The entity URI normalizer stripped every non-ASCII character via the
ASCII-only patterns `[^a-z0-9\-.]` and `[^a-z0-9\-]`. For non-Latin
entity names (e.g. Chinese), this deleted the entire name, so distinct
entities collapsed onto the same URI (".../<ontology>/-"), silently
merging unrelated nodes and breaking OntoRAG for non-English content.
Switch both filters to `[^\w\-.]` / `[^\w\-]`. In Python 3, `\w` is
Unicode-aware for str patterns, so non-ASCII letters (CJK, etc.) are
preserved while punctuation and symbols are still removed. ASCII
behaviour is unchanged: names are lowercased and underscores converted
to hyphens before the filter runs, so for ASCII input the patterns are
equivalent to the originals.
Adds tests covering ASCII regression guards and non-ASCII names/types,
including the core case that two distinct Chinese entities must not
collapse onto the same URI.
Co-authored-by: arthurxuwei <5179840+arthurxuwei@users.noreply.github.com>
- Align similarity_threshold default to 0.3 everywhere (class signature
had stale 0.7). Fix matching contradiction in tech-spec.
- Add bypass_selector_below parameter (default 5) to skip vector
similarity selection when ontology element count is small enough.
- Enforce domain/range constraints in TripleConverter for object
properties and datatype properties, with subclass hierarchy support.
Properties with no declared domain/range pass through unchanged.
- Add unit tests for domain/range validation, subclass acceptance,
polymorphic pass-through, and selector bypass.
Fixes#908, #920
Fixes#826. Addresses all five points the maintainer called out in
the follow-up to #825.
Source change (trustgraph-flow/trustgraph/extract/kg/ontology/extract.py):
- Added `_is_subclass_of(cls, target, ontology_subset, max_depth=100)`
helper with visited-set cycle detection + a defensive depth cap.
LLM-generated ontologies may emit cycles (A subclass_of B,
B subclass_of A); the prior while-loop would infinite-loop on that.
- Replaced both near-identical domain and range subclass walks in
`is_valid_triple` with a single call to the new helper. Net is
-20 duplicated lines + 26-line helper.
Tests (tests/unit/test_extract/test_ontology/test_prompt_and_extraction.py):
- test_is_valid_triple_subclass_is_accepted: domain expects Recipe,
actual type is Cake (subclass), validates.
- test_is_valid_triple_handles_subclass_cycle_without_infinite_loop:
A subclass_of B, B subclass_of A; call returns False within the
depth cap rather than hanging.
- test_parse_and_validate_triples_collects_entity_types_from_rdf_type:
end-to-end path: rdf:type triples build the entity_types dict,
subsequent domain-check triples validate against it.
- test_is_valid_triple_entity_types_none_default: the None default
path now has explicit coverage.
156 existing tests in tests/unit/test_extract/test_ontology still pass.
The extract-with-ontologies prompt is a JSONL prompt, which means the
prompt service returns a PromptResult with response_type="jsonl" and
the parsed items in `.objects` (plural). The ontology extractor was
reading `.object` (singular) — the field used for response_type="json"
— which is always None for JSONL prompts.
Effect: the parser received None on every chunk, hit its "Unexpected
response type: <class 'NoneType'>" branch, returned no ExtractionResult,
and extract_with_simplified_format returned []. Every extraction
silently produced zero triples.
Graphs populated only with the seed ontology schema (TBox) and
document/chunk provenance — no instance triples at all. The e2e test
threshold of >=100 edges per collection was met by schema + provenance
alone, so the failure mode was invisible until RAG queries couldn't
find any content.
Regression introduced in v2.3 with the token-usage work (commit
56d700f3 / 14e49d83) when PromptClient.prompt() began returning a
PromptResult wrapper instead of the raw text/dict/list. All other
call sites of .prompt() across retrieval/, agent/, orchestrator/ were
already reading the correct field for their prompt's response_type;
ontology extraction was the sole stranded caller.
Also adds tests/unit/test_extract/test_ontology/test_extract_with_simplified_format.py
covering:
- happy path: populated .objects produces non-empty triples
- production failure shape: .objects=None returns [] cleanly
- empty .objects returns [] without raising
- defensive: do not silently fall back to .object for a JSONL prompt
Introduces `workspace` as the isolation boundary for config, flows,
library, and knowledge data. Removes `user` as a schema-level field
throughout the code, API specs, and tests; workspace provides the
same separation more cleanly at the trusted flow.workspace layer
rather than through client-supplied message fields.
