From ab9e041f9e178084533d64feb1d725db9e70df4b Mon Sep 17 00:00:00 2001 From: Seongho Bae Date: Mon, 17 Aug 2026 01:21:11 +0900 Subject: [PATCH 1/4] 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/src/App.test.tsx | 31 +++++++++++-- frontend/src/App.tsx | 26 +++++++---- frontend/src/api.ts | 9 +++- scripts/seed_demo_data.py | 24 ++++++---- tests/test_analysis_run_create.py | 12 +++++ 13 files changed, 179 insertions(+), 43 deletions(-) create mode 100644 CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index bf19c5f77..e2fe01e72 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 00a19fe92..6d87d84e3 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). +## [0.87.1] - 2026-08-16 + +### 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 and names both clocks. + Cutoff body versioning stays a later slice (ADR 0016). The list + stays aggregates-only. No TEPP theta is invented. + ## [0.87.0] - 2026-08-16 ### Added diff --git a/CLAUDE.md b/CLAUDE.md index 870c77f87..4c92e9807 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -29,7 +29,8 @@ mention TEPP. A failed period-report row rebuilds the report. A pending TEPP row does not claim a calibrated measurement. A pending lineage row says reconstruction has not started yet. 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 3b74c22a3..685e7ad05 100644 --- a/backend/tests/test_api.py +++ b/backend/tests/test_api.py @@ -305,11 +305,21 @@ 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]) @@ -329,6 +339,14 @@ 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 " @@ -494,8 +512,14 @@ 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 c776053b1..8f465a482 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/src/App.test.tsx b/frontend/src/App.test.tsx index fd8a15146..f7468ba5b 100644 --- a/frontend/src/App.test.tsx +++ b/frontend/src/App.test.tsx @@ -302,7 +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", @@ -1688,19 +1701,29 @@ 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 07088e9d4..0ae3a3e50 100644 --- a/frontend/src/App.tsx +++ b/frontend/src/App.tsx @@ -1564,20 +1564,27 @@ 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({ @@ -1752,11 +1759,14 @@ 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/scripts/seed_demo_data.py b/scripts/seed_demo_data.py index 2f3c66c45..7bef3245d 100644 --- a/scripts/seed_demo_data.py +++ b/scripts/seed_demo_data.py @@ -233,22 +233,27 @@ 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] @@ -377,8 +382,8 @@ 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, @@ -389,6 +394,7 @@ 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"]) From 5ca456c96efa5a070d57a8d03fb3cbf9dbc6d576 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Sun, 16 Aug 2026 16:43:39 +0000 Subject: [PATCH 2/4] fix: rebase write-clock slice to 0.87.1 with honest updated_at Keep #150's cutoff comparison on current #74, take 0.87.1 so it does not collide with retention purge, bump source_post.updated_at on a title or body rewrite unless the statement already assigned the clock, and name both clocks on the opened live post. The seeded post-list exact set now includes the edited own-corp title. Co-authored-by: Seongho Bae --- ARCHITECTURE.md | 4 +- ...> 0.87.1-analysis-run-live-write-clock.md} | 5 +- CLAUDE.md | 5 +- backend/tests/test_api.py | 43 +++++++++++- docker/postgres-init/Dockerfile | 1 + ...016-analysis-run-knowledge-cutoff-posts.md | 6 +- docs/adr/0021-source-post-write-clock.md | 49 +++++++++++++ .../ANALYSIS_RUN_REGISTRY_REFERENCES.md | 2 +- docs/doctoring/DESIGN_TOKEN_REFERENCES.md | 2 +- docs/storybook-inventory.md | 1 + frontend/package.json | 2 +- frontend/src/App.css | 14 +++- frontend/src/App.test.tsx | 5 ++ frontend/src/App.tsx | 70 +++++++++++++++---- .../CutoffWriteClockBadge.stories.tsx | 19 +++++ .../components/CutoffWriteClockBadge.test.tsx | 10 +++ .../src/components/CutoffWriteClockBadge.tsx | 16 +++++ frontend/src/styles/tokens.css | 1 + lineageweave/__init__.py | 2 +- migrations/0021_source_post_write_clock.sql | 37 ++++++++++ .../rollback/0021_source_post_write_clock.sql | 9 +++ pyproject.toml | 2 +- scripts/seed_demo_data.py | 1 + tests/test_analysis_run_create.py | 16 +++++ tests/test_analysis_run_registry_schema.py | 15 ++++ uv.lock | 2 +- 26 files changed, 311 insertions(+), 28 deletions(-) rename CHANGELOG.d/{0.87.0-analysis-run-live-write-clock.md => 0.87.1-analysis-run-live-write-clock.md} (51%) create mode 100644 docs/adr/0021-source-post-write-clock.md create mode 100644 frontend/src/components/CutoffWriteClockBadge.stories.tsx create mode 100644 frontend/src/components/CutoffWriteClockBadge.test.tsx create mode 100644 frontend/src/components/CutoffWriteClockBadge.tsx create mode 100644 migrations/0021_source_post_write_clock.sql create mode 100644 migrations/rollback/0021_source_post_write_clock.sql diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index e2fe01e72..2de42827e 100644 --- a/ARCHITECTURE.md +++ b/ARCHITECTURE.md @@ -483,8 +483,8 @@ 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 still -shows the live body; titles rewritten after the run are marked -updated after cutoff. Status history is detail-only +shows the live body and names both clocks when the title was +rewritten after the run. 