File the over-merge findings: two tracklet fixes, and cosine is not identity

The user checked the lead's crops. LIM SEONHO's 36 assignments cover at least
six different men, a chibi and a cat, so 36 of 68 is a bug. 22 came from
native resolves and 14 from reconcile merges.

Two fixes are written in the orchestrator repo, tested, not deployed and not
run on a GPU. `link_tracklets` caps a tracklet's panel span, because `window`
bounded each pair while transitivity was unbounded and the lead's 22 native
assignments came from tracklets spanning 22 and 30 panels. And one shared
appearance tokenizer drops generic words, because whole chains hung on the
word `short` and one pair on the word `hair`.

The obvious third fix is ruled out by measurement. Over all 22 crop
embeddings, the cat scores up to 0.82 against men, two different men score
0.93, and the highest pair is 0.96. No threshold separates them, so
crop-to-crop cosine is not a link signal.

Item 1 of the agreed plan, sending the live cast instead of a cosine top-k
gallery, is not started.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

HANDOFF.md

@@ -5,13 +5,16 @@ Live state is in `NEXT.md`. This file is only what this session did. The previou
 
 ## Asked
 
-The two files, then "go" on the third GPU cycle.
+The two context files, then "go" on the third GPU cycle, then "commit", then "what's next". Then the user
+checked the lead's crops in the review UI and said the assignments were wrong. Then "test on one of the
+panels first". Then "mind presenting the panels with boxes". Then "so, we didn't fix it properly?". Then
+"go with the 1".
 
 ## Result
 
-One worker fix, one measurement that killed the plan's first item, one GPU cycle. The cycle proved the new
+One worker fix proven on a GPU. One measurement that killed the plan's item 1. One GPU cycle. Then the user
-fix and the fifth session's merge fix. Coverage rose for the first time, 50% to 57%. It is now explained
+found the registry is over-merged, which invalidates the cycle's headline numbers, and two more fixes were
-entirely by the `has_face` gate.
+written for it. The third fix the user chose, item 1 of the three options, is NOT started.
 
 | metric | 17:38 run | 18:07 run |
 | --- | --- | --- |
@@ -24,65 +27,98 @@ entirely by the `has_face` gate.
 | chains deeper than one hop | 1 | 0 |
 | `merged_from` stamps | 9 | 22 |
 
-## The corner-ordering fix
+Cycle timings, 18:07-18:13 UTC: vision 116/116 in 3m59s, identity 116/116 in 1m24s, reconcile 18/18 in 50s.
 
-`_bbox_to_pixels` sorts each coordinate pair after clamping. Three lines
+## Committed and proven on a GPU
-(`decisions/identity-bbox.md#bbox-corners-ordered`). The self-check feeds it run B's real
-`[226, 417, 130, 551]` and asserts `[117, 688, 203, 909]`. Unsorted the call returns `[203, 688, 117, 909]`,
-so the assert fails without the fix.
 
-The run returned 0 degenerate boxes over 119 detections. The caveat is deleted and the decision is indexed.
+`_bbox_to_pixels` sorts each coordinate pair after clamping
+(`decisions/identity-bbox.md#bbox-corners-ordered`). 0 degenerate boxes over 119 detections, against 1 in
+117. Commit `54bd126` on `restore-runtime`. Its caveat is deleted.
 
-## The measurement that killed item 1
+## Measured, no code
 
-The plan said to score precision with `eval_identity.py` against the 145 rows of `identity_labels`. Every
+**The 145 ground-truth labels are for a different manga.** Every row in `identity_labels` keys to chapter
-one of those rows belongs to chapter `8ca8249b`, a different manga with cast "Rico" and "Ikekin", spread
+`8ca8249b`, cast "Rico" and "Ikekin", 81 panels. Chapter `7c944dd4` has zero, so
-over 81 panels. Chapter `7c944dd4` has zero labels, so
+`/review/identity?job_id=778297bc...` returns `labeled: 0, accuracy: null`. Scoring `8ca8249b` gives 7/138
-`/review/identity?job_id=778297bc...` returns `labeled: 0, correct: 0, accuracy: null`.
+on a run with 44 assignments over 246 panels, predating every fix.
 
-Scoring `8ca8249b` anyway gives 7/138, with 113 rows labelled as a real person and left unassigned. That
+**Coverage is the `has_face` gate and nothing else.** All 68 assignments landed on face-bearing detections
-chapter's identity run is stale: 44 assignments over 246 panels, predating every fix. The number measures
+and none on a gated one. Recall among face-bearing detections is 96%, up from 82%.
-old code on the wrong chapter.
 
-So the eval path is proven end to end and the ground truth is absent. A precision number needs a hand pass
+**Embedding cosine cannot separate people.** All 22 crop embeddings for the lead, pulled from
-over `7c944dd4` through `POST /review/identity/label`, keyed by bbox rather than `local_id`.
+`manga/<manga_id>/characters/_crops/*.npy`, 1152 dims, L2-normalised. The cat scores up to 0.82 against
+men, two different men score 0.93, the highest pair in the matrix is 0.96
+(`caveats/audit-open.md#cosine-not-identity`). This rules out a crop-to-crop cosine link, which was the
+fix proposed one message before the measurement.
 
