From b4e6d2bb65908818be12721041bf0ae5704d360f Mon Sep 17 00:00:00 2001 From: Seongho Bae Date: Mon, 17 Aug 2026 01:21:11 +0900 Subject: [PATCH] feat: compare live post write clock with analysis-run cutoff (v0.87.0) In-cutoff titles now say whether the live row was rewritten after the run. Demo public post is the edited counter-example; Demo private post still matches the January cutoff. Bodies stay live. TEPP stays behind tepp_client. --- ARCHITECTURE.md | 5 +- .../0.87.0-analysis-run-live-write-clock.md | 5 ++ CHANGELOG.md | 12 +++++ CLAUDE.md | 5 +- backend/app/analysis_run_ingestion.py | 46 ++++++++++++++++--- backend/tests/test_api.py | 30 ++++++++++-- ...016-analysis-run-knowledge-cutoff-posts.md | 15 +++--- .../ANALYSIS_RUN_REGISTRY_REFERENCES.md | 2 +- frontend/package.json | 2 +- frontend/src/App.test.tsx | 46 +++++++++++++++++-- frontend/src/App.tsx | 26 +++++++---- frontend/src/api.ts | 9 +++- lineageweave/__init__.py | 2 +- pyproject.toml | 2 +- scripts/seed_demo_data.py | 24 ++++++---- tests/test_analysis_run_create.py | 12 +++++ uv.lock | 2 +- 17 files changed, 198 insertions(+), 47 deletions(-) create mode 100644 CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index b66c7cde7..8a5e5071c 100644 --- a/ARCHITECTURE.md +++ b/ARCHITECTURE.md @@ -482,8 +482,9 @@ unavailable, so that run is Failed rather than a fabricated score. The home list is clickable: `GET /api/analysis-runs/{id}` fills a labeled detail (cutoff, requested date, 12-character digest prefixes with full digests on hover, counts, status history) -without exposing a DSN or raw record. Opening a cutoff title warns -that the live body may have changed after the run. Status history is detail-only +without exposing a DSN or raw record. Opening a cutoff title still +shows the live body; titles rewritten after the run are marked +updated after cutoff. Status history is detail-only and uses lookup labels plus occurrence times; a failure event keeps its machine `failure_code` rather than an invented caption. Failed TEPP list rows add a next-action line (open the run, then connect the diff --git a/CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md b/CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md new file mode 100644 index 000000000..701f2fbb4 --- /dev/null +++ b/CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md @@ -0,0 +1,5 @@ +# 0.87.0 Analysis-run live write clock + +In-cutoff titles now say whether the live row was rewritten after the +run. Open Demo public post as the edited counter-example; Demo private +post still matches the January cutoff. Bodies stay live. diff --git a/CHANGELOG.md b/CHANGELOG.md index 13aeb02f9..333616792 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,18 @@ 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). +## [0.87.0] - 2026-08-17 + +### Added + +- Analysis-run detail now compares each in-cutoff title's live + `updated_at` with that run's knowledge cutoff. After `make seed`, + open the Demo Corp lineage run: Demo public post is marked + **Updated after cutoff**; Demo private post is not. Opening a + marked title still shows the live body -- cutoff body versioning + stays a later slice (ADR 0016). The list stays aggregates-only. + No TEPP theta is invented. + ## [0.86.2] - 2026-08-16 ### Fixed diff --git a/CLAUDE.md b/CLAUDE.md index a11127584..2d9bf975a 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -16,7 +16,8 @@ transport. A failed lineage row retries reconstruction -- it does not mention TEPP. A failed period-report row rebuilds the report. A pending TEPP row does not claim a calibrated measurement. Digest prefixes stay audible; hover a prefix to read the full digest. -Opening a cutoff title shows the live post -- compare it with the -cutoff before treating the body as reconstructed evidence (ADR 0016). +Opening a cutoff title shows the live post. Titles marked updated +after cutoff were rewritten after the run; compare those bodies +before treating them as reconstructed evidence (ADR 0016). `POST /api/analysis-runs` records Pending on an authorized cutoff capture (ADR 0017) and does not reconstruct lineage. diff --git a/backend/app/analysis_run_ingestion.py b/backend/app/analysis_run_ingestion.py index d26eb6f6e..1da59ad1d 100644 --- a/backend/app/analysis_run_ingestion.py +++ b/backend/app/analysis_run_ingestion.py @@ -93,6 +93,22 @@ def _iso(value: Any) -> str: