Files
jray-project/CLAUDE.md
T
dtourolleandClaude Opus 5 43368cdcdb Project home: system spec, working notes, and setup
Gives the system specification an owner. It defines the PR-nnn project
requirements and SR-nnn cross-component contracts that every component spec
traces up to, and until now it lived in no repository at all.

The three component repositories are linked from the README and gitignored
here rather than added as submodules. A submodule pins a commit, so with
feature branches and worktrees in flight across the components, every
component commit would leave this repository's pointer stale. The dependency
is meant to run the other way: components pull this repository in for the
shared tooling and system spec, both of which change rarely.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-30 18:15:20 +02:00

106 lines
5.1 KiB
Markdown

# JRay — working notes
Three components. Start with the system spec; each repo's spec implements it.
| Doc | Owns |
|---|---|
| [`SPEC.md`](SPEC.md) | **System** requirements — anything spanning more than one repo |
| [`scene-actor-extraction/docs/SPEC.md`](scene-actor-extraction/docs/SPEC.md) | Extraction pipeline software requirements |
| [`scene-actor-extraction/docs/requirements.md`](scene-actor-extraction/docs/requirements.md) | Stable requirement IDs, statuses, verification plan |
| [`scene-actor-extraction/docs/plan.md`](scene-actor-extraction/docs/plan.md) | Per-requirement implementation notes and dependencies |
| [`jRay/SPEC.md`](jRay/SPEC.md) | Truth-file format, Jellyfin plugin API |
| [`JRay-public-server/SPEC.md`](JRay-public-server/SPEC.md) | Jmanifest exchange, cut matching, audio signature |
---
## Invariants — do not violate without an explicit, recorded agreement
### Always use the calibrated probability. Never a raw cosine.
**Every similarity is converted through the sigmoid calibration before it is
used, compared, or thresholded.** This applies everywhere — identity matching,
tracking association, gallery expansion admission, cluster merging — not just at
the final identity decision.
A raw cosine threshold is an unfalsifiable magic number: it means something
different for every model, every gallery, and every face size, and it cannot be
combined with anything else. A calibrated probability means the same thing
everywhere and composes (see the per-track Bayesian accumulation in A9).
**If a raw cosine is ever used, it is an agreed exception and must be recorded as
such in the spec, with the reason.** Absent that, treat any bare cosine
comparison in the code as a defect to be fixed. The constants being retired for
this reason include `track_max_embed_dist`, `cut_revive_sim`,
`expand_novelty_sim` and `expand_track_spread_max`.
**Agreed exceptions so far** (do not "fix" these):
| Where | Why |
|---|---|
| `GR-008` — distributional outlier check on an actor's own references | The sigmoid is a monotonic squash: right for *decisions*, wrong for characterising a *distribution*, since it compresses exactly the tails where outliers live. Shape is a property of the metric space. Scope is analysis only — every match decision still goes through the calibration. |
### Every model gets the input it was trained for
Cost is reduced by running a model **less often** or on **fewer regions** — never
by degrading what a single inference sees. A model run off-distribution returns
confident, plausible, wrong output, and the error is invisible without a study
that should not have been needed. (See A5: TransNetV2 must be fed at native frame
rate, not a cheaper 12 fps.)
### Presence is scene-scoped, not instantaneous
The question is *"is this actor in this scene?"*, not *"is their face visible in
this frame?"* — because that is what the X-Ray ground truth records. An actor who
turns away, is occluded, or is off-camera while the shot cuts to whoever they are
speaking to **is still present**. Reporting them absent is not a stricter answer;
it is an answer to a different question. (SR-002.)
A window ends at the **last sighting**, never after it. Gaps *between* sightings
are absorbed; time *after* the final one never is.
### The public server stores no binary content
Its abuse defence is structural — no images, no base64, no opaque blobs, no
extension points. This is what makes it safe for a volunteer to operate. Any
proposal to ship images or embeddings through it is a proposal to delete that
property, not an incremental feature. (SR-004.)
---
## Conventions
### Tag code with the requirement it implements
House format, matching [`JellyTau`](../JellyTau/docs/traces-quick-ref.md) so the
tooling ports directly. Pipe separates requirement types, comma separates IDs
within a type:
```cpp
/// TRACES: AR-012, AR-013 | SR-002
struct TrackRegistry { … };
```
- Tag the unit that **decides**, not every helper it calls.
- **Tests carry TRACES too** (`UT-nnn`, `IT-nnn`) — that is what shows a
requirement is *verified*, not merely implemented.
- **A deliberate raw-cosine use is tagged `EXCEPTION: AR-024 <reason>`.** Per the
invariant above, a bare cosine with no recorded exception is a defect.
Chain: `PR-nnn → SR-nnn → component requirement → TRACES`, defined in
[`SPEC.md`](SPEC.md) §6. Registers live in each component's
`docs/requirements.md`; **IDs are permanent and never reused**, since renumbering
is what creates orphan tags.
When adding a requirement, give it a parent and a register row. When adding code,
give it a tag.
- **Specs are requirements + current-state deltas.** Each requirement carries
`Current:` and `Gap:` so the document doubles as a work list. Keep that shape
when editing.
- **State understanding before writing it into a doc.** Design here has been
settled by discussion, and the corrections have usually been *simpler* than the
proposal. Confirm first; do not write elaborate mechanism into a spec on an
unverified assumption.
- Breaking format changes are **batched into one `schema_version` bump** and
coordinated across all three repos (SR-003).