argus-cortex 0.4.3__tar.gz → 0.4.4__tar.gz

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/CHANGELOG.md

@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.4] - 2026-10-31
+
+### Fixed
+- **`SingGuardClient` keeps a longer writeup.** `to_result` clipped `explanation` at 4000
+  characters, which cut cascade/slow reasoning mid-sentence. The cap is now 16384, enough
+  for a 2048-token slow writeup plus a cascade preface.
+- **Re-recording an asset no longer erases what another stage recorded on it.** `record_asset`'s
+  upsert on `sha256` replaced `immich_id` and `metadata` outright, so argus-lens recording a caption
+  for an image argus-quarry had already recorded (licence, author, source) wiped that provenance,
+  and a call without an `immich_id` cleared the stored one. `metadata` now merges key by key
+  (`jsonb ||`: the new call's keys win, others are kept) and a `NULL` `immich_id` keeps the stored
+  one. `uri` is still last-write-wins: it is the asset's latest location. A caller that needs to
+  remove a metadata key can no longer do it through `record_asset`.
+
 ## [0.4.3] - 2026-10-30
 
 ### Added
@@ -164,7 +178,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
     (`LocalBackend`, `RemoteBackend`, `RemoteProvider`, `with_retries`
     retrying only transient errors, `resolve_device`).
 
-[Unreleased]: https://github.com/smk762/argus-cortex/compare/v0.4.3...HEAD
+[Unreleased]: https://github.com/smk762/argus-cortex/compare/v0.4.4...HEAD
+[0.4.4]: https://github.com/smk762/argus-cortex/compare/v0.4.3...v0.4.4
 [0.4.3]: https://github.com/smk762/argus-cortex/compare/v0.4.2...v0.4.3
 [0.4.2]: https://github.com/smk762/argus-cortex/compare/v0.4.1...v0.4.2
 [0.4.1]: https://github.com/smk762/argus-cortex/compare/v0.4.0...v0.4.1

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: argus-cortex
-Version: 0.4.3
+Version: 0.4.4
 Summary: Shared foundation for the Argus suite: taxonomy, versioned wire-schema tooling, and the local/remote AI backend contract
 Project-URL: Repository, https://github.com/smk762/argus-cortex
 Author: smk762

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/src/argus_cortex/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.4.3'
-__version_tuple__ = version_tuple = (0, 4, 3)
+__version__ = version = '0.4.4'
+__version_tuple__ = version_tuple = (0, 4, 4)
 
 __commit_id__ = commit_id = None

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/src/argus_cortex/moderation/singguard.py

@@ -47,7 +47,9 @@ MAX_EDGE = 1536
 MAX_BYTES = 4 * 1024 * 1024
 _MIN_EDGE = 256  # below this, give up rather than send SingGuard a postage stamp
 _NEEDS_PILLOW = "downscaling images needs: pip install argus-cortex[images] (or pass downscale=False)"
-_EXPLANATION_MAX = 4000
+# Fits a 2048-token slow writeup plus a short cascade preface. 4000
+# cut recorded reasoning mid-sentence on cascade scans.
+_EXPLANATION_MAX = 16384
 _FIELD_MAX = 200
 
 

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/src/argus_cortex/store/lineage.py

@@ -70,7 +70,13 @@ class LineageStore(Protocol):
         ...
 
     def record_asset(self, asset: SourceAsset) -> str | None:
-        """Insert (or reuse, by ``sha256``) a source asset; return its id."""
+        """Insert (or reuse, by ``sha256``) a source asset; return its id.
+
+        On reuse, ``uri`` becomes this call's; ``metadata`` merges into the
+        stored bag (this call's keys win); a ``None`` ``immich_id`` keeps the
+        stored one. So stages recording the same bytes add to the row rather
+        than erase each other's fields.
+        """
         ...
 
     def record_caption(self, asset_id: str, caption: Caption) -> str | None:
@@ -302,8 +308,12 @@ class PostgresLineageStore:
 
