feat(harness): authority, turn contract, tools, clean_agent_preview

Chat/agent harness work: request-authority model, turn contract, tool
policy/parsing/execution, clean_agent_preview streaming/thinking, ask_user
persistence, session probes, and scheduler.

Source: vendor/photocraft (ad1cff44) harness files, 3-way merged onto
upstream/dev (a8c147b2). Harness core files were independently developed
in both lineages; resolution policy documented in pr_work/C_conflicts.md
(vendor kept where ahead, upstream kept where vendor is behind; full delta
preserved in pr_work/C_upstream_delta.patch).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
pewdiepie-archdaemon
2026-10-13 13:41:53 +00:00
co-authored by Claude Opus 5.5
parent a8c147b238
commit 364229f2dc
60 changed files with 2778 additions and 696 deletions
+36
View File
@@ -17,6 +17,42 @@ ERROR = 'event: error\ndata: {"status": 504, "error": {"message": "stream timeou
DONE = 'data: [DONE]\n\n'
@pytest.mark.asyncio
async def test_answer_deltas_are_visible_before_terminal_completion_check():
finish = asyncio.Event()
@with_completion_gate
async def stream(messages):
yield _event({'delta': 'Live answer starts. '})
await finish.wait()
yield _event({'type': 'metrics', 'data': {}})
yield DONE
output = stream([])
first = await asyncio.wait_for(anext(output), timeout=0.2)
assert json.loads(first[6:])['delta'] == 'Live answer starts. '
finish.set()
remaining = [chunk async for chunk in output]
assert _decision([first, *remaining])['can_complete'] is True
@pytest.mark.asyncio
async def test_completion_replacement_replaces_already_streamed_answer_for_turn():
@with_completion_gate
async def stream(messages):
yield _event({'delta': 'The function returns a boolean. I ran pytest and all tests passed.'})
yield _event({'type': 'metrics', 'data': {}})
yield DONE
chunks = [chunk async for chunk in stream([{'role': 'user', 'content': 'Explain this code.'}])]
frames = [data for event, data in _frames(chunks) if event == 'message' and isinstance(data, dict)]
assert any(item.get('delta') == 'The function returns a boolean.' for item in frames)
assert not any('I ran pytest' in str(item.get('delta', '')) for item in frames)
replacement = next(item for item in frames if item.get('type') == 'final_response')
assert 'I ran pytest' not in replacement['content']
assert replacement['replacement_scope'] == 'turn'
@pytest.mark.asyncio
@pytest.mark.parametrize('terminal_texts', [[], ['', ''], ['Recovered answer with literal [DONE] text.']])
async def test_terminal_round_retraction_does_not_resurrect_buffered_drafts(terminal_texts):