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/0.87.1-analysis-run-live-write-clock.md similarity index 51% rename from CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md rename to CHANGELOG.d/0.87.1-analysis-run-live-write-clock.md index 701f2fbb4..bb7c0293c 100644 --- a/CHANGELOG.d/0.87.0-analysis-run-live-write-clock.md +++ b/CHANGELOG.d/0.87.1-analysis-run-live-write-clock.md @@ -1,5 +1,6 @@ -# 0.87.0 Analysis-run live write clock +# 0.87.1 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. +post still matches the January cutoff. The opened live body names both +clocks. Bodies stay live. diff --git a/CLAUDE.md b/CLAUDE.md index 4c92e9807..3cdbeb9f2 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -30,7 +30,8 @@ pending TEPP row does not claim a calibrated measurement. A pending lineage row says reconstruction has not started yet. Digest prefixes stay audible; hover a prefix to read the full digest. 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). +after cutoff were rewritten after the run; the opened body names +both clocks. Compare those bodies before treating them as +reconstructed evidence (ADR 0016 / 0021). `POST /api/analysis-runs` records Pending on an authorized cutoff capture (ADR 0017) and does not reconstruct lineage. diff --git a/backend/tests/test_api.py b/backend/tests/test_api.py index 685e7ad05..860a4ea54 100644 --- a/backend/tests/test_api.py +++ b/backend/tests/test_api.py @@ -33,6 +33,7 @@ _MIGRATION_PATH = Path(__file__).resolve().parents[2] / "migrations" / "0001_initial_schema.sql" _REGISTRY_MIGRATION = Path(__file__).resolve().parents[2] / "migrations" / "0018_analysis_run_registry.sql" _RETENTION_MIGRATION = Path(__file__).resolve().parents[2] / "migrations" / "0020_analysis_run_retention_purge.sql" +_WRITE_CLOCK_MIGRATION = Path(__file__).resolve().parents[2] / "migrations" / "0021_source_post_write_clock.sql" def _postgres_available() -> bool: @@ -117,6 +118,7 @@ def seeded_db(demo_analyst_token): cur.execute(_MIGRATION_PATH.read_text()) cur.execute(_REGISTRY_MIGRATION.read_text()) cur.execute(_RETENTION_MIGRATION.read_text()) + cur.execute(_WRITE_CLOCK_MIGRATION.read_text()) cur.execute( "insert into common_lookup_value (lookup_category, lookup_code, lookup_label) values " "('corporate_entity_level', 'group', 'Group'), " @@ -523,6 +525,40 @@ def test_analysis_runs_are_labeled_aggregates_and_hide_other_scopes( assert "postgresql://" not in str(body) assert "visible_posts" not in visible + admin_conn = psycopg2.connect(seeded_db["dsn"]) + admin_conn.autocommit = True + try: + with admin_conn.cursor() as cur: + cur.execute( + "select updated_at from source_post where post_title = %s", + ("Own-corp private post",), + ) + pinned = cur.fetchone()[0] + cur.execute( + "update source_post set post_body = post_body || ' rewritten' " + "where post_title = %s", + ("Own-corp private post",), + ) + cur.execute( + "select updated_at from source_post where post_title = %s", + ("Own-corp private post",), + ) + rewritten = cur.fetchone()[0] + assert rewritten > pinned + cur.execute( + "update source_post set post_body = %s, updated_at = %s " + "where post_title = %s", + ("body", pinned, "Own-corp private post"), + ) + cur.execute( + "select updated_at from source_post where post_title = %s", + ("Own-corp private post",), + ) + honoured = cur.fetchone()[0] + assert honoured == pinned + finally: + admin_conn.close() + hidden = client.get( f"/api/analysis-runs/{seeded_db['hidden_run_id']}", headers={"Authorization": f"Bearer {demo_analyst_token}"}, @@ -611,7 +647,12 @@ def test_post_list_includes_public_and_own_corp_but_excludes_other_corp(client, response = client.get("/api/posts", headers={"Authorization": f"Bearer {demo_analyst_token}"}) assert response.status_code == 200 titles = {post["post_title"] for post in response.json()} - assert titles == {"Public post", "Own-corp private post", "Late own-corp private post"} + assert titles == { + "Public post", + "Own-corp private post", + "Late own-corp private post", + "Edited own-corp private post", + } public = next(post for post in response.json() if post["post_title"] == "Public post") assert