World's first open-source enterprise world model.
Rust agent-memorybitemporalgraphragknowledge-baseknowledge-graphllmontologypgvectorpostgresqlragrustself-hostedsemantic-searchtemporal-knowledge-graphworld-model
The records say what is built (#747)
WaylandYang15beeccc43a2
diff --git a/docs/decisions/0044-the-ontology-is-a-view-over-what-documents-say.md b/docs/decisions/0044-the-ontology-is-a-view-over-what-documents-say.mdindex b91e3b33..9bd47def 100644--- a/docs/decisions/0044-the-ontology-is-a-view-over-what-documents-say.md+++ b/docs/decisions/0044-the-ontology-is-a-view-over-what-documents-say.md@@ -1,6 +1,6 @@# 0044 · The ontology is a view over what documents say-- **Status**: Proposed 2026-09-16 · replaces the staged-reading draft of this record (skim card, graded mentions, statements bound at write time), which the prototype below did not bear out · nothing built in the product · prototype scripts and measurements from 2026-09-15 are summarised in [What the prototype measured](#what-the-prototype-measured)+- **Status**: Accepted 2026-09-17 · cut 1 built: extraction writes open statements (#731), memory documents take the same path (#735), the typed path is deleted (#736), kind words bind to classes with two votes (#741), the contract's rules for things, phrases, tables and moods (#743, #744, #745) · cut 2 (alignment producing typed facts, identity profiles, the errata agent) not built · current state in [design/extraction](../design/extraction.md) and [design/ontology](../design/ontology.md) · replaces the staged-reading draft of this record (skim card, graded mentions, statements bound at write time), which the prototype below did not bear out · prototype scripts and measurements from 2026-09-15 are summarised in [What the prototype measured](#what-the-prototype-measured)- **Written**: 2026-09-16 (conventions in the [README](README.md))- **Related**: [0022](0022-an-unknown-date-is-not-an-open-one.md) put a document's date in `attested_at` beside the world and record axes; [0025](0025-governance-reads-the-ledger-before-it-decides.md) and [0027](0027-an-automatic-merge-is-gated-by-what-it-can-undo.md) put agent decisions through a gate that weighs what they can undo; [0041](0041-a-name-is-a-claim-about-an-entity.md) made names facts and identity a matter of evidence; [0043](0043-every-review-queue-is-governed.md) sent every review queue through the governor; #714 found upload time used as the document date in extraction.diff --git a/docs/decisions/0045-a-time-mention-is-resolved-against-its-document.md b/docs/decisions/0045-a-time-mention-is-resolved-against-its-document.mdindex 0c91ac11..0257fde1 100644--- a/docs/decisions/0045-a-time-mention-is-resolved-against-its-document.md+++ b/docs/decisions/0045-a-time-mention-is-resolved-against-its-document.md@@ -1,6 +1,6 @@# 0045 · A time mention is resolved against its document-- **Status**: Proposed 2026-09-16 · nothing built · expands decision 5 of [0044](0044-the-ontology-is-a-view-over-what-documents-say.md) and revises decision 3 of [0022](0022-an-unknown-date-is-not-an-open-one.md) for undated documents · closes #714 when cut 2 lands+- **Status**: Accepted 2026-09-17 · cuts 1 and 2 built (#740): a document is dated from its own text, each time mention is interpreted by the model and computed by code, upload time is used nowhere · cut 3 (grades replace the confidence gate in the temporal engine) and cut 4 (re-resolution when a person sets a document's date, the time-anchor review queue) not built · current state in [design/time](../design/time.md) · expands decision 5 of [0044](0044-the-ontology-is-a-view-over-what-documents-say.md) and revises decision 3 of [0022](0022-an-unknown-date-is-not-an-open-one.md) for undated documents · #714 closed- **Written**: 2026-09-16 (conventions in the [README](README.md))- **Related**: [0019](0019-the-second-clock-can-be-rewound.md) and [0022](0022-an-unknown-date-is-not-an-open-one.md) gave facts a world axis, a record axis and an attestation; [0024](0024-the-world-axis-reaches-the-second.md) fixed the precision ladder; [0031](0031-an-event-holds-at-the-moment-it-names.md) made a predicate's temporal kind normalise what is written; #679 made a timeline independent of arrival order; #680 read the opening of a document into every chunk; #688 accepted spelled-out dates; #714 found upload time used as the document date; [0041](0041-a-name-is-a-claim-about-an-entity.md) is the pattern this record copies for time.diff --git a/docs/decisions/README.md b/docs/decisions/README.mdindex 7d83b768..2f395625 100644--- a/docs/decisions/README.md+++ b/docs/decisions/README.md@@ -68,9 +68,8 @@ The test for writing one: if someone (including us) looks at a piece of code in| 0040 | [A chunk says where its words came from](0040-a-chunk-says-where-its-words-came-from.md) | Cuts 1–3 implemented (the ledger shape, and a file that needs a reader degrades with an alert instead of becoming garbage text; scans and images read by a workspace's MinerU service, one segment per page, waiting on the service without spending retries; recordings read by a diarizing transcription model, speakers in the text and times in the anchor, an unlabelled transcript degrades) · scans and images through a MinerU service, recordings only with speaker labels (revised 2026-09-15) · a chunk carries an **origin** (`stated`, `ocr`, `transcribed`, `described`) and the model that produced it, and an **anchor** back into the original bytes (a page and region, a time range, an image inside the file) — decided before any media reader, because a transcript stored without its times can never be tied to the recording again · the packer never mixes origins in a chunk · facts from a description enter below `AUTO_CLOSE_MIN_CONFIDENCE`, so a misread chart opens a conflict instead of closing a correct fact · per-modality