DumiFlex
58f5aff720
Fixes from the 2026-10-26 bench critiques (chat side): - Claim checks: "No <kind> card came" notes count the kinds a card changes or deletes, request gaps skip delete and tidy answers, and new notes mark a weight or factor no card sets, a bundle move the card doesn't make and "created successfully" before Apply (engine/ai/claims.py). Tool names in replies are said in plain words. - Deletes only target items the user named (a bulk ask still covers more), a category or tag delete never deletes an item of that name, and with deleting off the reply says where to turn it on. - edit_bundle: "switch off" switches off instead of removing; new move op (after/before). - A new item or rename onto a taken name warns; a rewritten derivation rule keeps its ELSE; a typo tag fix adds the tag it meant. - run_test runs a stack item with this answer's pending card and adds the items that set what a combine or derivation reads. - Only is described as a guest list (chat guide, docs, matrix legend). - read_page names the settings section the way open takes it, section aliases, more_tools hints carry the group's contents, library tags merge case, and Explain on a selection is read-only.
435 lines
19 KiB
Python
435 lines
19 KiB
Python
"""Tools that run in the user's browser, and web search, checked here first.
|
||
|
||
The model's call is turned into exactly what the browser should do: item
|
||
names become ids, pages come from fixed lists, text is cut to size. The
|
||
browser runs it (`src/manager/composables/useAiActions.ts`) and posts the
|
||
result back, and the turn goes on. The browser re-checks route names, but
|
||
nothing a model writes reaches the page without passing through here.
|
||
|
||
See `/pr-drafts/ai-client-tools.md`.
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import re
|
||
from typing import Any
|
||
|
||
from engine.ai import ask as ai_ask
|
||
from engine.ai import asked as ai_asked
|
||
from engine.ai import docs as ai_docs
|
||
from engine.ai import lang as ai_lang
|
||
from engine.ai import safety
|
||
|
||
MAX_IDS = 200
|
||
MAX_ORGANIZE = 40
|
||
MAX_STACK = 40
|
||
MAX_QUERY = 200
|
||
#: Most parts one highlight call points at.
|
||
MAX_POINTS = 5
|
||
#: The AI panels each kind of editor has, for `use_panel`. "describe" is
|
||
#: the Identity card's (name, description, tags); the wildcard's tabs are
|
||
#: add / remove / rewrite / retag / reweight; "draft" is Draft with AI.
|
||
PANELS: dict[str, tuple[str, ...]] = {
|
||
"wildcard": ("describe", "add", "remove", "rewrite", "retag", "reweight"),
|
||
"fixed_values": ("describe", "draft"),
|
||
"combine": ("describe", "draft"),
|
||
"template": ("describe", "draft"),
|
||
"derivation": ("describe", "draft"),
|
||
"constraint": ("describe", "draft"),
|
||
"bundle": ("describe",),
|
||
}
|
||
MAX_PIN_VALUE = 300
|
||
|
||
#: Pages the model may send the user to (route names in the manager).
|
||
PAGES = ("dashboard", "all", "wildcards", "fixed-values", "combines", "derivations",
|
||
"constraints", "bundles", "templates", "categories", "tags", "import-export", "test",
|
||
"pack-builder", "settings", "whats-new", "community")
|
||
SETTINGS_SECTIONS = ("general", "appearance", "editing", "autocomplete", "canvas",
|
||
"test-runner", "ai", "library", "advanced")
|
||
#: Names a model gives settings sections (the docs page is "ai-assistant",
|
||
#: the section "ai"; bench C4 mixed them up), lower-case with spaces.
|
||
SECTION_ALIASES = {"ai assistant": "ai", "assistant": "ai", "ai settings": "ai",
|
||
"test runner": "test-runner", "tests": "test-runner",
|
||
"auto complete": "autocomplete"}
|
||
|
||
|
||
def _text(value: Any, n: int) -> str:
|
||
out = safety.strip_invisible(value).strip() if isinstance(value, str) else ""
|
||
return " ".join(out.split())[:n]
|
||
|
||
|
||
def _row(lib: Any, raw: Any, what: str = "item", proposed: str = "") -> dict[str, Any]:
|
||
"""The library row `raw` names: an id, a chip, "Name (id)" (the way
|
||
answers write items; all-tools eval: show_test got "Lighting
|
||
(d97da2bb)"), or a unique name. A proposal of this chat is refused with
|
||
`proposed` as the way to work on it."""
