All gates are green. Final verification is complete — no fixes were needed; the phase is fully implemented and passing. **Phase 95 final verification report** - Verified all 3 tasks already implemented (task files in `complete/`): read cap + notice + `ToolResultPiece` (task 01), `tool_result` SSE + live/saved/shared marker (task 02), E2E suite (task 03). - Code checks passed: `BOR_READ_MAX_CHARS` (default 128 000, validator), pinned `READ_TRUNCATION_NOTICE` + `TRUNCATION_MARKER`, byte-identical at/under-cap read, holder `read_truncations` (no `tool_calls` impact), piece order (after `tool`, before next round), `ChatToolResultEvent`, `ToolCall` back-compat fields, `app.js` live/restore handlers, `shared.js`, `.truncated-note` CSS, `.env.example` entry, mock-LLM echo script. - **Tests:** `uv run pytest` → 1966 passed; `uv run pytest --cov=app --cov-report=term-missing` → all green, TOTAL **99%** (>90% gate). - **E2E:** `uv run pytest tests/e2e/test_read_truncation_cap.py -v --no-cov` → **3 passed** (frame order + live marker + LLM notice via echo; save→shared fidelity; short-read control). - **Regression (isolated):** `test_agent_document_tools` 4 ✓, `test_chat_history` 5 ✓, `test_share_chat` 4 ✓, `test_big_read_progress` 4 ✓, `test_stop_generation` 3 ✓. - **Lint/types:** `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors, 0 warnings. **Completion criteria:** ① over-cap read → first-cap-chars + marker + pinned notice — ✓ (unit-pinned: at-cap/cap+1/notice tests); ② user marker live/saved/shared — ✓ (E2E + frontend tests); ③ at/under cap byte-identical, no frame — ✓ (unit + control E2E); ④ top-2 `<documents>` retrieval untouched — ✓ (`app/rag/retriever.py` unmodified vs HEAD); ⑤ suite green, >90% coverage, ruff+pyright clean — ✓; ⑥ no completed-phase behavior change — ✓ (all gates green; commit left to harness per pass rules). - No defects found; no changes made this pass. Next pending phase: none in `todo/` (96 is the next free number).
682 lines
25 KiB
Python
682 lines
25 KiB
Python
"""Integration: the agent DB accessors against real Postgres (phase 37;
|
|
the harness-aligned ``ls``/``read``/``grep`` surface, phase 70; the
|
|
drill-down tree ``ls``, phase 94).
|
|
|
|
``_source_document_rows`` must order a source's rows by ``path`` (the
|
|
file lines' catalog order), ``list_source_names`` must resolve the
|
|
registered source names (the registry join), and ``find_document``
|
|
must resolve a hit to the full document row (content included, for the
|
|
never-truncated read) and return ``None`` for unknown pairs. Phase 70:
|
|
the ``ls``/``read``/``grep`` tools are pinned here too — the locked
|
|
parameter shape in ``AGENT_TOOLS``, and scripted ``ToolCallPiece``s
|
|
executed through ``run_agent`` against the real DB. Phase 94: the
|
|
drill-down ``ls`` against the REAL tables — ``ls()`` lists the
|
|
registered sources (registry order, recursive counts, stored
|
|
source-root summaries from ``folder_summaries``), ``ls(source)`` /
|
|
``ls(source/folder)`` list one folder level (the SQL prefix logic:
|
|
subfolders = slash-boundary prefixes, counts = the recursive subtree,
|
|
file lines in catalog order, capped at 50 + the grep-pointer note),
|
|
and the refusals (unknown source segment → the no-source refusal; an
|
|
unknown folder → NOT-A_FOLDER with the parent's subfolders).
|
|
``read`` runs on the canonical combined ``source/path`` form
|
|
(first-slash split; a bare source name and an unknown identity get the
|
|
no-document refusal), and ``grep`` (``all_documents`` for a whole-KB
|
|
search, ``find_document`` for a scoped one) — both byte-identical
|
|
across the phase-94 change.