Design
------
- IAM tech spec (docs/tech-specs/iam.md) documents current state,
proposed auth/access model, and migration direction.
- Data ownership model (docs/tech-specs/data-ownership-model.md)
captures the workspace/collection/flow hierarchy.
Schema + messaging
------------------
- Drop `user` field from AgentRequest/Step, GraphRagQuery,
DocumentRagQuery, Triples/Graph/Document/Row EmbeddingsRequest,
Sparql/Rows/Structured QueryRequest, ToolServiceRequest.
- Keep collection/workspace routing via flow.workspace at the
service layer.
- Translators updated to not serialise/deserialise user.
API specs
---------
- OpenAPI schemas and path examples cleaned of user fields.
- Websocket async-api messages updated.
- Removed the unused parameters/User.yaml.
Services + base
---------------
- Librarian, collection manager, knowledge, config: all operations
scoped by workspace. Config client API takes workspace as first
positional arg.
- `flow.workspace` set at flow start time by the infrastructure;
no longer pass-through from clients.
- Tool service drops user-personalisation passthrough.
CLI + SDK
---------
- tg-init-workspace and workspace-aware import/export.
- All tg-* commands drop user args; accept --workspace.
- Python API/SDK (flow, socket_client, async_*, explainability,
library) drop user kwargs from every method signature.
MCP server
----------
- All tool endpoints drop user parameters; socket_manager no longer
keyed per user.
Flow service
------------
- Closure-based topic cleanup on flow stop: only delete topics
whose blueprint template was parameterised AND no remaining
live flow (across all workspaces) still resolves to that topic.
Three scopes fall out naturally from template analysis:
* {id} -> per-flow, deleted on stop
* {blueprint} -> per-blueprint, kept while any flow of the
same blueprint exists
* {workspace} -> per-workspace, kept while any flow in the
workspace exists
* literal -> global, never deleted (e.g. tg.request.librarian)
Fixes a bug where stopping a flow silently destroyed the global
librarian exchange, wedging all library operations until manual
restart.
RabbitMQ backend
----------------
- heartbeat=60, blocked_connection_timeout=300. Catches silently
dead connections (broker restart, orphaned channels, network
partitions) within ~2 heartbeat windows, so the consumer
reconnects and re-binds its queue rather than sitting forever
on a zombie connection.
Tests
-----
- Full test refresh: unit, integration, contract, provenance.
- Dropped user-field assertions and constructor kwargs across
~100 test files.
- Renamed user-collection isolation tests to workspace-collection.
Expose LLM token usage (in_token, out_token, model) across all
service layers
Propagate token counts from LLM services through the prompt,
text-completion, graph-RAG, document-RAG, and agent orchestrator
pipelines to the API gateway and Python SDK. All fields are Optional
— None means "not available", distinguishing from a real zero count.
Key changes:
- Schema: Add in_token/out_token/model to TextCompletionResponse,
PromptResponse, GraphRagResponse, DocumentRagResponse,
AgentResponse
- TextCompletionClient: New TextCompletionResult return type. Split
into text_completion() (non-streaming) and
text_completion_stream() (streaming with per-chunk handler
callback)
- PromptClient: New PromptResult with response_type
(text/json/jsonl), typed fields (text/object/objects), and token
usage. All callers updated.
- RAG services: Accumulate token usage across all prompt calls
(extract-concepts, edge-scoring, edge-reasoning,
synthesis). Non-streaming path sends single combined response
instead of chunk + end_of_session.
- Agent orchestrator: UsageTracker accumulates tokens across
meta-router, pattern prompt calls, and react reasoning. Attached
to end_of_dialog.
- Translators: Encode token fields when not None (is not None, not truthy)
- Python SDK: RAG and text-completion methods return
TextCompletionResult (non-streaming) or RAGChunk/AgentAnswer with
token fields (streaming)
- CLI: --show-usage flag on tg-invoke-llm, tg-invoke-prompt,
tg-invoke-graph-rag, tg-invoke-document-rag, tg-invoke-agent
* Changed schema for Value -> Term, majorly breaking change
* Following the schema change, Value -> Term into all processing
* Updated Cassandra for g, p, s, o index patterns (7 indexes)
* Reviewed and updated all tests
* Neo4j, Memgraph and FalkorDB remain broken, will look at once settled down