return value.isoformat() if hasattr(value, "isoformat") else str(value) +def _as_utc(value: datetime) -> datetime: + """Treat a naive clock as UTC so cutoff comparison stays timezone-aware.""" + if value.tzinfo is None: + return value.replace(tzinfo=timezone.utc) + return value.astimezone(timezone.utc) + + +def live_write_after_cutoff(updated_at: datetime, knowledge_cutoff: datetime) -> bool: + """True when the live row was rewritten after the run's analysis clock. + + ``created_at <= knowledge_cutoff`` admits the title. ``updated_at`` is + the live write clock (ADR 0016). Equal times stay in-cutoff evidence. + """ + return _as_utc(updated_at) > _as_utc(knowledge_cutoff) + + async def _counts_by_run( conn: asyncpg.Connection, run_ids: list[str], @@ -258,15 +274,21 @@ async def fetch_visible_scope_posts( scope_key: str | None, affiliated_entity_ids: list[str], knowledge_cutoff: Any, -) -> list[dict[str, str]]: +) -> list[dict[str, Any]]: """ABAC-visible post titles known at the run cutoff -- never a hidden body. ``knowledge_cutoff`` is the analysis clock (W3C Time / ISO 8601-1:2019; ADR 0013/0016). A later live post must not appear inside an earlier run. + ``updated_at`` is compared separately so the operator can see which + in-cutoff titles were rewritten after that clock. The live body is + still not returned. """ + columns = ( + "post_id, post_title, visibility_code, corporate_entity_id, updated_at" + ) if scope_kind_code == "analysis_scope_corporate_entity" and corporate_entity_id: rows = await conn.fetch( - "select post_id, post_title, visibility_code, corporate_entity_id " + f"select {columns} " "from source_post where corporate_entity_id = $1 " "and created_at <= $2 " "order by created_at, post_title", @@ -275,7 +297,7 @@ async def fetch_visible_scope_posts( ) elif scope_kind_code == "analysis_scope_process_unit" and process_unit_id: rows = await conn.fetch( - "select post_id, post_title, visibility_code, corporate_entity_id " + f"select {columns} " "from source_post where process_unit_id = $1 " "and created_at <= $2 " "order by created_at, post_title", @@ -284,7 +306,7 @@ async def fetch_visible_scope_posts( ) elif scope_kind_code == "analysis_scope_thread_group" and scope_key: rows = await conn.fetch( - "select post_id, post_title, visibility_code, corporate_entity_id " + f"select {columns} " "from source_post where thread_group_key = $1 " "and created_at <= $2 " "order by created_at, post_title", @@ -293,7 +315,7 @@ async def fetch_visible_scope_posts( ) elif scope_kind_code == "analysis_scope_all_visible": rows = await conn.fetch( - "select post_id, post_title, visibility_code, corporate_entity_id " + f"select {columns} " "from source_post where created_at <= $1 " "order by created_at, post_title", knowledge_cutoff, @@ -301,12 +323,22 @@ async def fetch_visible_scope_posts( else: return [] affiliated = {str(entity_id) for entity_id in affiliated_entity_ids} - posts: list[dict[str, str]] = [] + posts: list[dict[str, Any]] = [] for row in rows: visible = row["visibility_code"] == "public" or str(row["corporate_entity_id"]) in affiliated if not visible: continue - posts.append({"post_id": str(row["post_id"]), "post_title": row["post_title"]}) + updated_at = row["updated_at"] + posts.append( + { + "post_id": str(row["post_id"]), + "post_title": row["post_title"], + "updated_at": _iso(updated_at), + "live_after_cutoff": live_write_after_cutoff( + updated_at, knowledge_cutoff + ), + } + ) return posts diff --git a/backend/tests/test_api.py b/backend/tests/test_api.py index 21c71bc9a..424996afc 100644 --- a/backend/tests/test_api.py +++ b/backend/tests/test_api.py @@ -303,11 +303,21 @@ def _insert_post( visibility_code: str, body: str = "body", created_at: str = "2026-01-10T12:00:00Z", + updated_at: str | None = None, ) -> str: + written_at = updated_at if updated_at is not None else created_at cur.execute( - "insert into source_post (author_account_id, corporate_entity_id, post_title, post_body, voc_type_code, visibility_code, created_at) " - "values (%s, %s, %s, %s, 'voc', %s, %s) returning post_id", - (account_id, corporate_entity_id, title, body, visibility_code, created_at), + "insert into source_post (author_account_id, corporate_entity_id, post_title, post_body, voc_type_code, visibility_code, created_at, updated_at) " + "values (%s, %s, %s, %s, 'voc', %s, %s, %s) returning