|
|
|
|
Requires: podman compose up -d db
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import uuid
|
|
from collections.abc import AsyncIterator, Iterator
|
|
from copy import deepcopy
|
|
from typing import TYPE_CHECKING, Any, cast
|
|
|
|
import pytest
|
|
from sqlalchemy import delete, text
|
|
from sqlalchemy.orm import Session
|
|
|
|
from app.config import Settings
|
|
from app.models import Document, FolderSummary, GitSource
|
|
from app.rag import agent
|
|
from app.rag.agent import AGENT_TOOLS, AgentHolder, run_agent
|
|
from app.rag.llm import (
|
|
LLMClient,
|
|
RetryPiece,
|
|
StreamPiece,
|
|
ToolCallPiece,
|
|
ToolResultPiece,
|
|
)
|
|
|
|
if TYPE_CHECKING:
|
|
from app.rag.scaffolding import ScaffoldingFilter
|
|
|
|
|
|
def _doc(db: Session, source: str, path: str, title: str, content: str) -> Document:
|
|
doc = Document(
|
|
id=uuid.uuid4(),
|
|
source=source,
|
|
path=path,
|
|
full_path=f"/tmp/{source}/{path}",
|
|
title=title,
|
|
content=content,
|
|
content_hash="0" * 64,
|
|
)
|
|
db.add(doc)
|
|
return doc
|
|
|
|
|
|
@pytest.fixture()
|
|
def kb(db) -> Iterator[None]:
|
|
"""Fresh documents + folder_summaries tables (chunks first — the FK)
|
|
for these accessors (phase 94: the drill-down ``ls`` reads the
|
|
stored summaries too)."""
|
|
db.execute(text("TRUNCATE chunks, documents, folder_summaries"))
|
|
db.commit()
|
|
yield
|
|
db.execute(text("TRUNCATE chunks, documents, folder_summaries"))
|
|
db.commit()
|
|
|
|
|
|
@pytest.fixture()
|
|
def registry(db) -> Iterator[None]:
|
|
"""A FRESH two-source registry (phase 94): the drill-down ``ls``
|
|
top level IS the registry, so the table is truncated and re-seeded
|
|
around the tests in a controlled ``(added_at, id)`` order —
|
|
``Deployments`` before ``Homelab`` (the top-level listing order)."""
|
|
db.execute(text("TRUNCATE git_sources"))
|
|
db.commit()
|
|
db.add(GitSource(url="https://github.com/reese/Deployments.git", kind="git"))
|
|
db.commit()
|
|
db.add(GitSource(url="https://github.com/reese/Homelab.git", kind="git"))
|
|
db.commit()
|
|
yield
|
|
db.execute(text("TRUNCATE git_sources"))
|
|
db.commit()
|
|
|
|
|
|
@pytest.fixture()
|
|
def src(db) -> Iterator[GitSource]:
|
|
"""One registered git source — the scoped ``ls`` source-name check
|
|
reads the real registry, so the row is inserted and deleted around
|
|
the tests (``repo_name`` resolves the URL to ``Homelab``)."""
|
|
row = GitSource(url="https://github.com/reese/Homelab.git", kind="git")
|
|
db.add(row)
|
|
db.commit()
|
|
yield row
|
|
db.execute(delete(GitSource).where(GitSource.id == row.id))
|
|
db.commit()
|
|
|
|
|
|
def test_source_document_rows_order_by_path_within_the_source(kb, db) -> None:
|
|
"""Phase 94: the file lines' order — the source's rows in ``path``
|
|
order (the old ``list_catalog``'s per-source ordering, now the
|
|
``ls`` folder-level accessor's contract; a different source's rows
|
|
never leak in)."""
