a5dd06043fe709b230fcdef701fda7dfd1f80a72
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
54b76ca75a |
fix(compiler): recover lost scene detail via 16.4k Danbooru KB + harden analyzer (#79)
* fix: recover concept detail lost in resolver and harden analyzer parsing
Three shippability fixes for the v1 pipeline:
P2 (main): the Illustrious Resolver did exact-key KB lookup only, so any
compound concept the analyzer emits ("white summer dress", "black business
suit") missed and was dropped silently as SC0001. Add a deterministic
head-noun fallback (§17.2): on a miss, drop leading modifiers and look up the
longest remaining suffix ("white summer dress" -> "dress"). No tag/concept is
invented. Emits SC0019 (Concept Reduced) so the reduction is visible.
P1a: the analyzer required the entire model response to be a single JSON
document, so any surrounding prose ("Sure! Here is the scene:") failed parsing
and, with the prompt reused unchanged, every retry failed identically ->
empty output. Extract the first balanced top-level {...} object from
surrounding text (string-aware brace scan); the object bytes are unchanged and
must still validate, so this is unwrapping, not JSON repair.
P1b: the node's "raw" output was to_raw_json(result.data) -- a re-serialization
of the parsed Scene, so on failure it was empty and the model's actual text was
invisible. Capture the last raw model text in analyzer metadata and surface it
as the node's raw output.
Regenerated goldens: unknown_concepts "hologram jacket" now resolves to
"jacket" via head-noun fallback (intended).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat: add entry rating + resolver.include_nsfw gating
Foundations for the Danbooru-vocab KB: a per-entry `rating` (general|explicit,
default general) and a `resolver.include_nsfw` config flag (default false). The
resolver omits explicit-rated entries from lookup and expansion unless enabled,
so a gated concept is reported as unknown (SC0001). Schema, model, config, and
example config updated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat: generate KB from embedded Danbooru vocab (188 -> 16.4k tags)
Replace the coverage ceiling of the 188-entry hand KB by importing a large,
validated Danbooru tag vocabulary. This is the fix for the core "detail loss"
symptom: compound concepts the analyzer emits ("red dress", "sunflower field",
"train station platform") are now real tags that resolve instead of being
dropped.
- scripts/build_vocab.py: one-time dev step that filters the Raffle node's
categorized tag dump (drops artist/character/copyright/attribution categories
and subjective adjectives, keeps only id-pattern-valid tags) into a committed,
self-contained snapshot at data/danbooru_vocab.txt (16.4k tags).
- scripts/generate_kb_from_vocab.py: additive, non-destructive generator. Writes
knowledge_base/gen_<category>.json, mapping the Raffle categories to the 19
canonical categories and tagging NSFW categories rating=explicit. Skips any tag
already defined as a hand-curated id/alias, so the curated canonicalization
(female + aliases) and expansions (school_uniform -> blazer, pleated_skirt) are
preserved and always win.
Result: 16.4k additive entries + 188 curated. Plain natural-language concepts
now resolve broadly via curated aliases + head-noun fallback with no analyzer
prompt change; NSFW gated behind resolver.include_nsfw; golden and dataset tests
stay green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style: ruff format build_vocab.py
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(security): drop untrusted CLI path in build_vocab (SonarCloud S8707)
The --source CLI argument fed an untrusted path to the file system (taint).
The script is a one-time dev step; hard-code the source path constant instead.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: kunail0804 <kunail0804@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
||
|
|
c1e6afeb41 |
Implement the Ollama Analyzer backend (#15) (#59)
* feat(analyzer): add the Ollama Analyzer backend (#15) Add compiler/analyzer/backend.py per MASTER_SPEC §12.3, §12.10. - AnalyzerBackend Protocol keeps the LLM backend swappable with no downstream coupling; the module imports no downstream compiler stage. - OllamaBackend talks to a local Ollama /api/generate endpoint using only the standard library (urllib). The HTTP call is an injectable transport, so the backend is fully unit-testable without a live Ollama. - Sends the configured model, temperature (default 0.0), and the user prompt unmodified, applying the configured timeout. BackendResult exposes the response text, model name, and request duration for logging. - Failure modes map to codes: connection failure -> BackendUnavailableError (SC0012, Fatal); timeout -> BackendTimeoutError (SC0013); HTTP error / unexpected response -> BackendResponseError (SC0018, new extension). Adds SC0018 (Analyzer Unexpected Response) to the message-code registry. Tests (no live Ollama): interface conformance, from_config, success with telemetry + unmodified prompt, and timeout/connection/URLError/HTTP/malformed response mapping. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(analyzer): use pytest.approx and single throwing call in backend tests Avoid float-equality on temperature (SonarCloud reliability) and construct the backend outside pytest.raises so each block has a single throwing invocation. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: kunail0804 <kunail0804@gmail.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
|
3f0358bfa9 |
feat(validator): implement the Scene Validator (#11) (#55)
Add the Scene Validator per MASTER_SPEC §14 and a central message-code registry.
- compiler/common/message_codes.py: single source of truth for message codes
(Appendix B SC0001-SC0014 plus documented extensions SC0015 Unexpected Field
Removed, SC0016 Empty Concept Removed, SC0017 Interaction Dropped) with a
message() factory that pins each code's severity and title.
- compiler/validator/scene_validator.py: validate_scene(scene_json, config,
logger=None) -> CompilerResult.
- Strict schema validation classifies failures: missing required -> SC0009,
wrong type/malformed -> SC0002 (Errors that stop the compilation).
- Recoverable normalization: unexpected fields -> SC0015 warning + removed
(suppressed when config.validator.allow_unknown_fields is true); empty/
whitespace concepts -> SC0016 warning + removed after trimming; interactions
whose participants reference a non-existent character -> SC0017 warning +
dropped.
- Never creates concepts, generates tags, or does KB lookup. Output is a
Scene model wrapped in a CompilerResult; order is deterministic.
New warning codes (SC0015-SC0017) are extensions to be folded into Appendix B.
Tests: valid input, hard errors (SC0009/SC0002) that stop, recoverable warnings
(SC0015/SC0016/SC0017), allow_unknown_fields suppression, determinism, and the
code registry.
Co-authored-by: kunail0804 <kunail0804@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|