post_id", + ( + account_id, + corporate_entity_id, + title, + body, + visibility_code, + created_at, + written_at, + ), ) return str(cur.fetchone()[0]) @@ -327,6 +337,14 @@ def _insert_post( "A follow-up written after the January 2026 run cutoff.", created_at="2026-01-20T12:00:00Z", ) + _insert_post( + "Edited own-corp private post", + own_corp_id, + "private", + "A January post rewritten after the run cutoff.", + created_at="2026-01-10T12:00:00Z", + updated_at="2026-01-13T09:00:00Z", + ) cur.execute( "insert into cataloged_person (person_name, person_side_code) values " @@ -492,8 +510,14 @@ def test_analysis_runs_are_labeled_aggregates_and_hide_other_scopes( assert all("failure_code" not in event for event in history) titles = {post["post_title"] for post in body["visible_posts"]} assert "Own-corp private post" in titles + assert "Edited own-corp private post" in titles assert "Late own-corp private post" not in titles assert "Other-corp private post" not in titles + posts_by_title = {post["post_title"]: post for post in body["visible_posts"]} + assert posts_by_title["Own-corp private post"]["live_after_cutoff"] is False + assert posts_by_title["Edited own-corp private post"]["live_after_cutoff"] is True + assert posts_by_title["Edited own-corp private post"]["updated_at"].startswith("2026-01-13") + assert "post_body" not in posts_by_title["Edited own-corp private post"] assert "postgresql://" not in str(body) assert "visible_posts" not in visible diff --git a/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md b/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md index 089443374..274d34dbd 100644 --- a/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md +++ b/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md @@ -25,9 +25,11 @@ every scope branch (corporate entity, process unit, thread group, and all-visible). ABAC visibility is applied after that temporal gate. Click-through still opens the live post body -- post versioning is a later slice -- but the run list itself must not advertise a post the -run was not allowed to know. The detail must say that next action -plainly: compare the opened body with this cutoff before treating it -as reconstructed evidence. +run was not allowed to know. Detail compares the live `updated_at` +write clock with `knowledge_cutoff` and marks titles rewritten after +the run. The next action is specific: only those marked titles need a +cutoff comparison before treating the live body as reconstructed +evidence. Reproducibility digests on the same detail use a labeled group whose accessible name does not replace the visible prefixes (W3C Accessible @@ -44,11 +46,12 @@ run. - After `make seed`, the Demo Corp lineage run lists Demo public post and other in-cutoff Demo Corp titles. The later fixture account-review post (2026-02-10) does not appear. -- Open the run, read the live-body warning, then open a listed post - and compare it with the cutoff date. +- Open the run: Demo public post is marked updated after cutoff + (`updated_at` 2026-01-13). Demo private post is not. - Hover a digest prefix to read the full code or configuration digest when you need to match the API payload. -- Post-body versioning at the cutoff remains future work. +- Post-body versioning at the cutoff remains future work. The write + clock is a projection, not a stored cutoff body. - Thread-group *run list* visibility now uses the same cutoff (ADR 0018). A later public post cannot surface a previously hidden thread-group run. diff --git a/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md b/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md index b41b31c17..4e65dd277 100644 --- a/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md +++ b/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md @@ -8,7 +8,7 @@ | Source | Product implication | Implemented evidence | |---|---|---| | W3C PROV-DM and PROV-O | Preserve identifiable entities, activities, agents, generation/use, and derivation without flattening provenance into display-only edges. | `analysis_source_snapshot`, `analysis_run`, authenticated requester, append-only status events, immutable digests; later product bindings continue to use the separate `provenance_*` layer from ADR 0011. | -| W3C Time Ontology in OWL | Keep temporal concepts explicit and avoid collapsing distinct clocks. | Evidence availability and snapshot capture remain on `analysis_source_snapshot`; analysis knowledge cutoff and request time remain on `analysis_run`; status occurrence and database record time remain distinct. `GET /api/analysis-runs/{id}` visible posts apply `created_at <= knowledge_cutoff` (ADR 0016). Opening a listed title warns that the live body may have changed after that cutoff. | +| W3C Time Ontology in OWL | Keep temporal concepts explicit and avoid collapsing distinct clocks. | Evidence availability and snapshot capture remain on `analysis_source_snapshot`; analysis knowledge cutoff and request time remain on `analysis_run`; status occurrence and database record time remain distinct. `GET /api/analysis-runs/{id}` visible posts apply `created_at <= knowledge_cutoff` (ADR 0016). Detail compares live `updated_at` with that cutoff and marks titles rewritten after the run. | | W3C Accessible Name and Description Computation 1.1 | Do not let `aria-label` replace visible text the operator must hear. | Analysis-run digest prefixes live in a labeled group; the prefixes remain the accessible contents and the full digest is on `title` for hover verification. | | ISO 8601-1:2019 | Use unambiguous timestamp representation and timezone-aware persistence. | PostgreSQL `timestamptz` for availability, capture, cutoff, request, occurrence, and record clocks; tests use explicit `Z` offsets. | | PostgreSQL 18 constraints and trigger contracts | Put integrity close to durable truth and use constraints for row shape while triggers enforce cross-row state and serialization. | Digest/check constraints, category allowlists, account-scoped uniqueness, shape constraints, immutable-row triggers, shared snapshot-row locking, and serialized status transitions. | diff --git a/frontend/package.json b/frontend/package.json index fb52f7948..c93670d28 100644 --- a/frontend/package.json +++ b/frontend/package.json @@ -1,7 +1,7 @@ { "name": "frontend", "private": true, - "version": "0.86.2", + "version": "0.87.0", "type": "module", "scripts": { "dev": "vite", diff --git a/frontend/src/App.test.tsx b/frontend/src/App.test.tsx index 65d25259b..92c3fa16f 100644 --- a/frontend/src/App.test.tsx +++ b/frontend/src/App.test.tsx @@ -85,6 +85,7 @@ describe("App, authenticated", () => { let nextTicketId = 1; const events: { event_id: string; event_type: string; actor_account_id: string; summary: string }[] = []; let nextEventId = 1; + const createdAnalysisRuns: Record[] = []; const fetchMock = vi.fn((input: RequestInfo | URL, init?: RequestInit) => { const url = String(input); @@ -301,7 +302,20 @@ describe("App, authenticated", () => { count_value: 3, }, ], - visible_posts: [{ post_id: "post-1", post_title: "Public post" }], + visible_posts: [ + { + post_id: "post-1", + post_title: "Public post", + updated_at: "2026-01-13T09:00:00Z", + live_after_cutoff: true, + }, + { + post_id: "post-2", + post_title: "Private post", + updated_at: "2026-01-10T12:00:00Z", + live_after_cutoff: false, + }, + ], code_revision_sha: "abcdef0123456789deadbeefcafebabe", configuration_sha256: "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef", @@ -351,6 +365,19 @@ describe("App, authenticated", () => { }, ], }; + createdAnalysisRuns.push({ + analysis_run_id: created.analysis_run_id, + run_kind_code: created.run_kind_code, + run_kind_label: created.run_kind_label, + scope_kind_code: created.scope_kind_code, + scope_kind_label: created.scope_kind_label, + scope_entity_name: created.scope_entity_name, + status_code: created.status_code, + status_label: created.status_label, + knowledge_cutoff: created.knowledge_cutoff, + requested_at: created.requested_at, + source_counts: created.source_counts, + }); return Promise.resolve(new Response(JSON.stringify(created), { status: 201 })); } if (url.endsWith("/api/analysis-runs")) { @@ -431,6 +458,7 @@ describe("App, authenticated", () => { }, ] : []), + ...createdAnalysisRuns, ], }), ); @@ -1685,19 +1713,29 @@ describe("App, authenticated", () => { expect(screen.getByRole("list", { name: "Posts known at this run cutoff" })).toBeInTheDocument(); expect( screen.getByText( - "Opening a title shows the live post. Compare it with cutoff 2026-01-12 before you treat the body as reconstructed evidence — it may have changed after this run.", + "Opening a title shows the live post. Titles marked updated after cutoff were rewritten after 2026-01-12. Compare those bodies with this run