|
|
_doc(db, "Zeta", "b/second.md", "Zeta B", "ZB")
|
|
_doc(db, "Zeta", "a/first.md", "Zeta A", "ZA")
|
|
_doc(db, "Alpha", "c/third.md", "Alpha C", "AC")
|
|
db.commit()
|
|
|
|
assert agent._source_document_rows(db, "Zeta") == [
|
|
("a/first.md", "Zeta A"),
|
|
("b/second.md", "Zeta B"),
|
|
]
|
|
|
|
|
|
def test_source_document_rows_is_empty_without_rows(kb, db) -> None:
|
|
assert agent._source_document_rows(db, "Zeta") == []
|
|
|
|
|
|
def test_list_source_names_resolves_registry_rows(db) -> None:
|
|
"""The real registry: git names resolve through the import pipeline's
|
|
``repo_name`` (trailing ``.git`` stripped); a second row resolving to
|
|
the same name (the phase-69 sibling case) is listed once."""
|
|
a = GitSource(url="https://github.com/reese/Homelab.git", kind="git")
|
|
b = GitSource(url="https://github.com/reese/Homelab", kind="git") # sibling
|
|
c = GitSource(url="https://e.com/deployments", kind="git")
|
|
db.add_all([a, b, c])
|
|
db.commit()
|
|
try:
|
|
assert agent.list_source_names(db).count("Homelab") == 1 # deduped
|
|
assert "deployments" in agent.list_source_names(db)
|
|
finally:
|
|
db.execute(delete(GitSource).where(GitSource.id.in_([a.id, b.id, c.id])))
|
|
db.commit()
|
|
|
|
|
|
def test_find_document_hit_returns_full_row(kb, db) -> None:
|
|
created = _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
|
|
db.commit()
|
|
|
|
found = agent.find_document(db, "Alpha", "deep/nested/doc.md")
|
|
assert found is not None
|
|
assert found.id == created.id
|
|
assert found.source == "Alpha"
|
|
assert found.path == "deep/nested/doc.md"
|
|
assert found.title == "The Doc"
|
|
assert found.content == "FULL-TEXT" # the read tool feeds this, untruncated
|
|
|
|
|
|
def test_find_document_none_for_unknown_pairs(kb, db) -> None:
|
|
_doc(db, "Alpha", "x.md", "X", "X-CONTENT")
|
|
db.commit()
|
|
|
|
assert agent.find_document(db, "Alpha", "nope.md") is None # wrong path
|
|
assert agent.find_document(db, "Beta", "x.md") is None # wrong source
|
|
assert agent.find_document(db, "nope", "nope.md") is None # nothing at all
|
|
|
|
|
|
# ---------- AGENT_TOOLS surface (phase 70: ls / read / grep) ----------
|
|
|
|
|
|
def test_agent_tools_offers_the_harness_aligned_surface() -> None:
|
|
by_name = {t["function"]["name"]: t for t in AGENT_TOOLS}
|
|
assert list(by_name) == [ # the harness order, phase 70
|
|
"ls",
|
|
"read",
|
|
"grep",
|
|
]
|
|
ls = by_name["ls"]["function"]["parameters"]
|
|
assert ls["type"] == "object"
|
|
assert ls["required"] == [] # path is optional
|
|
assert set(ls["properties"]) == {"path"}
|
|
read = by_name["read"]["function"]["parameters"]
|
|
assert read["type"] == "object"
|
|
assert read["required"] == ["path"]
|
|
assert set(read["properties"]) == {"path"}
|
|
grep = by_name["grep"]["function"]["parameters"]
|
|
assert grep["type"] == "object"
|
|
assert grep["required"] == ["pattern"]
|
|
assert set(grep["properties"]) == {"pattern", "path"}
|
|
assert all(p["type"] == "string" for p in grep["properties"].values())
|
|
|
|
|
|
class ScriptedToolLLM:
|
|
"""One scripted tool-call stream, then one canned answer stream.
|
|
Records every ``chat_stream`` request's messages and tools."""
