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
+201
View File
@@ -0,0 +1,201 @@
"""Unit: the phase-37 "calling tool" frontend contract (task 05).
No new Python app logic exists for this task — the behavior lives in
``frontend/assets/app.js`` + ``styles.css`` and is E2E-gated by the story
suite (task 06). Like the other frontend-adjacent unit files, this module
pins the JS/CSS markers the story depends on, so a silent regression in
the tool branch, the persistence shape, or the tool-line styling is
caught without a browser.
"""
from __future__ import annotations
import re
from pathlib import Path
FRONTEND = Path(__file__).resolve().parents[2] / "frontend"
APP_JS = FRONTEND / "assets" / "app.js"
STYLES_CSS = FRONTEND / "assets" / "styles.css"
def _js() -> str:
return APP_JS.read_text(encoding="utf-8")
def _css() -> str:
return STYLES_CSS.read_text(encoding="utf-8")
def test_tool_branch_is_a_first_class_turn_branch() -> None:
"""The turn handler must branch on `tool` frames BETWEEN the
thinking and delta branches: the stream stays alive (guard clears),
the brain wrap is created on demand, and the label state is
applied only while the UI state is still "thinking" (a late frame
after the first delta just appends the line — never a crash)."""
js = _js()
thinking_idx = js.find('ev.type === "thinking"')
tool_idx = js.find('ev.type === "tool"')
delta_idx = js.find('ev.type === "delta"')
assert -1 < thinking_idx < tool_idx < delta_idx, (
"the turn handler must branch on tool frames"
)
branch = js[tool_idx:delta_idx]
assert "toolAcc.push" in branch, "every tool frame is recorded for persistence"
assert "clearTurnTimeout()" in branch, "a tool frame proves the stream is alive"
assert 'addMessage("brain", "")' in branch, "first frame creates the brain wrap"
assert "uiState === UI_STATE.thinking" in branch, (
"label updates only while the state is still thinking"
)
assert "appendToolLine(wrap, name, argument)" in branch
# No setUiState in the branch: the state stays "thinking" (never stale).
assert "setUiState" not in branch, (
"the tool branch must keep uiState=thinking (button stays disabled)"
)
def test_calling_tool_label_strings() -> None:
"""The 'calling tool' label strings the story keys off: the button
text and the status/typing-indicator labels (plain literals —
phase 39 centralizes brand strings; no helper here)."""
js = _js()
tool_idx = js.find('ev.type === "tool"')
delta_idx = js.find('ev.type === "delta"')
branch = js[tool_idx:delta_idx]
assert '"Calling tool…"' in branch, "the button carries the calling-tool text"
assert '"Brain of Reese is listing documents"' in branch
assert "Brain of Reese is reading ${argument}" in branch
assert "sendStatus.textContent = toolStatus" in branch, (
"the #send-status live region announces what Brain is doing"
)
assert 'setAttribute("aria-label", toolStatus)' in branch, (
"the typing indicator label follows the tool state"
)
# The elapsed-seconds hint keeps running through tool frames: the
# branch must not stop/restart the clock.
assert "stopThinkingClock" not in branch
assert "startThinkingClock" not in branch
def test_tool_lines_render_into_the_bubble_wrap() -> None:
"""appendToolLine: first frame creates the .tool-calls list (role=list
+ accessible name) BEFORE the bubble — below an existing Thinking
block — and each line is a .tool-call listitem with the exact marks:
🔎 Listing documents / 📄 Reading <code>path</code>. The path goes
through textContent (storage can never inject HTML)."""
js = _js()
fn = js.find("function appendToolLine")
assert fn != -1, "appendToolLine must exist"
body = js[fn : js.find("\n}\n", fn)]
assert 'querySelector(".tool-calls")' in body, "idempotent per wrap"
assert 'className = "tool-calls"' in body
assert 'setAttribute("role", "list")' in body
assert 'setAttribute("aria-label", "Tool calls")' in body
assert 'insertBefore(container, body.querySelector(".bubble"))' in body, (
"the list sits ABOVE the answer"
)
assert 'className = "tool-call"' in body
assert 'setAttribute("role", "listitem")' in body
assert 'line.textContent = "📄 Reading "' in body
assert 'line.textContent = "🔎 Listing documents"' in body
assert "code.textContent = argument" in body, (
"the path is data — textContent, never innerHTML"
)
assert "name === \"read_document\" && argument" in body
def test_tool_branch_is_append_only_and_interleaving_safe() -> None:
"""Append-only, the same rule as thinking: multiple calls append
multiple lines in order, and a tool frame after the first delta
(should not happen in v1) still appends — the branch has no early
return gated on acc/delta state."""