before you treat them as reconstructed evidence.", ), ).toBeInTheDocument(); expect( screen.getByRole("button", { - name: "Open live post (may have changed after cutoff): Public post", + name: "Open live post (updated after cutoff): Public post", + }), + ).toBeInTheDocument(); + expect( + screen.getByRole("button", { + name: "Open live post: Private post", }), ).toBeInTheDocument(); + const cutoffPosts = screen.getByRole("list", { name: "Posts known at this run cutoff" }); + expect(cutoffPosts).toHaveTextContent("Updated after cutoff"); + expect(screen.getByRole("button", { name: "Open live post: Private post" }).closest("li")).not.toHaveTextContent( + "Updated after cutoff", + ); expect(screen.queryByText(/postgresql:\/\//)).not.toBeInTheDocument(); await userEvent.click( screen.getByRole("button", { - name: "Open live post (may have changed after cutoff): Public post", + name: "Open live post (updated after cutoff): Public post", }), ); await waitFor(() => expect(screen.getByText("The full body text.")).toBeInTheDocument()); diff --git a/frontend/src/App.tsx b/frontend/src/App.tsx index a511f713d..ac5ca7cf7 100644 --- a/frontend/src/App.tsx +++ b/frontend/src/App.tsx @@ -1548,20 +1548,27 @@ function analysisRunDigestPrefix(digest: string): string { /** * Next action when a cutoff title opens the live post (ADR 0016). * - * Post-body versioning is a later slice. Until then the operator must - * compare the opened body with this run's cutoff instead of treating - * today's text as reconstructed evidence. + * Post-body versioning is a later slice. Titles marked + * `live_after_cutoff` were rewritten after this run; others still + * match the write clock the run knew. */ function analysisRunLivePostWarning(cutoffIso: string): string { const cutoffDate = cutoffIso.slice(0, 10); return ( - `Opening a title shows the live post. Compare it with cutoff ${cutoffDate} ` + - "before you treat the body as reconstructed evidence — it may have changed after this run." + `Opening a title shows the live post. Titles marked updated after cutoff ` + + `were rewritten after ${cutoffDate}. Compare those bodies with this run ` + + "before you treat them as reconstructed evidence." ); } -function analysisRunLivePostButtonLabel(postTitle: string): string { - return `Open live post (may have changed after cutoff): ${postTitle}`; +function analysisRunLivePostButtonLabel(post: { + post_title: string; + live_after_cutoff?: boolean; +}): string { + if (post.live_after_cutoff) { + return `Open live post (updated after cutoff): ${post.post_title}`; + } + return `Open live post: ${post.post_title}`; } function AnalysisRunReproducibilityDigests({ @@ -1734,11 +1741,14 @@ function AnalysisRunsPanel({
  • + {post.live_after_cutoff && ( + Updated after cutoff + )}
    • ))} diff --git a/frontend/src/api.ts b/frontend/src/api.ts index 3385d5179..9eaaba8b8 100644 --- a/frontend/src/api.ts +++ b/frontend/src/api.ts @@ -536,6 +536,13 @@ export interface AnalysisRunStatusEvent { failure_code?: string; } +export interface AnalysisRunVisiblePost { + post_id: string; + post_title: string; + updated_at?: string; + live_after_cutoff?: boolean; +} + export interface AnalysisRun { analysis_run_id: string; run_kind_code: AnalysisRunKindCode; @@ -549,7 +556,7 @@ export interface AnalysisRun { requested_at: string; source_counts: AnalysisRunCount[]; status_history?: AnalysisRunStatusEvent[]; - visible_posts?: { post_id: string; post_title: string }[]; + visible_posts?: AnalysisRunVisiblePost[]; code_revision_sha?: string; configuration_sha256?: string; } diff --git a/lineageweave/__init__.py b/lineageweave/__init__.py index efe84890b..1950c39f8 100644 --- a/lineageweave/__init__.py +++ b/lineageweave/__init__.py @@ -55,4 +55,4 @@ "sentence_excerpts", ] -__version__ = "0.86.2" +__version__ = "0.87.0" diff --git a/pyproject.toml b/pyproject.toml index 6e41c7ca7..ecfe24877 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "lineageweave" -version = "0.86.2" +version = "0.87.0" description = "Reconstructs git-branch-style lineage DAGs from scattered short records using multi-channel score fusion and LLM adjudication." readme = "README.md" license = { text = "MIT" } diff --git a/scripts/seed_demo_data.py b/scripts/seed_demo_data.py index 9d246445d..5f69bbcde 100644 --- a/scripts/seed_demo_data.py +++ b/scripts/seed_demo_data.py @@ -232,22 +232,27 @@ def