     def record_asset(self, asset: SourceAsset) -> str | None:
         # De-dupe on content hash: re-ingesting identical bytes returns the
-        # existing row (DO UPDATE ensures RETURNING fires even on conflict) and
-        # refreshes uri/immich_id/metadata to the latest call (last-write-wins).
+        # existing row (DO UPDATE ensures RETURNING fires even on conflict).
+        # Several stages record the same asset (quarry with provenance, lens
+        # with a caption), so a later call must not erase what an earlier one
+        # knew: uri is the latest location (last-write-wins), immich_id keeps
+        # the stored id when this call has none, and metadata merges key by
+        # key (jsonb ||: this call's keys win, the others are kept).
         # NOTE: dedup only works when sha256 is set — NULLs are distinct under the
         # UNIQUE index, so a hash-less asset inserts a fresh row every call.
         return self._insert(
@@ -312,8 +322,8 @@ class PostgresLineageStore:
             VALUES (%s, %s, %s, %s::jsonb)
             ON CONFLICT (sha256) DO UPDATE
                 SET uri = EXCLUDED.uri,
-                    immich_id = EXCLUDED.immich_id,
-                    metadata = EXCLUDED.metadata
+                    immich_id = COALESCE(EXCLUDED.immich_id, source_asset.immich_id),
+                    metadata = source_asset.metadata || EXCLUDED.metadata
             RETURNING id
             """,
             (asset.uri, asset.sha256, asset.immich_id, self._json(asset.metadata)),

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/tests/test_moderation.py

@@ -253,6 +253,24 @@ def test_singguard_config() -> None:
         SingGuardClient("gopher://g")
 
 
+def test_to_result_keeps_a_long_explanation() -> None:
+    writeup = "Cascade: fast flagged this; the slow pass is the verdict.\n\n" + ("A posed adult. " * 400)
+    writeup = writeup.strip()
+    assert 4000 < len(writeup) < singguard._EXPLANATION_MAX
+    result = singguard.to_result(
+        {"safe": True, "verdict": "safe", "rule": "Safe", "explanation": writeup, "categories": []}
+    )
+    assert result.explanation == writeup
+
+
+def test_to_result_clips_explanation_at_max() -> None:
+    exact = "y" * singguard._EXPLANATION_MAX
+    over = exact + "z"
+    payload = {"safe": True, "verdict": "safe", "rule": "Safe", "categories": []}
+    assert singguard.to_result({**payload, "explanation": exact}).explanation == exact
+    assert singguard.to_result({**payload, "explanation": over}).explanation == exact
+
+
 def test_singguard_check(singguard_server) -> None:
     fake, url = singguard_server
     client = SingGuardClient(url, timeout=5, thinking="fast-slow", policy="### A. Minors")

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/tests/test_store.py

@@ -206,9 +206,11 @@ def test_record_asset_returns_id_and_upserts_on_sha() -> None:
     sql, params = conn.executed[-1]
     assert "INSERT INTO source_asset" in sql
     assert "ON CONFLICT (sha256)" in sql
-    # on a dedup hit, uri/immich_id/metadata are all refreshed (not just uri)
-    assert "immich_id = EXCLUDED.immich_id" in sql
-    assert "metadata = EXCLUDED.metadata" in sql
+    # on a dedup hit uri is refreshed, but a call without an immich_id or a
+    # metadata key keeps the stored one (another stage may have recorded it)
+    assert "uri = EXCLUDED.uri" in sql
+    assert "immich_id = COALESCE(EXCLUDED.immich_id, source_asset.immich_id)" in sql
+    assert "metadata = source_asset.metadata || EXCLUDED.metadata" in sql
     # metadata is serialised to a JSON string for the ::jsonb cast
     assert params == ("immich://1", "abc", None, '{"k": "v"}')
 

{argus_cortex-0.4.3 → argus_cortex-0.4.4}/tests/test_store_pg_integration.py

@@ -81,6 +81,20 @@ def test_transaction_rolls_back_on_error(store: PostgresLineageStore) -> None:
     assert reused is not None
 
 
+def test_reupsert_merges_metadata_and_keeps_immich_id(store: PostgresLineageStore) -> None:
+    # quarry records provenance first; lens later records the same bytes with
+    # none: the provenance and immich id survive, the uri moves, shared keys update.
+    sha = uuid.uuid4().hex
+    first = store.record_asset(
+        SourceAsset(uri="quarry://a", sha256=sha, immich_id="im-1", metadata={"license": "cc0", "seen": 1})
+    )
+    again = store.record_asset(SourceAsset(uri="/data/images/a.png", sha256=sha, metadata={"seen": 2}))
+    assert again == first
+    with store._acquire() as conn:
+        row = conn.execute("SELECT uri, immich_id, metadata FROM source_asset WHERE id = %s", (first,)).fetchone()
+    assert row == ("/data/images/a.png", "im-1", {"license": "cc0", "seen": 2})
+
+
 def test_concurrent_writes_are_isolated(store: PostgresLineageStore) -> None:
     # Many concurrent record_asset calls each borrow their own pooled connection;
     # all succeed with distinct ids (no "another operation in progress").