|
||
row = lib.get(raw) if isinstance(raw, str) else None
|
||
bare = getattr(lib, "_bare_id", None)
|
||
if row is None and isinstance(raw, str) and bare is not None:
|
||
row = lib.get(bare(raw))
|
||
if row is None and isinstance(raw, str):
|
||
row = lib._find(raw)
|
||
if row is not None and row.get("_proposed"):
|
||
raise ValueError(f"no {what} {_text(raw, 40)!r}: it is a proposal of this chat, not "
|
||
f"applied yet{'; ' + proposed if proposed else ''}")
|
||
if row is None:
|
||
finder = getattr(lib, "not_found", None)
|
||
raise ValueError(finder(raw, what) if finder else f"no {what} {_text(raw, 40)!r}")
|
||
return row
|
||
|
||
|
||
class Shown(Exception):
|
||
"""The call asks to show what is already on screen (a card of this
|
||
answer): the message is the call's result, not an error. Chat eval round
|
||
1: the 9B opened its own card after nearly every proposal."""
|
||
|
||
|
||
def prepare(lib: Any, tool: str, args: dict[str, Any],
|
||
said: str = "") -> tuple[dict[str, Any], str]:
|
||
"""(the args the browser gets, a short label for the steps list).
|
||
``said`` is the user's message, for what the model's call left out.
|
||
Raises ValueError with a message for the model."""
|
||
fn = _PREPARE.get(tool)
|
||
if fn is None:
|
||
raise ValueError(f"unknown tool {tool}")
|
||
if tool == "draft_options":
|
||
return _draft_options(lib, args, said)
|
||
return fn(lib, args)
|
||
|
||
|
||
def _open(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
if not any(str(args.get(k) or "").strip() for k in ("doc", "page", "id", "proposal")):
|
||
# The 9B opened "" after every proposal: its card is already shown.
|
||
raise ValueError("open needs an item id, a page or a docs page; a card you just "
|
||
"proposed is already on screen, so don't open it")
|
||
if args.get("doc"):
|
||
doc = ai_docs.page(args.get("doc"))
|
||
if doc is None or doc["id"] == "settings":
|
||
raise ValueError(f"no docs page {_text(args.get('doc'), 40)!r}")
|
||
return {"doc": doc["id"]}, f"Opened the docs: {doc['title']}"
|
||
if args.get("page") and not args.get("id"):
|
||
name = _text(args.get("page"), 40).lower().strip("/ ")
|
||
if name not in PAGES:
|
||
raise ValueError(f"no manager page {name!r}; pages: {', '.join(PAGES)}")
|
||
out: dict[str, Any] = {"page": name}
|
||
label = f"Opened the {name} list" if name in LIST_PAGES else f"Opened {name}"
|
||
if name == "settings" and args.get("section"):
|
||
section = _text(args.get("section"), 30).lower().strip()
|
||
section = SECTION_ALIASES.get(section.replace("_", " ").replace("-", " "), section)
|
||
if section not in SETTINGS_SECTIONS:
|
||
raise ValueError(f"no settings section {section!r}; sections: "
|
||
+ ", ".join(SETTINGS_SECTIONS))
|
||
out["section"] = section
|
||
label += f" › {section}"
|
||
return out, label
|
||
raw = args.get("proposal") or args.get("id")
|
||
mine = _this_answer(lib, raw)
|
||
if mine:
|
||
raise Shown(f"open: card {mine} is already on screen for the user, who applies it "
|
||
"from there; there is nothing to open. Answer now, or make the next "
|
||
"change")
|
||
pid = _proposal(lib, raw)
|
||
if pid:
|
||
title = str((lib.earlier_proposals.get(pid) or {}).get("title") or pid)
|
||
return {"proposal": pid}, f"Opened {title} in an editor"
|
||
try:
|
||
row = _row(lib, raw)
|
||
except ValueError:
|
||
# A docs page id given as an item id (the 9B opened {"id":
|
||
# "constraints"} for the constraints docs): open the doc.
|
||
doc = ai_docs.page(raw) if isinstance(raw, str) and not args.get("proposal") else None
|
||
if doc is None or doc["id"] == "settings":
|
||
raise
|
||
return {"doc": doc["id"]}, f"Opened the docs: {doc['title']}"
|
||
return ({"id": row["id"], "type": lib._kind(row)},
|
||
f"Opened {row.get('name') or row['id']}")
|
||
|
||
|
||
def _this_answer(lib: Any, raw: Any) -> str:
|
||
"""The pid of a card proposed earlier in this same answer that ``raw``
|
||
names (its pid or the id it will get), else "": the browser shows it
|
||
only once the answer ends, so there is nothing to open yet."""