|
|
|
|
def __init__(self, call: ToolCallPiece) -> None:
|
|
self.call = call
|
|
self.requests: list[
|
|
tuple[list[dict[str, Any]], list[dict[str, Any]] | None]
|
|
] = []
|
|
|
|
async def chat_stream(
|
|
self,
|
|
messages: list[dict[str, str]],
|
|
tools: list[dict[str, Any]] | None = None,
|
|
scaffolding: ScaffoldingFilter | None = None, # phase 71 pass-through
|
|
) -> AsyncIterator[StreamPiece | ToolCallPiece]:
|
|
self.requests.append((deepcopy(messages), deepcopy(tools)))
|
|
if len(self.requests) == 1:
|
|
yield self.call
|
|
else:
|
|
yield StreamPiece("content", "ans")
|
|
|
|
|
|
def _settings(**kwargs: Any) -> Settings:
|
|
kwargs.setdefault("_env_file", None)
|
|
return Settings(**kwargs) # pyright: ignore[reportCallIssue]
|
|
|
|
|
|
class ScriptedToolCallsLLM:
|
|
"""N scripted tool-call rounds (one ``ToolCallPiece`` each), then one
|
|
canned answer; records every request's messages and tools (the
|
|
phase-72 task-02 two-round self-correction cases: the refusal round,
|
|
then the corrected call)."""
|
|
|
|
def __init__(self, calls: list[ToolCallPiece]) -> None:
|
|
self.calls = calls
|
|
self.requests: list[
|
|
tuple[list[dict[str, Any]], list[dict[str, Any]] | None]
|
|
] = []
|
|
|
|
async def chat_stream(
|
|
self,
|
|
messages: list[dict[str, str]],
|
|
tools: list[dict[str, Any]] | None = None,
|
|
scaffolding: ScaffoldingFilter | None = None,
|
|
) -> AsyncIterator[StreamPiece | ToolCallPiece]:
|
|
self.requests.append((deepcopy(messages), deepcopy(tools)))
|
|
index = len(self.requests) - 1
|
|
if index < len(self.calls):
|
|
yield self.calls[index]
|
|
else:
|
|
yield StreamPiece("content", "ans")
|
|
|
|
|
|
def _run_call(
|
|
db: Session, name: str, arguments: dict[str, Any]
|
|
) -> tuple[AgentHolder, ScriptedToolLLM]:
|
|
"""Drive one scripted tool call through ``run_agent``."""
|
|
holder = AgentHolder()
|
|
llm = ScriptedToolLLM(ToolCallPiece(id="call_1", name=name, arguments=arguments))
|
|
asyncio.run(_consume(cast("LLMClient", llm), db, holder))
|
|
return holder, llm
|
|
|
|
|
|
async def _consume(
|
|
llm: LLMClient, db: Session, holder: AgentHolder
|
|
) -> list[StreamPiece | ToolCallPiece | RetryPiece | ToolResultPiece]:
|
|
out: list[StreamPiece | ToolCallPiece | RetryPiece | ToolResultPiece] = []
|
|
async for piece in run_agent(
|
|
llm,
|
|
db,
|
|
system_prompt="SYSTEM_PROMPT",
|
|
user_message="QUESTION",
|
|
seed_docs=[],
|
|
settings=_settings(),
|
|
holder=holder,
|
|
):
|
|
out.append(piece)
|
|
return out
|
|
|
|
|
|
# ---------- ls (the drill-down tree, phase 94 — the real registry + DB) ----------
|
|
|
|
|
|
def test_ls_top_level_lists_registered_sources_through_run_agent(
|
|
kb, registry, db
|
|
) -> None:
|
|
"""No path: the TOP level against the real tables — registry order
|
|
(``(added_at, id)`` — Deployments before Homelab), recursive counts
|
|
(all of a source's documents), the stored source-root summary
|
|
(``folder_path = ''``) shown only when stored."""
|
|
_doc(db, "Deployments", "a/one.md", "A1", "A1-CONTENT")
|
|
_doc(db, "Homelab", "x.md", "X", "X-CONTENT")
|
|
_doc(db, "Homelab", "y/z.md", "Z", "Z-CONTENT")
|
|
db.add(FolderSummary(source="Homelab", folder_path="", summary="Home lab notes."))