public["voc_type_label"] == "Voice of Customer" assert public["visibility_label"] == "Public" diff --git a/docker/postgres-init/Dockerfile b/docker/postgres-init/Dockerfile index ce2f0e6b5..333741958 100644 --- a/docker/postgres-init/Dockerfile +++ b/docker/postgres-init/Dockerfile @@ -26,6 +26,7 @@ COPY migrations/0017_prov_o_standard_relations.sql /docker-entrypoint-initdb.d/1 COPY migrations/0018_analysis_run_registry.sql /docker-entrypoint-initdb.d/19-analysis-run-registry.sql COPY migrations/0019_role_catalog_identity.sql /docker-entrypoint-initdb.d/20-role-catalog-identity.sql COPY migrations/0020_analysis_run_retention_purge.sql /docker-entrypoint-initdb.d/21-analysis-run-retention-purge.sql +COPY migrations/0021_source_post_write_clock.sql /docker-entrypoint-initdb.d/22-source-post-write-clock.sql # Official image already drops to this account at runtime; declare it so # the Dockerfile itself satisfies DS-0002 (explicit non-root USER). USER postgres diff --git a/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md b/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md index 274d34dbd..c63e9034f 100644 --- a/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md +++ b/docs/adr/0016-analysis-run-knowledge-cutoff-posts.md @@ -48,10 +48,14 @@ run. post (2026-02-10) does not appear. - Open the run: Demo public post is marked updated after cutoff (`updated_at` 2026-01-13). Demo private post is not. +- Open a marked title: the live popup names the write clock and the + cutoff. Compare that body with the run before treating it as + reconstructed evidence. - 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. The write - clock is a projection, not a stored cutoff body. + clock is a projection, not a stored cutoff body. Migration 0021 + (ADR 0021) keeps `updated_at` honest after a title or body write. - 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/adr/0021-source-post-write-clock.md b/docs/adr/0021-source-post-write-clock.md new file mode 100644 index 000000000..a8a0e1a45 --- /dev/null +++ b/docs/adr/0021-source-post-write-clock.md @@ -0,0 +1,49 @@ +# ADR 0021 — Source-post write clock honors explicit pins + +**Decision status:** Accepted +**Date:** 2026-08-16 + +## Context + +ADR 0016 compares live `source_post.updated_at` with +`analysis_run.knowledge_cutoff` so the operator can see which in-cutoff +titles were rewritten after the run. The column defaulted to `now()` on +insert and never moved on a later title or body write, so a real rewrite +stayed unmarked and `make seed` could not pin Demo public post to +2026-01-13 unless every statement assigned `updated_at`. + +W3C Time Ontology in OWL (Hobbs & Pan, 2017) and ISO 8601-1:2019 keep +the live write clock distinct from the analysis cutoff. A missing write +clock and a confidently-in-cutoff clock are different things. + +## Decision + +Migration `0021_source_post_write_clock.sql` adds +`touch_source_post_write_clock` on `BEFORE UPDATE` of `source_post`. +The trigger bumps `updated_at` to `clock_timestamp()` only when +`post_title` or `post_body` changes and the statement did not already +assign `updated_at`. Thread-group, visibility, or grouping-key updates +do not pretend to be a rewrite. + +`make seed` may still pin Demo public post to 2026-01-13 and Demo +private post to its create clock. A later product body edit after the +January cutoff marks the title. + +## Consequences + +- After `make seed`, open the Demo Corp lineage run: Demo public post + is marked updated after cutoff; Demo private post is not. +- Open a marked title: the live popup names both clocks. Compare that + body with the run before treating it as reconstructed evidence. +- Cutoff body versioning remains a later slice. +- Roll back `0021` before `0020` / `0018` when emptying a database + that also uses the retention purge. + +## References + +International Organization for Standardization. (2019). *ISO 8601-1:2019: +Date and time—Representations for information interchange—Part 1: Basic +rules* (confirmed 2024; Amendment 1:2022). + +World Wide Web Consortium. (2022). *Time ontology in OWL* (W3C +Recommendation). https://www.w3.org/TR/owl-time/ diff --git a/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md b/docs/doctoring/ANALYSIS_RUN_REGISTRY_REFERENCES.md index 8f465a482..101f9d72b 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). Detail compares live `updated_at` with that cutoff and marks titles rewritten after the run. | +| 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. Migration 0021 bumps `updated_at` on a title or body rewrite unless the statement already assigned the clock (ADR 0021). | | 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/docs/doctoring/DESIGN_TOKEN_REFERENCES.md