feat(rag): agent document tools — list/read tools with env-tuned budgets, SSE tool events + "calling tool" UI

Grounded chat turns now run the agent loop (app/rag/agent.py) instead
of a bare chat_stream: while the per-turn budgets last
(BOR_AGENT_LIST_CALLS / BOR_AGENT_READ_CALLS, default 1 each) the model
gets list_documents (the indexed catalog, /api/docs order) and
read_document (full text, never truncated — A7-revised contract); once
both budgets are spent the tools key is dropped from the request and
the model must answer. Rejected calls (unknown tool, unknown/missing
path, document already in context, spent budget) consume no budget.
Budgets 0/0 make exactly one tools=None request — byte-identical to
the pre-phase path (budgets-as-kill-switch). Deflected turns keep the
direct chat_stream (A8 unchanged; the LOW prompt never carries the
<tools> section).

SSE contract gains {"type":"tool","name":...,"argument":
"source/path"|null} frames ahead of the answer deltas (PLAN §4
extension, owner permission 2026-08-26); done.sources, query_log.sources
and the per-turn log line (gains tool_calls=N) report the retrieval
docs + read docs, deduped. The UI shows a "calling tool"
button/label state and one visible .tool-call line per call above the
answer; the lines persist with the chat record and re-render on
reload. chat_stream passes tools through and accumulates streaming
tool_calls deltas into ToolCallPiece (tools=None stays byte-identical).

E2E: deterministic mock tool flow ("use your tools" + <tools> marker:
list -> read first catalog line -> quoted answer) plus the story suite
(marker flow, reload re-render, plain/deflected no-tool regressions).
Docs: .env.example + README (the two tools, the budgets, the SSE tool
frame, the "calling tool" UI state).

probe: turbo tool_calls=supported 2026-08-26 (uv run python -m
scripts.llm_probe --tools — non-streaming + streaming
finish_reason=tool_calls, indexed delta.tool_calls partials)
This commit is contained in:
2026-08-26 22:39:14 -04:00
parent 9efffcb428
commit 15c1272828
30 changed files with 3594 additions and 67 deletions
+300
View File
@@ -0,0 +1,300 @@
"""Agent loop: the grounded-turn document tools (phase 37, task 03).
Probe verdict (task 01 — ``uv run python -m scripts.llm_probe --tools``
run live against aipi): **``probe: turbo tool_calls=supported 2026-08-26``**
— ``turbo`` answers OpenAI ``tools`` requests with
``finish_reason="tool_calls"`` and streams the calls as indexed
``delta.tool_calls`` partials (id + name on the first partial, arguments
in fragments). This module therefore uses the **native tool-calling
path**: tool calls arrive as :class:`app.rag.llm.ToolCallPiece` values
from ``chat_stream(messages, tools=AGENT_TOOLS)``. The prompt-based
JSON-block fallback (documented in the task file) is *not* implemented —
it exists only for a "not supported"/"intermittent" verdict, and the
probe came back "supported".
Loop contract (one grounded chat turn; the API layer wires this in,
task 04):
1. While budget remains the model is offered the two OpenAI functions in
:data:`AGENT_TOOLS`: up to ``settings.agent_list_calls``
(``BOR_AGENT_LIST_CALLS``, default 1) ``list_documents`` calls and up
to ``settings.agent_read_calls`` (``BOR_AGENT_READ_CALLS``, default 1)
``read_document`` calls. With both budgets at 0 the loop makes exactly
one request with ``tools=None`` — byte-identical to the pre-phase chat
path (budgets-as-kill-switch, phase 37 locked decision).
2. Each tool call the model emits is executed server-side against
Postgres only (no LLM, no network): ``list_documents`` returns the
indexed catalog — one ``source/path — title`` line per document,
``GET /api/docs`` order (uncapped in v1; the UI never shows it, only
the model does) — and ``read_document`` returns the document's **full**
content (A7-revised contract: never truncated).
3. Rejected calls consume **no** budget and get a one-line refusal:
unknown tool name → ``"Unknown tool."``; missing ``source``/``path``
arguments; a document already in context (seed or previously read) →
``"Already in your context."``; an unknown ``source/path`` →
``"No document at …"``; an exhausted list/read budget → the matching
``"No … budget left"`` refusal.