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {})
|
|
|
|
assert llm.requests[0][1] == AGENT_TOOLS
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"2 sources:\n"
|
|
"\n"
|
|
"Deployments — 1 documents\n"
|
|
"Homelab — 2 documents\n"
|
|
" Home lab notes."
|
|
)
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == []
|
|
|
|
|
|
def test_ls_top_level_empty_registry_through_run_agent(
|
|
kb, db, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
"""No registered sources: the top level is the header line alone
|
|
(``0 sources:`` — the old ``0 documents:`` behavior preserved in
|
|
spirit), still counted. The env fallback (``BOR_GIT_SOURCES`` — the
|
|
operator's ``.env`` may name sources) is emptied for the test, so
|
|
the registry is genuinely empty."""
|
|
import app.rag.git_sources as git_sources_mod
|
|
|
|
db.execute(text("TRUNCATE git_sources"))
|
|
db.commit()
|
|
monkeypatch.setattr(
|
|
git_sources_mod,
|
|
"get_settings",
|
|
lambda: _settings(git_sources=""),
|
|
)
|
|
_doc(db, "Orphan", "a.md", "A", "A-CONTENT") # indexed but unregistered
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {})
|
|
assert llm.requests[1][0][3]["content"] == "0 sources:"
|
|
assert holder.tool_calls == 1
|
|
|
|
|
|
def test_ls_source_scope_lists_root_folder_through_run_agent(kb, registry, db) -> None:
|
|
"""A registered source name: the source's ROOT folder — the direct
|
|
subfolders (path order, recursive counts, stored summaries attached)
|
|
+ the root's own file lines in catalog order — against the real
|
|
tables; a registered source with no documents lists its header
|
|
line alone."""
|
|
_doc(db, "Homelab", "backups/cron.md", "Cron", "CRON")
|
|
_doc(db, "Homelab", "backups/restic.md", "Restic", "RESTIC")
|
|
_doc(db, "Homelab", "networking/lan.md", "LAN", "LAN")
|
|
_doc(db, "Homelab", "readme.md", "Readme", "README")
|
|
db.add(
|
|
FolderSummary(
|
|
source="Homelab", folder_path="backups", summary="Backup notes."
|
|
)
|
|
)
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "Homelab"})
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"Homelab — 1 documents, 2 folders:\n"
|
|
"\n"
|
|
" backups/ — 2 documents: Backup notes.\n"
|
|
" networking/ — 1 documents\n"
|
|
"\n"
|
|
"source: Homelab | path: readme.md | title: Readme"
|
|
)
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == []
|
|
|
|
# A registered source with no documents: the header line alone.
|
|
holder0, llm0 = _run_call(db, "ls", {"path": "Deployments"})
|
|
assert llm0.requests[1][0][3]["content"] == "Deployments — 0 documents, 0 folders:"
|
|
assert holder0.tool_calls == 1
|
|
|
|
|
|
def test_ls_nested_folder_scope_drills_one_level_through_run_agent(
|
|
kb, registry, db
|
|
) -> None:
|
|
"""A ``source/folder`` path: that folder's subfolders + own file
|
|
lines (identity = ``source/folder``) — the drill-down against the
|
|
real tables."""
|
|
_doc(db, "Homelab", "networking/lan/a.md", "A", "A")
|
|
_doc(db, "Homelab", "networking/lan/b.md", "B", "B")
|
|
_doc(db, "Homelab", "networking/vpn/c.md", "C", "C")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "Homelab/networking"})
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"Homelab/networking — 0 documents, 2 folders:\n"
|
|
"\n"
|
|
" networking/lan/ — 2 documents\n"
|
|
" networking/vpn/ — 1 documents"
|
|
)
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == []
|
|
|
|
# One level deeper.
|
|
holder2, llm2 = _run_call(db, "ls", {"path": "Homelab/networking/lan"})
|
|
assert llm2.requests[1][0][3]["content"] == (
|
|
"Homelab/networking/lan — 2 documents, 0 folders:\n"
|
|
"\n"
|
|
"source: Homelab | path: networking/lan/a.md | title: A\n"
|
|
"source: Homelab | path: networking/lan/b.md | title: B"
|
|
)
|
|
assert holder2.tool_calls == 1
|
|
|
|
|
|
def test_ls_folder_file_cap_through_run_agent(kb, registry, db) -> None:
|
|
"""The cap end-to-end: 51 direct files in one folder cost 50 file
|
|
lines + the deterministic grep-pointer note, never 51."""