b/docs/doctoring/DESIGN_TOKEN_REFERENCES.md index 2f0647dca..ba4624c5a 100644 --- a/docs/doctoring/DESIGN_TOKEN_REFERENCES.md +++ b/docs/doctoring/DESIGN_TOKEN_REFERENCES.md @@ -8,7 +8,7 @@ the Storybook inventory. | Source | Product implication | Implemented evidence | |---|---|---| -| W3C Design Tokens Format Module 1.0 | Name color, space, type, and radius once; consume those names from repeated objects. | `frontend/src/styles/tokens.css` defines `--color-*`, `--space-*`, `--radius-chip`, and `--font-*`. `CitationChip` and `PopupCloseButton` read those names through `App.css`. | +| W3C Design Tokens Format Module 1.0 | Name color, space, type, and radius once; consume those names from repeated objects. | `frontend/src/styles/tokens.css` defines `--color-*`, `--space-*`, `--radius-chip`, and `--font-*`. `CitationChip`, `PopupCloseButton`, and `CutoffWriteClockBadge` read those names through `App.css`. | | Storybook for React & Vite | Catalog repeated controls so a buyer can try the next click without reading `App.tsx`. | `frontend/src/components/*.stories.tsx` and `docs/storybook-inventory.md`. | ## APA 7th references diff --git a/docs/storybook-inventory.md b/docs/storybook-inventory.md index 282e3515e..296d300d4 100644 --- a/docs/storybook-inventory.md +++ b/docs/storybook-inventory.md @@ -6,6 +6,7 @@ buyer-facing control you can click before changing product CSS. | Story | Buyer next action | Token / module | |---|---|---| | `Evidence/CitationChip` | Click a cited title to open that source post. | `--color-chip-border`, `--radius-chip`, `CitationChip` | +| `AnalysisRun/CutoffWriteClockBadge` | Open the marked title and compare the live body with the run cutoff. | `--color-accent-border`, `--radius-chip`, `--font-size-badge`, `CutoffWriteClockBadge` | | `Chrome/PopupCloseButton` | Close the evidence panel or post popup. | `--space-close-inset`, `--font-size-close`, `PopupCloseButton` | Repeated web objects must use `frontend/src/styles/tokens.css` and a module diff --git a/frontend/package.json b/frontend/package.json index 0d43d9fa2..25956961a 100644 --- a/frontend/package.json +++ b/frontend/package.json @@ -1,7 +1,7 @@ { "name": "frontend", "private": true, - "version": "0.87.0", + "version": "0.87.1", "type": "module", "scripts": { "dev": "vite", diff --git a/frontend/src/App.css b/frontend/src/App.css index 5251e69f8..35577150b 100644 --- a/frontend/src/App.css +++ b/frontend/src/App.css @@ -49,11 +49,23 @@ } .post-badge { - font-size: 0.75rem; + font-size: var(--font-size-badge); opacity: 0.7; text-transform: uppercase; } +.cutoff-write-clock-badge { + display: inline-block; + margin-left: var(--space-chip-gap); + padding: var(--space-chip-block) var(--space-chip-inline); + border: 1px solid var(--color-accent-border); + border-radius: var(--radius-chip); + background: var(--color-accent-background); + color: var(--color-text-heading); + font-size: var(--font-size-badge); + text-transform: uppercase; +} + .popup-backdrop { position: fixed; inset: 0; diff --git a/frontend/src/App.test.tsx b/frontend/src/App.test.tsx index f7468ba5b..233aee1f4 100644 --- a/frontend/src/App.test.tsx +++ b/frontend/src/App.test.tsx @@ -1727,6 +1727,11 @@ describe("App, authenticated", () => { }), ); await waitFor(() => expect(screen.getByText("The full body text.")).toBeInTheDocument()); + expect( + screen.getByText( + "This live body was rewritten on 2026-01-13, after cutoff 2026-01-12. Compare it with this run before you treat it as reconstructed evidence.", + ), + ).toBeInTheDocument(); await userEvent.click( screen.getByRole("button", { diff --git a/frontend/src/App.tsx b/frontend/src/App.tsx index 0ae3a3e50..2e3ccab68 100644 --- a/frontend/src/App.tsx +++ b/frontend/src/App.tsx @@ -59,6 +59,7 @@ import { type VocEvidence, } from "./api"; import { CitationChip } from "./components/CitationChip"; +import { CutoffWriteClockBadge } from "./components/CutoffWriteClockBadge"; import { PopupCloseButton } from "./components/PopupCloseButton"; import { LineageDag } from "./LineageDag"; import { PostBody } from "./PostBody"; @@ -1163,13 +1164,15 @@ function PostDetailPopup({ graph, onClose, onSelectPost, + liveWriteClock, }: { postId: string; accessToken: string; canExtract: boolean; graph: LineageGraph | null; onClose: () => void; - onSelectPost?: (postId: string) => void; + onSelectPost?: SelectPostFn; + liveWriteClock?: AnalysisRunLiveWriteClock | null; }) { const [post, setPost] = useState(null); const [error, setError] = useState(null); @@ -1242,6 +1245,9 @@ function PostDetailPopup({ {post.visibility_label ?? post.visibility_code} ·{" "} {new Date(post.created_at).toLocaleString()}