|
||
if not isinstance(raw, str) or not raw.strip():
|
||
return ""
|
||
key = raw.strip()
|
||
earlier = getattr(lib, "earlier_proposals", {}) or {}
|
||
if re.fullmatch(r"p\d+", key) and key not in earlier \
|
||
and int(key[1:]) <= int(getattr(lib, "_next_pid", 0) or 0):
|
||
return key
|
||
made = getattr(lib, "_created", {}) or {}
|
||
pid = made.get(key.split("#", 1)[0].strip())
|
||
return pid if isinstance(pid, str) and pid not in earlier else ""
|
||
|
||
|
||
def _proposal(lib: Any, raw: Any) -> str:
|
||
"""The pid of a proposal the user hasn't applied yet that ``raw`` names
|
||
(its pid, the id it will get, or words of its title), else ""."""
|
||
if not isinstance(raw, str) or not raw.strip():
|
||
return ""
|
||
key = raw.strip()
|
||
earlier = getattr(lib, "earlier_proposals", {}) or {}
|
||
if key in earlier and earlier[key].get("status") not in ("applied", "replaced"):
|
||
return key
|
||
row = lib.get(key) or lib._find(key)
|
||
if row is not None:
|
||
return str(row.get("_proposed") or "")
|
||
low = key.lower().lstrip("$")
|
||
for pid, p in earlier.items():
|
||
if p.get("status") not in ("applied", "replaced") and low in str(
|
||
p.get("title") or "").lower():
|
||
return pid
|
||
return ""
|
||
|
||
|
||
def _read_page(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
within = _anchor(args.get("within"))
|
||
if within:
|
||
return {"within": within}, f"Read the page: {within}"
|
||
return {}, "Read the page"
|
||
|
||
|
||
def _anchor(raw: Any) -> str:
|
||
# read_page lists parts as "[key] label"; models copy the brackets.
|
||
return _text(raw, 80).strip().strip("[]").strip()
|
||
|
||
|
||
def _point(raw: Any) -> dict[str, str]:
|
||
if not isinstance(raw, dict):
|
||
raise ValueError("each point is {\"anchor\", \"caption\", \"text\"}")
|
||
anchor = _anchor(raw.get("anchor"))
|
||
if not anchor:
|
||
raise ValueError("highlight needs an anchor from read_page")
|
||
out = {"anchor": anchor, "caption": _text(raw.get("caption"), 160)}
|
||
# A quote to mark inside the part; models often end it with an ellipsis.
|
||
text = _text(raw.get("text"), 200).strip("…").strip().strip("\"'")
|
||
if text:
|
||
out["text"] = text
|
||
return out
|
||
|
||
|
||
#: A highlight before any read_page on this page: its anchors are guesses.
|
||
READ_PAGE_FIRST = "call read_page first, then highlight an anchor it returned"
|
||
|
||
|
||
def _highlight(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
raw = args.get("points")
|
||
if isinstance(raw, list) and raw:
|
||
points = [_point(p) for p in raw[:MAX_POINTS]]
|
||
else:
|
||
points = [_point(args)]
|
||
first = points[0]
|
||
label = f"Pointed at {first['caption'] or first['anchor']}"
|
||
if len(points) > 1:
|
||
label += f" and {len(points) - 1} more"
|
||
return {"points": points}, label
|
||
|
||
|
||
def _ids(lib: Any, raw: Any, cap: int) -> list[dict[str, Any]]:
|
||
if not isinstance(raw, list) or not raw:
|
||
raise ValueError("give a list of item ids or names")
|
||
rows: list[dict[str, Any]] = []
|
||
missing: list[str] = []
|
||
for value in raw[:cap]:
|
||
try:
|
||
row = _row(lib, value)
|
||
except ValueError:
|
||
missing.append(_text(value, 30))
|
||
continue
|
||
if all(r["id"] != row["id"] for r in rows):
|
||
rows.append(row)
|
||
if missing and not rows:
|
||
raise ValueError("none of those items exist: " + ", ".join(missing[:8]))
|
||
return rows
|
||
|
||
|
||
def _select_rows(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
rows = _ids(lib, args.get("ids"), MAX_IDS)
|
||
return {"ids": [r["id"] for r in rows]}, f"Selected {len(rows)} row" + (
|
||
"" if len(rows) == 1 else "s")
|
||
|
||
|
||
def _organize(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
rows = _ids(lib, args.get("ids"), MAX_ORGANIZE)
|
||
return ({"ids": [r["id"] for r in rows], "note": _text(args.get("note"), 500)},
|
||
f"Organize {len(rows)} item" + ("" if len(rows) == 1 else "s"))
|
||
|
||
|
||
def _draft_options(lib: Any, args: dict[str, Any],
|
||
said: str = "") -> tuple[dict[str, Any], str]:
|
||
row = _row(lib, args.get("id"), "wildcard")
|
||
if row.get("type") != "wildcard":
|
||
raise ValueError(f"{row.get('name')} is a {lib._kind(row)}, not a wildcard")
|
||
instruction = _text(args.get("instruction"), 1000)
|
||
if len(instruction) < 3:
|
||
raise ValueError("say what options to write")
|
||
count = args.get("count")
|
||
if isinstance(count, bool) or not isinstance(count, int):