|
|
for i in range(51):
|
|
_doc(db, "Homelab", f"big/f{i:03d}.md", f"T{i}", "BODY")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "Homelab/big"})
|
|
|
|
content = llm.requests[1][0][3]["content"]
|
|
lines = content.splitlines()
|
|
assert lines[0] == "Homelab/big — 51 documents, 0 folders:"
|
|
assert lines[2] == "source: Homelab | path: big/f000.md | title: T0"
|
|
assert lines[51] == "source: Homelab | path: big/f049.md | title: T49"
|
|
assert lines[52] == (
|
|
"…and 1 more documents in this folder — use grep (pattern) to "
|
|
"find a specific one."
|
|
)
|
|
assert len(lines) == 53
|
|
assert holder.tool_calls == 1
|
|
|
|
|
|
def test_ls_scoped_unknown_source_refused_through_run_agent(kb, src, db) -> None:
|
|
"""A ``path`` without ``/`` matching no source name is a refusal —
|
|
the extended line with the teaching parenthetical (phase 72, the
|
|
prefix byte-identical to the pre-phase-72 line); still not counted."""
|
|
_doc(db, "Homelab", "a.md", "A", "A-CONTENT")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "Ghost"})
|
|
|
|
assert (
|
|
llm.requests[1][0][3]["content"]
|
|
== agent.NO_SOURCE_NOT_A_DIRECTORY.format(scope="Ghost")
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
|
|
|
|
def test_ls_path_like_scope_unknown_source_gets_no_source_refusal(kb, src, db) -> None:
|
|
"""Phase 94: a ``/`` now names a folder — the phase-72 document-path
|
|
teaching is DELETED; a ``source/…`` argument whose FIRST segment
|
|
names no registered source gets the no-source refusal (the segment
|
|
echoed), not counted, the tools stay offered."""
|
|
_doc(db, "Homelab", "a.md", "A", "A-CONTENT")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "app/rag/importer.py"})
|
|
|
|
assert (
|
|
llm.requests[1][0][3]["content"]
|
|
== agent.NO_SOURCE_NOT_A_DIRECTORY.format(scope="app")
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
assert llm.requests[1][1] == AGENT_TOOLS # rejected → tools stay offered
|
|
|
|
|
|
def test_ls_unknown_folder_gets_not_a_folder_with_parents_subfolders(
|
|
kb, src, db,
|
|
) -> None:
|
|
"""Phase 94: a folder segment matching no indexed prefix gets the
|
|
NOT-A_FOLDER teaching — the argument echoed, the source named, its
|
|
DIRECT subfolders listed (the self-correction list), not counted,
|
|
the tools stay offered."""
|
|
_doc(db, "Homelab", "backups/cron.md", "Cron", "CRON")
|
|
_doc(db, "Homelab", "containers/caddy.md", "Caddy", "CADDY")
|
|
_doc(db, "Homelab", "networking/lan.md", "LAN", "LAN")
|
|
_doc(db, "Homelab", "readme.md", "Readme", "README")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "ls", {"path": "Homelab/netwoking"})
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"'Homelab/netwoking' is not a folder — Homelab has: "
|
|
"backups/ containers/ networking/"
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
assert llm.requests[1][1] == AGENT_TOOLS # rejected → tools stay offered
|
|
|
|
|
|
# ---------- read (the canonical combined source/path form) ----------
|
|
|
|
|
|
def test_read_combined_path_through_run_agent(kb, db) -> None:
|
|
"""The combined ``source/path`` identity resolves at the FIRST slash
|
|
against the REAL table (a path with further slashes included): the
|
|
read executes, the holder records the row, the result header carries
|
|
the true source/path."""
|
|
created = _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "read", {"path": "Alpha/deep/nested/doc.md"})
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"Document Alpha/deep/nested/doc.md:\nFULL-TEXT"
|
|
)
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == [created]
|
|
|
|
|
|
def test_read_bare_source_name_refused_through_run_agent(kb, db) -> None:
|
|
"""A bare source name (no '/') can never be a document — the
|
|
no-document refusal echoing the argument as passed; the old
|
|
split-teaching refusal is gone (phase 70)."""
|
|
_doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "read", {"path": "Alpha"})
|
|
|
|
assert (
|
|
llm.requests[1][0][3]["content"] == "No document at 'Alpha' — check the ls output."