model settings, media reading as a resumable job, origin and anchor in the API, MCP and RDF · cuts: ledger shape, scans via MinerU, recordings, descriptions, video || 0041 | [A name is a claim about an entity](0041-a-name-is-a-claim-about-an-entity.md) | Cut 0 built (identity bench) · cut 1 implemented (#670): names are value facts on `known_as`, the extractor reports other names, a shared name goes to the adjudicator; forward/reverse F1 0.43/0.54 → 0.68/0.68 · cuts 2–4 (name vectors and neighbours, evidence decides, re-evaluation) not started || 0042 | [The chat loop is a runner with hooks](0042-the-chat-loop-is-a-runner-with-hooks.md) | Implemented (#548) · the loop is rig's runner and every policy is a hook with a typed result · the wire stays `LlmClient` behind `RigModel` · a turn cannot end before a tool has run, `no_evidence_needed` is the exit for questions not about the base · RAG fallback only on a 400/422 to the first request with tools · an empty reply is asked again once · the skip rate is the model's (DeepSeek-V3 1–3 of 12, Qwen2.5-72B 0) and recorded, not prevented |-| 0044 | [A document is read in stages](0044-a-document-is-read-in-stages.md) | Proposed · nothing built · extraction becomes stages with narrow contracts: a skim that writes a document card with evidenced fields, graded mentions where descriptions never become entities, statements in the text's words with ends from the inventory, normalisation once per distinct phrase with proposals through governance, time resolved by code, identity by evidence in batch · reviews become decisions that write back · today's extractor frozen until an offline prototype of stages 0 and 3 reports on five benches |-| 0044 | [The ontology is a view over what documents say](0044-the-ontology-is-a-view-over-what-documents-say.md) | Proposed · nothing built · replaces the staged-reading draft · three layers: extraction writes an open graph in the documents' words (0 of 333 statements unstated in the prototype, against 4–9% of facts bound at write time), a small ontology proposed by an agent and approved by people, and a typed graph computed from the open graph on cached signatures · time mentions resolved against a document time context by code · identity across documents on deterministic evidence before the adjudicator · an errata agent reviews the typed graph |-| 0045 | [A time mention is resolved against its document](0045-a-time-mention-is-resolved-against-its-document.md) | Proposed · nothing built · a time expression is a mention with its words and place; the model returns shape, anchor, offset and granularity and code computes the interval; a document carries its own date, calendars and anchors across chunks, never its upload time; unresolved mentions wait for an anchor; timelines close on resolution grade instead of confidence |+| 0044 | [The ontology is a view over what documents say](0044-the-ontology-is-a-view-over-what-documents-say.md) | Accepted · cut 1 built (#731, #735, #736, #741, #743–#745): extraction writes open statements, memory documents take the same path, the typed path is deleted, kind words bind to classes · cut 2 (alignment producing typed facts, identity profiles, the errata agent) not built · three layers: extraction writes an open graph in the documents' words (0 of 333 statements unstated in the prototype, against 4–9% of facts bound at write time), a small ontology proposed by an agent and approved by people, and a typed graph computed from the open graph on cached signatures · time mentions resolved against a document time context by code · identity across documents on deterministic evidence before the adjudicator · an errata agent reviews the typed graph |+| 0045 | [A time mention is resolved against its document](0045-a-time-mention-is-resolved-against-its-document.md) | Accepted · cuts 1 and 2 built (#740): a document is dated from its own text, each mention is interpreted by the model and computed by code, upload time is used nowhere · cuts 3 and 4 (grades replace the confidence gate, re-resolution and the anchor queue) not built · a time expression is a mention with its words and place; the model returns shape, anchor, offset and granularity and code computes the interval; a document carries its own date, calendars and anchors across chunks, never its upload time; unresolved mentions wait for an anchor; timelines close on resolution grade instead of confidence || | Record | Domain | Status ||---|---|---|---|| 0001 | [Ontology import and governance](0001-ontology-import-and-governance.md) | ontology | partly superseded (by 0009, 0010, 0012, 0044) |@@ -115,8 +114,8 @@ The test for writing one: if someone (including us) looks at a piece of code in| 0040 | [A chunk says where its words came from](0040-a-chunk-says-where-its-words-came-from.md) | sources | current || 0041 | [A name is a claim about an entity](0041-a-name-is-a-claim-about-an-entity.md) | identity | current || 0042 | [The chat loop is a runner with hooks](0042-the-chat-loop-is-a-runner-with-hooks.md) | chat-and-mcp | current |-| 0044 | [The ontology is a view over what documents say](0044-the-ontology-is-a-view-over-what-documents-say.md) | ontology | proposed |-| 0045 | [A time mention is resolved against its document](0045-a-time-mention-is-resolved-against-its-document.md) | time | proposed |+| 0044 | [The ontology is a view over what documents say](0044-the-ontology-is-a-view-over-what-documents-say.md) | ontology | current |+| 0045 | [A time mention is resolved against its document](0045-a-time-mention-is-resolved-against-its-document.md) | time | current |The status word is whether a later record has overtaken this one; what is built is in the record's own status line. Domains are the files of [../design/](../design/README.md), where every record is dated and the status words are defined.