import X" but the
hand-maintained _EXPECTED list omitted three underscore helpers, so the
claim wasn't enforced. Re-exporting the three (cf1f5e3) fixed the known
gap; this closes the structural one.

Add test_every_facade_import_in_repo_resolves: ast-enumerate every
`from src.tool_implementations import X` site in src/ and tests/ and
assert hasattr(ti, X) for each. A forgotten re-export that anything in
the repo imports now fails the build automatically — including underscore
helpers, which the do_* discovery test does not cover.

Together with test_shim_reexports_every_domain_do_function, the shim
contract is now self-verifying. Demote _EXPECTED in the docstring to the
curated historical/downstream surface (the three helpers have no in-repo
consumer, so they stay manual by necessity) instead of "ground truth".

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(tools): dedupe _parse_tool_args + align shim guard with route consumers

Addresses two P3s from review (RaresKeY, 2026-06-26):

1. maintainability — _common carried a full copy of _parse_tool_args
   alongside the canonical src.tool_utils one; future parser fixes could
   diverge. The two bodies were byte-identical in logic, so _common now
   re-exports from tool_utils (a leaf module, no circular-import risk).
   The single-source test is extended to assert _common._parse_tool_args
   and tool_implementations._parse_tool_args are the same object as
   tool_utils._parse_tool_args.

2. test — the shim guard's import-site scan only walked src/ and tests/,
   missing routes/chat_routes.py's clear_active_email/set_active_email
   imports, and _EXPECTED omitted the active-email facade helpers. The
   scan now walks every first-party Python dir (pruning venvs/caches/data
   in-place), and set/get/clear_active_email are added to _EXPECTED
   (get_active_email has no in-repo importer, so the scan alone can't see
   it).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: yuandonghao <yuandonghao@cohl.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 15:40:04 +01:00

143 lines
6.4 KiB
Python

"""Research-domain tool implementations.
Extracted from tool_implementations.py as part of slice 1 (#4082/#4071).
Holds the manage_research (library CRUD) and trigger_research (live job)
tools.
``src.tool_implementations`` re-exports these for backward compatibility.
``_internal_headers`` and ``_INTERNAL_BASE`` still live in
tool_implementations.py and are pulled back function-locally where needed.
"""
import re
from typing import Any, Dict, Optional
from src.constants import DEEP_RESEARCH_DIR
from src.tools._common import _parse_tool_args
async def do_manage_research(content: str, owner: Optional[str] = None) -> Dict:
"""List, read/open, or delete saved deep-research results from the Library.
Args (JSON): {"action": "list|read|delete", "id": "<id>", "search": "..."}.
Research is stored as data/deep_research/<id>.json (query, summary, sources)."""
import json as _json
from pathlib import Path as _Path
try:
args = _parse_tool_args(content) if content.strip().startswith("{") else {}
except ValueError:
args = {}
if not isinstance(args, dict):
args = {}
action = (args.get("action") or "list").lower()
rid = (args.get("id") or args.get("session_id") or args.get("research_id") or "").strip()
data_dir = _Path(DEEP_RESEARCH_DIR)
# SECURITY: the research id is interpolated straight into a filesystem
# path (data/deep_research/<rid>.json) for read AND delete. Without this
# gate an agent-supplied id like "../settings" or "../../etc/passwd"
# escapes the research dir — reading exfiltrates arbitrary *.json into
# chat, deleting unlinks arbitrary *.json on disk. Allow only a bare
# token (research session ids are hex/uuid/slug — no separators).
if rid and not re.fullmatch(r"[A-Za-z0-9_-]+", rid):
return {"error": "Invalid research id."}
def _load(p):
try:
return _json.loads(p.read_text(encoding="utf-8"))
except Exception:
return None
if action in ("read", "open", "view", "get"):
if not rid:
return {"error": "Provide the research id (from action='list')."}
p = data_dir / f"{rid}.json"
if not p.exists():
return {"error": f"Research '{rid}' not found."}
d = _load(p) or {}
summary = d.get("result") or d.get("raw_report") or d.get("summary") or d.get("report") or "(no report body)"
srcs = d.get("sources", []) or []
out = f"# {d.get('query', '(untitled)')}\n\n{summary}"
if srcs:
out += "\n\nSources:\n" + "\n".join(
f"- {s.get('title') or s.get('url', '')}: {s.get('url', '')}" for s in srcs[:30]
)
return {"output": out[:16000], "exit_code": 0}
if action == "delete":
if not rid:
return {"error": "Provide the research id to delete (from action='list')."}
p = data_dir / f"{rid}.json"
if p.exists():
try:
p.unlink()
except Exception as e:
return {"error": f"Failed to delete: {e}"}
return {"output": f"Deleted research '{rid}'.", "exit_code": 0}
return {"error": f"Research '{rid}' not found."}
# default: list — clickable [query](#research-<id>) rows, most-recent first
search = (args.get("search") or "").lower()
items = []
if data_dir.exists():
for p in data_dir.glob("*.json"):
d = _load(p)
if not d:
continue
q = d.get("query", "")
if search and search not in q.lower():
continue
items.append((d.get("completed_at", 0) or 0, p.stem, q, len(d.get("sources", []) or [])))
items.sort(reverse=True)
if not items:
return {"output": "No research found in the library." + (f" (search: {search})" if search else ""), "exit_code": 0}
rows = "\n".join(f"- [{q or '(untitled)'}](#research-{sid}) — {n} sources" for _, sid, q, n in items[:50])
return {"output": f"Research library ({len(items)} item{'s' if len(items) != 1 else ''}):\n{rows}", "exit_code": 0}
async def do_trigger_research(content: str, owner: Optional[str] = None) -> Dict:
"""Start a live deep-research job that appears in the Deep Research
sidebar. Hits /api/research/start (the same path the sidebar's
'Research' button uses) so the session is discoverable + streamable
there, rather than creating a scheduled task that never surfaces."""
import httpx
from src.tool_implementations import _internal_headers, _INTERNAL_BASE # shared constants, still live in the facade
try:
args = _parse_tool_args(content)
except ValueError:
return {"error": "Invalid JSON arguments", "exit_code": 1}
topic = args.get("topic", "") or args.get("query", "")
if not topic:
return {"error": "topic (or query) is required", "exit_code": 1}
payload: Dict[str, Any] = {"query": topic}
# Optional knobs the research panel supports.
if args.get("max_rounds") is not None:
try: payload["max_rounds"] = int(args["max_rounds"])
except (ValueError, TypeError): pass
if args.get("max_time") is not None:
try: payload["max_time"] = int(args["max_time"])
except (ValueError, TypeError): pass
if args.get("category"):
payload["category"] = args["category"]
if args.get("search_provider"):
payload["search_provider"] = args["search_provider"]
try:
async with httpx.AsyncClient(timeout=30) as client:
resp = await client.post(f"{_INTERNAL_BASE}/api/research/start",
json=payload, headers=_internal_headers(owner))
if resp.status_code >= 400:
return {"error": f"research/start returned HTTP {resp.status_code}: {resp.text[:200]}", "exit_code": 1}
data = resp.json()
sid = data.get("session_id", "?")
return {
"output": (
f"Deep research started: [{topic}](#research-{sid}). "
"Click to open the Deep Research sidebar and watch progress / read the report."
),
"session_id": sid,
"anchor": f"[{topic}](#research-{sid})",
# UI hint so the frontend can open/refresh the research panel.
"ui_event": "research_started",
"research_session_id": sid,
"exit_code": 0,
}
except Exception as e:
return {"error": str(e), "exit_code": 1}