|
||
# Bench W18: "draft 6 desert weather options" came without a count
|
||
# and the panel drafted 10. The request's own number, else 10.
|
||
# A request in another language: the request frame's count.
|
||
count = ai_asked.option_count(instruction) or ai_asked.option_count(said) \
|
||
or ai_lang.count(getattr(lib, "request_frame", None)) or 10
|
||
count = max(1, min(50, count))
|
||
return ({"id": row["id"], "instruction": instruction, "count": count},
|
||
f"Drafting {count} options for {row.get('name')}")
|
||
|
||
|
||
def _show_test(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
raw = args.get("stack")
|
||
if not isinstance(raw, list) or not raw:
|
||
raise ValueError("give the stack: names or ids of modules and bundles")
|
||
stack: list[dict[str, str]] = []
|
||
for value in raw[:MAX_STACK]:
|
||
# The Test Runner shows what is in the library; the eval's 9B kept
|
||
# asking it for its own card's items.
|
||
row = _row(lib, value, proposed="the Test Runner only shows applied items. run_test "
|
||
"runs a stack with this chat's proposals swapped in, or ask the user to "
|
||
"Apply the card first")
|
||
kind = lib._kind(row)
|
||
if kind == "template":
|
||
raise ValueError(f"{row.get('name')} is a template; the stack takes modules and "
|
||
"bundles")
|
||
stack.append({"bundle": row["id"]} if kind == "bundle" else {"module": row["id"]})
|
||
change = _text(args.get("change"), 10).lower() or "replace"
|
||
if change not in ("replace", "add", "remove"):
|
||
raise ValueError("change is replace, add or remove")
|
||
needs = getattr(lib, "with_needs", None)
|
||
added: list[str] = []
|
||
if needs is not None and change != "remove":
|
||
ids, added = needs([x.get("module") or x.get("bundle") or "" for x in stack])
|
||
stack = [{"bundle": i} if i in lib.bundles else {"module": i} for i in ids][:MAX_STACK]
|
||
seeds = _got if isinstance(_got := args.get("seeds"), int) else 20
|
||
out: dict[str, Any] = {"stack": stack, "seeds": max(1, min(500, seeds))}
|
||
if change != "replace":
|
||
out["change"] = change
|
||
if not isinstance(args.get("seeds"), int):
|
||
out.pop("seeds") # keep the open run's seeds
|
||
if isinstance(args.get("from"), int) and not isinstance(args.get("from"), bool):
|
||
out["from"] = max(0, args["from"])
|
||
pins = args.get("pins")
|
||
if isinstance(pins, dict) and pins:
|
||
out["pins"] = {_text(str(k), 60).lstrip("$"): _text(v, MAX_PIN_VALUE)
|
||
for k, v in list(pins.items())[:30] if _text(str(k), 60).lstrip("$")}
|
||
if args.get("output"):
|
||
out["output"] = _text(args.get("output"), 60).lstrip("$")
|
||
if args.get("save"):
|
||
out["save"] = _text(args.get("save"), 80)
|
||
run = args.get("run") is not False
|
||
if not run:
|
||
out["run"] = False
|
||
n = len(stack)
|
||
what = f"{n} item" + ("" if n == 1 else "s")
|
||
label = (f"Ran {what} in the Test Runner" if run else f"Set up {what} in the Test Runner")
|
||
if change == "add":
|
||
label = f"Added {what} to the Test Runner" + (" and ran it" if run else "")
|
||
elif change == "remove":
|
||
label = f"Took {what} out of the Test Runner" + (" and ran it" if run else "")
|
||
if out.get("save"):
|
||
label += f", saved as {out['save']}"
|
||
if added:
|
||
out["notes"] = added
|
||
return out, label
|
||
|
||
|
||
def _use_panel(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
row = _row(lib, args.get("id"))
|
||
kind = lib._kind(row)
|
||
panels = PANELS.get(kind, ())
|
||
panel = _text(args.get("panel"), 20).lower()
|
||
if panel not in panels:
|
||
raise ValueError(f"a {kind.replace('_', ' ')} has no {panel or 'such'} panel; its "
|
||
"panels: " + ", ".join(panels))
|
||
request = _text(args.get("request"), 1000)
|
||
if len(request) < 3:
|
||
raise ValueError("say what to ask the panel")
|
||
name = row.get("name") or row["id"]
|
||
what = {"describe": "Describe", "draft": "Draft with AI"}.get(panel, panel.capitalize())
|
||
return ({"id": row["id"], "type": kind, "panel": panel, "request": request},
|
||
f"Asked {what} in {name}")
|
||
|
||
|
||
def _web_search(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
query = _text(args.get("query"), MAX_QUERY)
|
||
if len(query) < 2:
|
||
raise ValueError("web_search needs a query")
|
||
return {"query": query}, f"Web search: {query}"
|
||
|
||
|
||
def _same_url(a: str, b: str) -> bool:
|
||
return a.rstrip("/").lower() == b.rstrip("/").lower()
|
||
|
||
|
||
def _read_result(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
url = _text(args.get("url"), 500).strip("<>[]() ")