4. Every executed call is appended back to the message history as the
assistant tool-call message + the tool result, and the model is called
again. Once **both** budgets are spent, ``tools`` is dropped from the
request and the model must answer. Belt-and-braces round cap:
``max_rounds = 2 + agent_list_calls + agent_read_calls`` (every tool
round consumes a budget, so the cap only catches pathological streams
that keep calling rejected tools) — at the cap the loop forces one
final ``chat_stream(messages, tools=None)`` and returns.
5. A rare stream that carries both content and a tool call keeps the
content (it was already emitted) **and** still runs the tool.
6. *holder* (an :class:`AgentHolder`) records the read documents and the
number of budget-consuming tool executions; the API layer (task 04)
reads it after the stream to extend ``done.sources`` /
``query_log.sources`` and the per-turn log line (``tool_calls=N``).
The DB accessors (:func:`list_catalog`, :func:`find_document`) are
module-level functions so unit tests can monkeypatch them without a
database.
"""
from __future__ import annotations
import json
import logging
from collections.abc import AsyncIterator, Sequence
from dataclasses import dataclass, field
from typing import Any, cast
from sqlalchemy import select
from sqlalchemy.orm import Session
from app.config import Settings
from app.models import Document
from app.rag.llm import LLMClient, StreamPiece, ToolCallPiece
logger = logging.getLogger("app.agent")
#: The two agent tools (phase 37): OpenAI function definitions passed as
#: ``tools=AGENT_TOOLS`` to ``chat_stream`` while the per-turn budgets
#: (``BOR_AGENT_LIST_CALLS`` / ``BOR_AGENT_READ_CALLS``) remain.
AGENT_TOOLS: list[dict[str, Any]] = [
{
"type": "function",
"function": {
"name": "list_documents",
"description": (
"List every document indexed in the knowledge base, one "
"`source/path — title` line each"
),
"parameters": {"type": "object", "properties": {}, "required": []},
},
},
{
"type": "function",
"function": {
"name": "read_document",
"description": (
"Add the full content of exactly one more indexed document "
"to your context"
),
"parameters": {
"type": "object",
"properties": {
"source": {
"type": "string",
"description": (
"The document's source (a directory basename, "
"e.g. 'Homelab')."
),
},
"path": {
"type": "string",
"description": (
"The document's path relative to its source "
"directory."
),
},
},
"required": ["source", "path"],
},
},
},
]
#: Tool refusal texts (phase 37): rejected calls consume no budget.
LIST_EXHAUSTED = "No listing budget left — answer with what you have."
READ_EXHAUSTED = "No reading budget left — answer with what you have."
ALREADY_IN_CONTEXT = "Already in your context."
UNKNOWN_TOOL = "Unknown tool."
MISSING_READ_ARGS = "read_document requires string arguments 'source' and 'path'."
def list_catalog(db: Session) -> list[tuple[str, str, str]]:
"""Every indexed document as ``(source, path, title)``.
Ordered by ``(source, path)`` — the same order as ``GET /api/docs``.
Module-level (not a method) so unit tests can monkeypatch it.
"""
rows = db.execute(
select(Document.source, Document.path, Document.title).order_by(
Document.source, Document.path
)
).all()
return [(source, path, title) for source, path, title in rows]
def find_document(db: Session, source: str, path: str) -> Document | None:
"""The indexed document at ``(source, path)``, or ``None``.
Module-level (not a method) so unit tests can monkeypatch it.
"""
return db.scalar(
select(Document).where(Document.source == source, Document.path == path)
)
@dataclass
class AgentHolder:
"""Per-turn agent state the API layer reads after the stream (task 04).
``read_docs``: the documents ``read_document`` added to the context,
in read order (deduped — re-reading a document appends nothing).
``tool_calls``: how many tool executions consumed budget; rejected
calls (unknown tool, unknown/missing document, exhausted budget,
already-in-context) do not count. Drives the per-turn log line's
``tool_calls=N`` field (task 04).
