Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions ARCHITECTURE.md
Original file line number Diff line number Diff line change
Expand Up @@ -83,17 +83,17 @@ flowchart LR
| `server.py` | Stdlib HTTP server: `GET /api/lineage` (JSON graph) + static viewer |
| `web/index.html` | Self-contained SVG DAG viewer, no build step, no external script dependency |

> **Known local-test-environment limitation:** `adjudication_client.py`'s
> `mode="verify"` call depends on contextual-orchestrator's
> `TaskOrchestrator.route_and_verify`, which as of this writing is still
> an open, unmerged upstream PR
> **Known local-test-environment limitation:** `adjudication_client.py`
> and `post_chat.py` send `mode="verify"` (ADR-0013). That call depends
> on contextual-orchestrator's `TaskOrchestrator.route_and_verify`,
> which as of this writing is still an open, unmerged upstream PR
> (`ContextualWisdomLab/contextual-orchestrator#149`). Until it merges,
> the four adjudication/chat tests that exercise `mode="verify"` against
> the live adjudication/chat tests that exercise `mode="verify"` against
> a real orchestrator fail with `invalid_mode` (the deployed `main` only
> accepts `auto`/`route`/`conduct`) -- confirmed by reproducing the same
> `400` directly against the orchestrator's own `/v1/chat/completions`,
> not caused by anything in this repo. `mode="route"` (every other
> pluggable client) is unaffected.
> not caused by anything in this repo. Ordinary product adapters request
> `mode="auto"` and are unaffected.

## Design decisions worth naming

Expand Down
10 changes: 10 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,16 @@ All notable changes to this project are documented here. Format follows
[Keep a Changelog](https://keepachangelog.com/en/1.1.0/); versioning follows
[Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [Unreleased]

### Changed

- Product LLM adapters now request contextual-orchestrator
`mode="auto"` rather than forcing a one-model route. The
orchestrator owns the quality-sufficient route, verification, or
conducted workflow. Citation-bearing post-chat and lineage
adjudication keep their explicit `verify` contracts.

## [0.71.0] - 2026-08-14

### Added
Expand Down
7 changes: 4 additions & 3 deletions docs/lineage-bi-research-notes.md
Original file line number Diff line number Diff line change
Expand Up @@ -254,9 +254,10 @@ classified into the closed `{our_side, counterparty}` set is dropped
rather than guessed. N:N organization attachments are slot-filling on
that mention (a person may have zero, one, or several affiliations in
the same post), not a second independent NER pass. The live client
calls contextual-orchestrator (`mode="route"`) rather than a raw LLM
API so reasoning-effort allocation stays centralized with the
adjudication channel. Proven for real during development against
calls contextual-orchestrator (`mode="auto"`) rather than a raw LLM
API so the orchestration plane can allocate route, verify, or a
deeper workflow; adjudication and post-chat keep explicit
`mode="verify"`. Proven for real during development against
`fixtures.ambiguous_keyman_post` when orchestrator credentials are set;
the default suite asserts the parser and the never-fake null client.

Expand Down
2 changes: 1 addition & 1 deletion lineageweave/post_chat.py
Original file line number Diff line number Diff line change
Expand Up @@ -187,7 +187,7 @@ class ContextualOrchestratorPostChatClient:
``mode="verify"`` exists for (one worker call plus one checked
verifier judgment), same reasoning ``adjudication_client`` already
uses, not ``keyman_extraction``/``entity_relationship_classification``'s
single-pass ``mode="route"`` structured extraction.
single-pass ``mode="auto"`` structured extraction.
"""

available = True
Expand Down
111 changes: 111 additions & 0 deletions tests/test_adaptive_orchestrator_default.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,111 @@
"""LineageWeave delegates product-default LLM execution to auto policy."""

from __future__ import annotations

from pathlib import Path

from lineageweave import adjudication_client, post_chat, post_evaluation
from lineageweave.post_chat import ChatSourceDocument, ContextualOrchestratorPostChatClient


def test_post_evaluation_adapter_defaults_to_auto(monkeypatch) -> None:
observed: dict[str, object] = {}

def fake_post_json(url, payload, *, headers, timeout):
observed.update(
url=url,
payload=payload,
headers=headers,
timeout=timeout,
)
return {"choices": [{"message": {"content": "{}"}}]}

monkeypatch.setattr(post_evaluation, "post_json", fake_post_json)
adapter = post_evaluation._OrchestratorCompleteAdapter(
"https://orchestrator.example.test", "inference_token"
)
adapter.complete([{"role": "user", "content": "Evaluate this evidence."}])

assert observed["payload"]["mode"] == "auto"


def test_post_evaluation_judge_uses_auto_by_default() -> None:
client = post_evaluation.ContextualOrchestratorPostEvaluationClient(
"https://orchestrator.example.test", "inference_token"
)
assert client._judge.mode == "auto"


def test_post_chat_requests_verify_mode(monkeypatch) -> None:
"""Citation chat must send verify on the wire, not a docstring mention of auto."""