|
||
# Only links a search the user allowed in this chat returned.
|
||
seen = list(getattr(lib, "web_urls", None) or [])
|
||
hit = next((u for u in seen if _same_url(u, url)), None)
|
||
if hit is None:
|
||
raise ValueError("read_result only reads links from your web_search results in this "
|
||
"chat; search first, then pass one of their links exactly")
|
||
short = hit.split("://", 1)[-1]
|
||
return {"url": hit}, "Read page: " + (short if len(short) <= 80 else short[:79] + "…")
|
||
|
||
|
||
def _danbooru(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
tag = "_".join(_text(args.get("tag"), 120).lower().split())
|
||
if len(tag) < 2 or "," in tag:
|
||
raise ValueError("danbooru looks up one tag, e.g. {\"tag\": \"hatsune_miku\"}")
|
||
return {"tag": tag}, f"Danbooru: {tag}"
|
||
|
||
|
||
def _ask(lib: Any, args: dict[str, Any]) -> tuple[dict[str, Any], str]:
|
||
# The chat's settled answers ride on the library for the turn.
|
||
return ai_ask.prepare(args, getattr(lib, "decisions", None))
|
||
|
||
|
||
_PREPARE = {
|
||
"open": _open, "read_page": _read_page, "highlight": _highlight,
|
||
"select_rows": _select_rows, "organize": _organize, "draft_options": _draft_options,
|
||
"show_test": _show_test, "use_panel": _use_panel, "web_search": _web_search, "ask": _ask,
|
||
"read_result": _read_result, "danbooru": _danbooru,
|
||
}
|
||
|
||
#: Longest browser answer kept for the model.
|
||
MAX_RESULT = 4000
|
||
|
||
|
||
#: Said after a page call that did nothing, so a small model doesn't tell
|
||
#: the user it worked (Nemotron said "I've highlighted the paragraph").
|
||
FAILED_NOTE = ("This call FAILED: nothing happened on the user's page. Don't say it worked; "
|
||
"fix the call (read_page lists the parts) or tell the user it didn't work.")
|
||
#: Manager pages that list one kind of module; each has a docs page too.
|
||
LIST_PAGES = ("wildcards", "fixed-values", "combines", "derivations", "constraints", "bundles",
|
||
"templates")
|
||
|
||
|
||
def failed(text: str) -> bool:
|
||
"""Whether a page call's result says it did nothing."""
|
||
body = text.split(": ", 1)[1] if ": " in text else text
|
||
return body.startswith("couldn't") or body.startswith("no part ")
|
||
|
||
|
||
def open_note(args: dict[str, Any]) -> str:
|
||
"""What the model is told after opening a list page, which it confuses
|
||
with that module's docs page."""
|
||
page = args.get("page")
|
||
if page in LIST_PAGES:
|
||
return (f" (the user's {page} list, not the docs: a docs page opens with "
|
||
'{"doc": id})')
|
||
return ""
|
||
|
||
|
||
def result_text(tool: str, answer: dict[str, Any]) -> str:
|
||
"""What the model reads back for one paused call: the browser's text,
|
||
or that the user declined or the page couldn't do it."""
|
||
if answer.get("denied"):
|
||
return f"{tool}: the user declined this"
|
||
if answer.get("cancelled"):
|
||
return f"{tool}: not run (the user moved on)"
|
||
text = answer.get("text")
|
||
if not isinstance(text, str) or not text.strip():
|
||
return f"{tool}: done"
|
||
text = safety.strip_invisible(text).strip()
|
||
if len(text) > MAX_RESULT:
|
||
text = text[:MAX_RESULT] + " …"
|
||
return f"{tool}: {text}"
|