"""
read_docs: list[Document] = field(default_factory=list)
tool_calls: int = 0
def _execute_tool(
db: Session,
call: ToolCallPiece,
seed_docs: Sequence[Document],
holder: AgentHolder,
list_left: int,
read_left: int,
) -> tuple[str, int, int]:
"""Execute one tool call server-side (DB only).
Returns ``(result, list_left, read_left)``. Rejected calls consume no
budget; a successful read appends the :class:`Document` to
``holder.read_docs`` and bumps ``holder.tool_calls``.
"""
if call.name == "list_documents":
if list_left <= 0:
return LIST_EXHAUSTED, list_left, read_left
rows = list_catalog(db)
listing = f"{len(rows)} documents:\n" + "\n".join(
f"{source}/{path} — {title}" for source, path, title in rows
)
holder.tool_calls += 1
return listing, list_left - 1, read_left
if call.name == "read_document":
raw_source = call.arguments.get("source")
raw_path = call.arguments.get("path")
source = raw_source.strip() if isinstance(raw_source, str) else ""
path = raw_path.strip() if isinstance(raw_path, str) else ""
if not source or not path:
return MISSING_READ_ARGS, list_left, read_left
known = {(doc.source, doc.path) for doc in (*seed_docs, *holder.read_docs)}
if (source, path) in known:
return ALREADY_IN_CONTEXT, list_left, read_left
if read_left <= 0:
return READ_EXHAUSTED, list_left, read_left
doc = find_document(db, source, path)
if doc is None:
return (
f"No document at {source}/{path} — check the list_documents output.",
list_left,
read_left,
)
holder.read_docs.append(doc)
holder.tool_calls += 1
return f"Document {source}/{path}:\n{doc.content}", list_left, read_left - 1
return UNKNOWN_TOOL, list_left, read_left
async def run_agent(
llm: LLMClient,
db: Session,
*,
system_prompt: str,
user_message: str,
seed_docs: Sequence[Document],
settings: Settings,
holder: AgentHolder,
) -> AsyncIterator[StreamPiece | ToolCallPiece]:
"""Run the grounded-turn tool loop, yielding every stream piece.
Every piece (``thinking`` / ``content`` / tool calls) is yielded as it
arrives; the API layer (task 04) turns tool-call pieces into SSE
``tool`` events. After the loop finishes, *holder* carries the read
documents and the budget-consuming tool count.
``seed_docs`` are the documents the retrieval already put in context
(they shape the *system_prompt* the caller built); re-reading one of
them is rejected as "Already in your context." without spending budget.
"""
messages: list[dict[str, Any]] = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_message},
]
list_left = settings.agent_list_calls
read_left = settings.agent_read_calls
tools: list[dict[str, Any]] | None = AGENT_TOOLS if (list_left or read_left) else None
# Every tool round consumes a budget, so this cap only catches
# pathological streams that keep calling rejected tools (belt and
# braces — the budgets already force the answer after
# list + read rounds).
max_rounds = 2 + settings.agent_list_calls + settings.agent_read_calls
rounds = 0
while True:
calls: list[ToolCallPiece] = []
async for piece in llm.chat_stream(
cast("list[dict[str, str]]", messages), tools=tools
):
if isinstance(piece, ToolCallPiece):
calls.append(piece)
yield piece
if not calls:
return # the answer was streamed
call = calls[0] # a stream can carry several calls; run the first
result, list_left, read_left = _execute_tool(
db, call, seed_docs, holder, list_left, read_left
)
logger.info(
"agent tool=%s args=%s budget list_left=%d read_left=%d",
call.name,
json.dumps(call.arguments, ensure_ascii=False)[:200],
list_left,
read_left,
)
messages.append(
{
"role": "assistant",
"content": None,
"tool_calls": [
{
"id": call.id,
"type": "function",
"function": {
"name": call.name,
"arguments": json.dumps(call.arguments),
},
}
],
}
)
messages.append({"role": "tool", "tool_call_id": call.id, "content": result})
tools = None if (list_left == 0 and read_left == 0) else AGENT_TOOLS
rounds += 1
if rounds >= max_rounds:
logger.warning(
"agent round cap reached (rounds=%d) — forcing a final "
"no-tools answer",
rounds,
)
async for piece in llm.chat_stream(
cast("list[dict[str, str]]", messages), tools=None
):
yield piece
return