js = _js()
tool_idx = js.find('ev.type === "tool"')
delta_idx = js.find('ev.type === "delta"')
branch = js[tool_idx:delta_idx]
assert "if (aborted) return" not in branch, (
"the aborted guard lives at the dispatch top, not per branch"
)
assert "acc" not in branch.split("appendToolLine")[0].replace("toolAcc", ""), (
"the tool branch must not depend on accumulated answer text"
)
def test_tool_frames_persist_next_to_thinking() -> None:
"""The `done` save point gains an optional `tools` key next to
`thinking` (empty turns persist exactly as before — `undefined`
drops the key from the JSON), and the accumulator is turn-scoped
in handleSend."""
js = _js()
assert "let toolAcc = []" in js
done_idx = js.find('ev.type === "done"')
error_idx = js.find('ev.type === "error"')
assert -1 < done_idx < error_idx
done_block = js[done_idx:error_idx]
assert "thinking: thinkingAcc || undefined" in done_block
assert "tools: toolAcc.length ? toolAcc : undefined" in done_block, (
"tools persisted next to thinking, optional like it"
)
def test_tool_lines_re_render_on_restore() -> None:
"""Phase 14 convention: a stored brain record with `tools` re-renders
the lines on load through the SAME append helper (after the thinking
re-render, before the deflected/sources additions)."""
js = _js()
fn = js.find("function renderStoredMessage")
assert fn != -1
end = js.find("function restoreConversation")
body = js[fn:end]
assert "Array.isArray(m.tools)" in body
assert "appendToolLine(wrap, t.name, arg)" in body
thinking_restore = body.find("if (m.thinking)")
tools_restore = body.find("Array.isArray(m.tools)")
assert -1 < thinking_restore < tools_restore, (
"tools restore sits after the thinking restore (same order as live)"
)
assert "typeof t.name !== \"string\"" in body, "malformed entries skipped"
def test_thinking_block_stays_on_top_of_tool_lines() -> None:
"""If a tool frame precedes the first thinking frame, the Thinking
block is still created ABOVE the tool lines (scratchpad on top),
not below them."""
js = _js()
fn = js.find("function ensureThinkingBlock")
assert fn != -1
body = js[fn : js.find("\n}\n", fn)]
assert 'querySelector(".tool-calls")' in body, (
"the thinking anchor must account for existing tool lines"
)
assert 'querySelector(".bubble")' in body
assert "insertBefore" in body
assert "block.open = true" in body
def test_tool_call_style_is_accent_and_contrast_safe() -> None:
"""styles.css: .tool-call is an inline row with the accent palette
(distinct from the brand-ink Thinking block) and mono `code` styling
for the path; the wrapper stacks lines without shifting the column."""
css = _css()
assert ".tool-calls" in css
assert ".tool-call" in css
m = re.search(r"\.tool-call \{([^}]*)\}", css)
assert m, "the .tool-call rule must exist"
row = m.group(1)
assert "display: flex" in row, "inline row: icon + text"
assert "var(--accent-ink)" in row, (
"accent color distinguishes it from the thinking block (≈10.4:1 on surface)"
)
assert "var(--accent-line)" in row, "accent left border"
code = re.search(r"\.tool-call code \{([^}]*)\}", css)
assert code, "the path `code` must be styled"
assert "var(--mono)" in code.group(1)
assert "var(--ink)" in code.group(1) # ≈11.5:1 on --brand-soft
assert "gap" in css.split(".tool-calls {")[1].split("}")[0], (
"lines stack with a gap — append-only, no reflow"
)
def test_no_cdn_added() -> None:
"""AGENTS.md rule 6: the tool state adds no external script/link."""
index = (FRONTEND / "index.html").read_text(encoding="utf-8")
assert 'src="http' not in index and 'href="http' not in index