observed: dict[str, object] = {}

def fake_post_json(url, payload, *, headers, timeout):
observed["payload"] = payload
return {
"choices": [
{
"message": {
"content": (
'{"answer_text": "The follow-up names the same bid.",'
' "cited_source_numbers": [1]}'
)
}
}
]
}

monkeypatch.setattr(post_chat, "post_json", fake_post_json)
client = ContextualOrchestratorPostChatClient(
"https://orchestrator.example.test", "inference_token"
)
answer = client.answer(
"What happened between these events?",
[
ChatSourceDocument(
post_id="post-bid-follow-up",
post_title="Bid follow-up",
post_body="Northridge asked to confirm the bid date.",
)
],
)

assert answer.cited_post_ids == ("post-bid-follow-up",)
assert observed["payload"]["mode"] == "verify"


def test_adjudication_requests_verify_mode(monkeypatch) -> None:
"""Lineage adjudication must send verify on the wire, not a source substring."""

observed: dict[str, object] = {}

def fake_post_json(url, payload, *, headers, timeout):
observed["payload"] = payload
return {"choices": [{"message": {"content": "0.91"}}]}

monkeypatch.setattr(adjudication_client, "post_json", fake_post_json)
client = adjudication_client.ContextualOrchestratorAdjudicationClient(
"https://orchestrator.example.test", "inference_token"
)
confidence = client.judge(
"Quarterly budget review meeting notes",
"Budget review follow-up: revised quarterly numbers",
)

assert confidence == 0.91
assert observed["payload"]["mode"] == "verify"


def test_runtime_clients_do_not_force_single_model_route() -> None:
package_root = Path(__file__).resolve().parents[1] / "lineageweave"
violations: list[str] = []
for path in sorted(package_root.glob("*.py")):
text = path.read_text(encoding="utf-8")
if '"mode": "route"' in text or "'mode': 'route'" in text:
violations.append(f"{path.name}: request payload")
if 'mode="route"' in text or "mode='route'" in text:
violations.append(f"{path.name}: constructor/call default")
if 'mode: str = "route"' in text or "mode: str = 'route'" in text:
violations.append(f"{path.name}: typed default")
assert violations == []
77 changes: 77 additions & 0 deletions tests/test_contextual_orchestrator_default_policy.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
"""Contract tests for adaptive contextual-orchestrator consumer defaults."""

from __future__ import annotations

from pathlib import Path
import unittest

ROOT = Path(__file__).resolve().parents[1]
AUTO_CLIENTS = (
"lineageweave/post_summary.py",
"lineageweave/post_evaluation.py",
"lineageweave/keyman_extraction.py",
"lineageweave/commitment_extraction.py",
"lineageweave/entity_relationship_classification.py",
)
VERIFY_CLIENTS = (
"lineageweave/post_chat.py",
"lineageweave/adjudication_client.py",
)
_ROUTE_MARKERS = (
'"mode": "route"',
'mode="route"',
'mode: str = "route"',
)
_AUTO_MARKERS = (
'"mode": "auto"',
'mode="auto"',
'mode: str = "auto"',
)
_VERIFY_MARKERS = (
'"mode": "verify"',
'mode="verify"',
'mode: str = "verify"',
)


def _source(relative: str) -> str:
return (ROOT / relative).read_text(encoding="utf-8")


def _contains_any(source: str, markers: tuple[str, ...]) -> bool:
return any(marker in source for marker in markers)


class AdaptiveOrchestratorDefaultTest(unittest.TestCase):
"""Protect production clients from regressing to forced one-model routing."""

def test_auto_clients_request_auto_and_never_force_route(self) -> None:
for relative in AUTO_CLIENTS:
source = _source(relative)
with self.subTest(path=relative):
for marker in _ROUTE_MARKERS:
self.assertNotIn(marker, source)
self.assertTrue(
_contains_any(source, _AUTO_MARKERS),
f"{relative} must request mode=auto in executable source",
)
Comment on lines +54 to +57

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This _contains_any(..., _AUTO_MARKERS) check still treats a docstring mode="auto" as enough. #117 requires the payload literal "mode": "auto" (and "mode": "verify" for the verify list), with the post-evaluation typed-default exception.

Close this draft in favor of #117 rather than merging this scan.


def test_verify_clients_keep_checked_judgment_and_never_force_route(self) -> None:
for relative in VERIFY_CLIENTS:
source = _source(relative)
with self.subTest(path=relative):
for marker in _ROUTE_MARKERS:
self.assertNotIn(marker, source)
self.assertTrue(
_contains_any(source, _VERIFY_MARKERS),
f"{relative} must request mode=verify in executable source",
)
self.assertNotIn(
'"mode": "auto"',
source,
f"{relative} must send verify, not a payload-level auto default",
)


if __name__ == "__main__":
unittest.main()
Loading