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
|
|
|
|
def test_read_unknown_combined_path_refused_through_run_agent(kb, db) -> None:
|
|
"""A combined identity that matches NOTHING — not a document and not
|
|
any indexed document's ``path`` (zero candidates) — gets today's
|
|
no-document refusal byte-identical (the argument echoed as passed —
|
|
the model sees its own form)."""
|
|
_doc(db, "Alpha", "x.md", "X", "X-CONTENT")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "read", {"path": "Alpha/nope/deep.md"})
|
|
|
|
assert (
|
|
llm.requests[1][0][3]["content"]
|
|
== "No document at 'Alpha/nope/deep.md' — check the ls output."
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
|
|
|
|
def test_read_bare_path_single_source_suggestion_then_corrected_read(kb, db) -> None:
|
|
"""Phase 72, task 02: a bare path under ONE source (exact ``path``
|
|
match, the source prefix missing) → the single-identity suggestion
|
|
(a refusal — not counted); the scripted corrected call (round 2, the
|
|
suggested combined identity) then succeeds against real Postgres —
|
|
the two-round self-correction."""
|
|
created = _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
|
|
db.commit()
|
|
|
|
llm = ScriptedToolCallsLLM(
|
|
[
|
|
ToolCallPiece(
|
|
id="call_1", name="read", arguments={"path": "deep/nested/doc.md"}
|
|
),
|
|
ToolCallPiece(
|
|
id="call_2",
|
|
name="read",
|
|
arguments={"path": "Alpha/deep/nested/doc.md"},
|
|
),
|
|
]
|
|
)
|
|
holder = AgentHolder()
|
|
asyncio.run(_consume(cast("LLMClient", llm), db, holder))
|
|
|
|
# Round 1: the bare path resolves to no combined identity, but it IS
|
|
# the indexed document's path — the refusal names the one combined
|
|
# identity to use (not counted, the tools stay offered).
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"No document at 'deep/nested/doc.md' — "
|
|
"did you mean 'Alpha/deep/nested/doc.md'?"
|
|
)
|
|
assert llm.requests[1][1] == AGENT_TOOLS
|
|
# Round 2: the corrected combined identity succeeds — the full
|
|
# content, the holder records the row, and it counts.
|
|
assert llm.requests[2][0][5]["content"] == (
|
|
"Document Alpha/deep/nested/doc.md:\nFULL-TEXT"
|
|
)
|
|
assert llm.requests[2][1] == AGENT_TOOLS
|
|
assert holder.read_docs == [created]
|
|
assert holder.tool_calls == 1 # only the corrected read executed
|
|
|
|
|
|
def test_read_bare_path_two_sources_one_of_suggestion_then_corrected_read(
|
|
kb, db,
|
|
) -> None:
|
|
"""Phase 72, task 02: the same bare path under TWO sources → the
|
|
``one of`` line (up to ``SUGGESTION_LIMIT`` identities, catalog
|
|
order — Alpha before Beta); the scripted corrected call (round 2,
|
|
the first suggested identity) then succeeds."""
|
|
a = _doc(db, "Alpha", "shared/x.md", "Alpha X", "A-TEXT")
|
|
_doc(db, "Beta", "shared/x.md", "Beta X", "B-TEXT")
|
|
db.commit()
|
|
|
|
llm = ScriptedToolCallsLLM(
|
|
[
|
|
ToolCallPiece(id="call_1", name="read", arguments={"path": "shared/x.md"}),
|
|
ToolCallPiece(
|
|
id="call_2", name="read", arguments={"path": "Alpha/shared/x.md"}
|
|
),
|
|
]
|
|
)
|
|
holder = AgentHolder()
|
|
asyncio.run(_consume(cast("LLMClient", llm), db, holder))
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"No document at 'shared/x.md' — did you mean one of: "
|
|
"'Alpha/shared/x.md', 'Beta/shared/x.md'?"