seed( cur.execute("select post_id from source_post where post_title = 'Demo public post'") if cur.fetchone() is None: cur.execute( - "insert into source_post (author_account_id, corporate_entity_id, process_unit_id, post_title, post_body, voc_type_code, visibility_code, created_at) " + "insert into source_post (author_account_id, corporate_entity_id, process_unit_id, post_title, post_body, voc_type_code, visibility_code, created_at, updated_at) " "values (%s, %s, %s, 'Demo public post', " "'Ada West at Demo Corp followed up with Priya Nair at Northridge Grid about the delayed shipment.', " - "'voc', 'public', '2026-01-10T12:00:00Z')", + "'voc', 'public', '2026-01-10T12:00:00Z', '2026-01-13T09:00:00Z')", (account_ids["demo.analyst"], corporate_entity_id, process_units["DEMO-PU-A"]), ) cur.execute( - "insert into source_post (author_account_id, corporate_entity_id, process_unit_id, post_title, post_body, voc_type_code, visibility_code, created_at) " - "values (%s, %s, %s, 'Demo private post', 'A synthetic private post scoped to Demo Corp accounts.', 'vom', 'private', '2026-01-10T12:00:00Z')", + "insert into source_post (author_account_id, corporate_entity_id, process_unit_id, post_title, post_body, voc_type_code, visibility_code, created_at, updated_at) " + "values (%s, %s, %s, 'Demo private post', 'A synthetic private post scoped to Demo Corp accounts.', 'vom', 'private', '2026-01-10T12:00:00Z', '2026-01-10T12:00:00Z')", (account_ids["demo.admin"], corporate_entity_id, process_units["DEMO-PU-HQ"]), ) cur.execute( - "update source_post set created_at = '2026-01-10T12:00:00Z' " - "where post_title in ('Demo public post', 'Demo private post') " - "and created_at > '2026-01-12T12:00:00Z'" + "update source_post set created_at = '2026-01-10T12:00:00Z', " + "updated_at = '2026-01-13T09:00:00Z' " + "where post_title = 'Demo public post'" + ) + cur.execute( + "update source_post set created_at = '2026-01-10T12:00:00Z', " + "updated_at = '2026-01-10T12:00:00Z' " + "where post_title = 'Demo private post'" ) cur.execute("select post_id from source_post where post_title = 'Demo public post'") demo_public_post_id = cur.fetchone()[0] @@ -376,8 +381,8 @@ def insert_fixture_source_posts(cur, author_account_id, corporate_entity_id, pro "insert into source_post " "(author_account_id, corporate_entity_id, process_unit_id, " " post_title, post_body, voc_type_code, visibility_code, " - " thread_group_key, secondary_grouping_key, created_at) " - "values (%s, %s, %s, %s, %s, %s, 'public', %s, %s, %s) returning post_id", + " thread_group_key, secondary_grouping_key, created_at, updated_at) " + "values (%s, %s, %s, %s, %s, %s, 'public', %s, %s, %s, %s) returning post_id", ( author_account_id, corporate_entity_id, @@ -388,6 +393,7 @@ def insert_fixture_source_posts(cur, author_account_id, corporate_entity_id, pro rec.group_key, rec.secondary_key, occurred, + occurred, ), ) post_id = str(cur.fetchone()[0]) diff --git a/tests/test_analysis_run_create.py b/tests/test_analysis_run_create.py index 4e24a4228..4b7ffcf53 100644 --- a/tests/test_analysis_run_create.py +++ b/tests/test_analysis_run_create.py @@ -5,6 +5,7 @@ from backend.app.analysis_run_ingestion import ( AnalysisRunCreateError, _resolve_corporate_entity_id, + live_write_after_cutoff, plan_analysis_run_capture, ) import pytest @@ -124,6 +125,17 @@ def test_empty_corpus_uses_the_cutoff_as_latest_available_time() -> None: assert capture.maximum_available_time == _CUTOFF +def test_live_write_clock_is_distinct_from_the_cutoff_admission_clock() -> None: + """An in-cutoff title can still have been rewritten after the run.""" + cutoff = _CUTOFF + assert live_write_after_cutoff(_EARLIER, cutoff) is False + assert live_write_after_cutoff(cutoff, cutoff) is False + assert live_write_after_cutoff( + datetime(2026, 1, 13, 9, 0, tzinfo=timezone.utc), cutoff + ) is True + assert live_write_after_cutoff(datetime(2026, 1, 13, 9, 0), cutoff) is True + + def test_create_rejects_an_unaffiliated_or_ambiguous_corporate_entity() -> None: with pytest.raises(AnalysisRunCreateError) as hidden: _resolve_corporate_entity_id("corp-other", ["corp-1"]) diff --git a/uv.lock b/uv.lock index e1d2860cf..6915a3531 100644 --- a/uv.lock +++ b/uv.lock @@ -454,7 +454,7 @@ wheels = [ [[package]] name = "lineageweave" -version = "0.86.2" +version = "0.87.0" source = { virtual = "." } dependencies = [ { name = "certifi" },