Experimental/brain-of-reese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(agent): align the document tools with the harness-trained shape — ls, read(path), grep(pattern, path?)

Browse Source
This commit is contained in:
ducoterra
2026-09-03 11:17:47 -04:00
parent 16f1cfbcaf
commit 801639efcc
55 changed files with 4031 additions and 1466 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/e2e/test_agent_unlimited_tools.py
+24 -18
View File
@@ -9,16 +9,20 @@ MOCK-ONLY suite: ``E2E_REAL_LLM=1`` is not supported — the gate is the
deterministic MULTI-READ marker flow in ``tests/e2e/mock_llm.py`` (user
message contains BOTH ``use your tools`` (``TOOLS_TRIGGER``) and ``read
two documents`` (``MULTI_READ_TRIGGER``) **and** the system prompt
carries the ``<tools>`` section of the HIGH prompt):
carries the ``<tools>`` section of the HIGH prompt; phase 70: the flow
emits the harness-aligned names — ``ls``, then ``read`` on the JOINED
combined ``source/path`` of each catalog line):
1. request 1 (``tools`` offered, no tool results yet) → streams ONLY
``tool_calls`` deltas calling ``list_documents`` (id ``call_0``);
2. request 2 (the ``tool``-role catalog result) → ``read_document`` on
the FIRST catalog line (id ``call_1``);
3. request 3 (one ``tool``-role read result) → ``read_document`` on the
SECOND catalog line (id ``call_2``) — the pre-phase-45 per-tool
budgets would have refused exactly this second read (``No reading
budget left — answer with what you have.``);
``tool_calls`` deltas calling ``ls`` (id ``call_0``);
2. request 2 (the ``tool``-role catalog result) → ``read`` on the
JOINED combined ``source/path`` of the FIRST catalog line
(id ``call_1``);
3. request 3 (one ``tool``-role read result) → ``read`` on the JOINED
combined ``source/path`` of the SECOND catalog line (id ``call_2``)
— the pre-phase-45 per-tool budgets would have refused exactly this
second read (``No reading budget left — answer with what you
have.``);
4. request 4 (two read results) → the forced answer, byte-stable: the
single-read shape quoting the FIRST read result, plus the line
``I read <sp1> and <sp2>.`` naming both read paths in read order.
@@ -393,14 +397,15 @@ def test_multi_read_turn(
_submit(page, MULTI_QUESTION)
_wait_settled(page)
# Wire level: exactly THREE `tool` frames — list, read #1, read #2,
# in order — and all ahead of the first `delta` frame. This third
# Wire level: exactly THREE `tool` frames — ls, read #1, read #2
# (each read's argument is the JOINED combined source/path), in
# order — and all ahead of the first `delta` frame. This third
# frame is the one the pre-phase-45 read budget refused.
frames = _frames(page)
assert _tool_frames(frames) == [
{"type": "tool", "name": "list_documents", "argument": None},
{"type": "tool", "name": "read_document", "argument": READ1_SP},
{"type": "tool", "name": "read_document", "argument": READ2_SP},
{"type": "tool", "name": "ls", "argument": None},
{"type": "tool", "name": "read", "argument": READ1_SP},
{"type": "tool", "name": "read", "argument": READ2_SP},
]
first_delta = next(i for i, f in enumerate(frames) if f.get("type") == "delta")
assert all(
@@ -518,7 +523,7 @@ def test_relist_allowed(
# per-tool budgets would have refused (list budget 1, read budget
# 1 — this turn makes one list and TWO reads).
frames = _frames(page)
assert {"type": "tool", "name": "list_documents", "argument": None} in _tool_frames(
assert {"type": "tool", "name": "ls", "argument": None} in _tool_frames(
frames
)
line0 = page.locator(".msg.brain .tool-call").nth(0)
@@ -556,12 +561,13 @@ def test_single_tool_flow_regression(
_submit(page, SINGLE_QUESTION)
_wait_settled(page)
# Exactly TWO tool frames — list then ONE read of the first catalog
# line — no second read (the marker carries no multi-read trigger).
# Exactly TWO tool frames — ls then ONE read of the first catalog
# line (the JOINED combined source/path) — no second read (the
# marker carries no multi-read trigger).
frames = _frames(page)
assert _tool_frames(frames) == [
{"type": "tool", "name": "list_documents", "argument": None},
{"type": "tool", "name": "read_document", "argument": READ1_SP},
{"type": "tool", "name": "ls", "argument": None},
{"type": "tool", "name": "read", "argument": READ1_SP},
]
lines = page.locator(".msg.brain .tool-call")
expect(lines).to_have_count(2)