|
|
)
|
|
assert llm.requests[2][0][5]["content"] == "Document Alpha/shared/x.md:\nA-TEXT"
|
|
assert holder.read_docs == [a]
|
|
assert holder.tool_calls == 1 # only the corrected read executed
|
|
|
|
|
|
# ---------- grep (the phase-68 A5 contract under the new name) ----------
|
|
|
|
|
|
def test_all_documents_orders_by_source_then_path(kb, db) -> None:
|
|
_doc(db, "Zeta", "b/second.md", "Zeta B", "ZB")
|
|
_doc(db, "Zeta", "a/first.md", "Zeta A", "ZA")
|
|
_doc(db, "Alpha", "c/third.md", "Alpha C", "AC")
|
|
db.commit()
|
|
|
|
docs = agent.all_documents(db)
|
|
assert [(d.source, d.path) for d in docs] == [
|
|
("Alpha", "c/third.md"),
|
|
("Zeta", "a/first.md"),
|
|
("Zeta", "b/second.md"),
|
|
]
|
|
assert [d.content for d in docs] == ["AC", "ZA", "ZB"] # full rows
|
|
|
|
|
|
def test_grep_whole_kb_through_run_agent(kb, db) -> None:
|
|
_doc(db, "Beta", "b/two.md", "Two", "no hit\nNEEDLE in two\nlast")
|
|
_doc(db, "Alpha", "a/one.md", "One", "first\nneedle in one\nthird")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "grep", {"pattern": "needle"})
|
|
|
|
# Offered: the first request carries AGENT_TOOLS (the 3-tool list).
|
|
assert llm.requests[0][1] == AGENT_TOOLS
|
|
# Executed against the real DB: catalog order, grep-style lines.
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"Alpha/a/one.md:2: needle in one\n"
|
|
"Beta/b/two.md:2: NEEDLE in two"
|
|
)
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == [] # locked A5: grep adds no context
|
|
|
|
|
|
def test_grep_scoped_through_run_agent(kb, db) -> None:
|
|
_doc(db, "Alpha", "a/one.md", "One", "first\nNeedle here\nthird")
|
|
_doc(db, "Beta", "b/two.md", "Two", "NEEDLE too")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "grep", {"pattern": "needle", "path": "Alpha/a/one.md"})
|
|
|
|
# Only the named document is searched — the other one's hit is absent.
|
|
assert llm.requests[1][0][3]["content"] == "Alpha/a/one.md:2: Needle here"
|
|
assert holder.tool_calls == 1
|
|
assert holder.read_docs == []
|
|
|
|
|
|
def test_grep_scoped_missing_doc_refused_through_run_agent(kb, db) -> None:
|
|
"""A scoped ``grep`` miss that matches no indexed document's ``path``
|
|
(zero candidates) keeps today's line byte-identical — a refusal,
|
|
not counted."""
|
|
_doc(db, "Alpha", "a/one.md", "One", "nothing")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "grep", {"pattern": "needle", "path": "Alpha/ghost.md"})
|
|
|
|
assert (
|
|
llm.requests[1][0][3]["content"]
|
|
== "No document at 'Alpha/ghost.md' — check the ls output."
|
|
)
|
|
assert holder.tool_calls == 0 and holder.read_docs == []
|
|
|
|
|
|
def test_grep_no_matches_through_run_agent(kb, db) -> None:
|
|
_doc(db, "Alpha", "a/one.md", "One", "nothing matching")
|
|
db.commit()
|
|
|
|
holder, llm = _run_call(db, "grep", {"pattern": "zebra"})
|
|
|
|
assert llm.requests[1][0][3]["content"] == (
|
|
"No matches for 'zebra' in the knowledge base."
|
|
)
|
|
assert holder.tool_calls == 1 # an executed grep with zero hits
|
|
assert holder.read_docs == []
|