    + {liveWriteClock?.liveAfterCutoff && ( +

    {analysisRunOpenedPostWarning(liveWriteClock)}

    + )}
    @@ -1587,6 +1593,30 @@ function analysisRunLivePostButtonLabel(post: { return `Open live post: ${post.post_title}`; } +type AnalysisRunLiveWriteClock = { + knowledgeCutoff: string; + updatedAt?: string; + liveAfterCutoff?: boolean; +}; + +type SelectPostFn = (postId: string, liveWriteClock?: AnalysisRunLiveWriteClock) => void; + +/** + * Next action after a marked cutoff title opens the live body. + */ +function analysisRunOpenedPostWarning(clock: AnalysisRunLiveWriteClock): string { + const cutoffDate = clock.knowledgeCutoff.slice(0, 10); + const writtenDate = clock.updatedAt?.slice(0, 10); + if (!clock.liveAfterCutoff) { + return `This live body still matches the write clock this run knew (cutoff ${cutoffDate}).`; + } + const written = writtenDate ? ` on ${writtenDate}` : ""; + return ( + `This live body was rewritten${written}, after cutoff ${cutoffDate}. ` + + "Compare it with this run before you treat it as reconstructed evidence." + ); +} + function AnalysisRunReproducibilityDigests({ codeRevisionSha, configurationSha256, @@ -1622,7 +1652,7 @@ function AnalysisRunsPanel({ onSelectPost, }: { accessToken: string; - onSelectPost: (postId: string) => void; + onSelectPost: SelectPostFn; }) { const [runs, setRuns] = useState(null); const [selected, setSelected] = useState(null); @@ -1760,13 +1790,17 @@ function AnalysisRunsPanel({ - {post.live_after_cutoff && ( - Updated after cutoff - )} + {post.live_after_cutoff && } ))} @@ -2036,6 +2070,12 @@ function PostList({ accessToken }: { accessToken: string }) { const [graph, setGraph] = useState(null); const [error, setError] = useState(null); const [selectedPostId, setSelectedPostId] = useState(null); + const [liveWriteClock, setLiveWriteClock] = useState(null); + + function selectPost(postId: string, comparison?: AnalysisRunLiveWriteClock) { + setSelectedPostId(postId); + setLiveWriteClock(comparison ?? null); + } const [canRebuild, setCanRebuild] = useState(false); const [rebuilding, setRebuilding] = useState(false); const [rebuildError, setRebuildError] = useState(null); @@ -2067,9 +2107,9 @@ function PostList({ accessToken }: { accessToken: string }) { return ( <> - - - + + +

    Event Lineage

    @@ -2081,7 +2121,7 @@ function PostList({ accessToken }: { accessToken: string }) {
    {rebuildError &&

    {rebuildError}

    } {!graph &&

    Loading lineage graph...

    } - {graph && } + {graph && }
      {posts.map((post) => ( @@ -2089,7 +2129,7 @@ function PostList({ accessToken }: { accessToken: string }) {