-## What the cycle settled
+## Written, tested, NOT deployed and NOT run on a GPU
 
-**Coverage is the gate and nothing else.** All 68 assignments landed on face-bearing detections and none on
+Both in `/mnt/server/home/kami/docker-apps/manga-infra/orchestrator/`, uncommitted there:
-a gated one. Recall among face-bearing detections is 96%, up from 82%. The resolver is not losing cast, so
-the suspicion in `caveats/audit-open.md#coverage-trend` is closed.
 
-**The merge-chain fix holds under load.** 9 merges this run against 7 last run, and 22 `merged_from`
+- `tracklets.py`: `link_tracklets` rejects a merge whose group would span more than `window` panels
-stamps. No chain is deeper than one hop.
+  (`decisions/identity-bbox.md#tracklet-span-cap`). `window` bounded each pair, transitivity was unbounded,
+  and the lead's 22 native assignments came from 3 tracklets spanning 0, 22 and 30 panels.
+- `tracklets.py` + `service.py`: one `appearance_tokens` with a `GENERIC` stopword set, and
+  `service._appearance_tokens` delegates to it, so reconcile's pre-filter is fixed too
+  (`decisions/identity-bbox.md#generic-tokens`). Whole chains hung on the word `short`, one pair on the
+  word `hair`.
 
-## What the cycle opened
+On the same 22 crops, candidate overlap forced to pass: 3 tracklets at worst span 30 becomes 9 at worst
+span 8.
 
-**The lead may be absorbing.** 36 of 68 assignments, 53%, against 25 of 59 before. `audit_registry.py`
+## Not started
-flags it. A protagonist in half the panels looks identical to an over-merge without labels.
 
-**Panel 7 got worse.** 5 of its 6 detections carry `has_face = False`, and `person_6`, the one that does,
+**Item 1, which the user chose: stop letting cosine pick the gallery.** `run_stage_identity` builds
-went unassigned. The previous run bound its colleague. That is the cost of requiring a face, `NEXT.md`
+`union_cands` from the members' cosine top-k. So a metric that cannot separate people decides who gemma is
-item 4.
+even allowed to consider. There are 9 live characters. Send the live cast instead, gender-gated, capped and
+logged when truncated. Two traps found while reading it:
 
-## Not done
+- `/vision/resolve` sends up to 3 reference images per candidate (`worker_vision.py:1057`), so 9 candidates
+  is 27 images plus the query. It needs a cap.
+- only a crop with a non-empty cosine shortlist enters `shortlists` at all, via the
+  `if s.get("candidates")` guard in `service.py`. An empty top-k drops the crop from resolution entirely.
 
-- Nothing downstream re-ran. The job is still parked at `dialogue waiting` with every stage below cleared.
+Also open: nothing downstream re-ran, the job is still parked at `dialogue waiting`, and vision boxes cats
-- Nothing is committed. All edits are in the working tree.
+as people and dresses them (`p081`, `p108`).
 
 ## Checks
 
 ```bash
 .venv/bin/python worker_vision.py     # self-check ok, including the swapped-corner assert
-./check_stale.sh                      # exit 0 before the run and after it
+./check_stale.sh                      # exit 0 before the cycle and after it
+/usr/bin/ssh kami@192.168.1.104 "cd /home/kami/docker-apps/manga-infra/orchestrator && python3 tracklets.py && python3 -m pytest -q --ignore=test_api.py"   # self-check ok, 118 passed
 ```
 
-## Traps confirmed
+Every new assert was confirmed to fail with its fix disabled: the span cap returns `[[0, 1, 2]]`, and the
+generic-word pair links with `GENERIC` emptied.
+
+## Next command
+
+Deploy the two orchestrator fixes and run the fourth cycle.
+
+```bash
+cd /home/kami/Programs/n8n-worker && ./check_stale.sh     # must exit 0
+/usr/bin/ssh kami@192.168.1.104 "cd /home/kami/docker-apps/manga-infra/orchestrator && docker compose up -d --build orchestrator"
+J=778297bc-e7ce-439d-91b5-8a027060d17f; M=ef105a86-4b7e-4ac4-b45c-b7d83b8f5b5e
+/usr/bin/ssh kami@192.168.1.104 "curl -s -X POST http://127.0.0.1:9090/characters/reset -H 'Content-Type: application/json' -d '{\"manga_id\":\"$M\",\"confirm\":true}'"
+# the reset returns restart_identity_worker: true -- honour it, see the traps
+/usr/bin/ssh kami@192.168.1.104 "curl -s -X POST http://127.0.0.1:9090/stage/clear -H 'Content-Type: application/json' -d '{\"job_id\":\"$J\",\"stage\":\"vision\"}'"
+for S in vision identity reconcile; do /usr/bin/ssh kami@192.168.1.104 "curl -s --max-time 5400 -X POST http://127.0.0.1:9090/stage/run -H 'Content-Type: application/json' -d '{\"job_id\":\"$J\",\"stage\":\"$S\"}'"; done
+/usr/bin/ssh kami@192.168.1.104 "docker logs manga-orchestrator --since 1h 2>&1 | grep tracklet"   # expect ~30 tracklets, was 12
+/usr/bin/ssh kami@192.168.1.104 "docker exec manga-orchestrator python3 /app/audit_registry.py 7c944dd4-e972-42c7-ba60-9f6939548e80 6"
+```
+
+Then re-check the lead's crops by eye. A stage counter will not show this defect.
+
+## Traps confirmed or found
 
 - Restart a worker with `tmux send-keys -t manga-workers:<window> C-c`, then re-send the launch line from
-  `start_workers.sh` with the `MIOPEN_ENV` prefix. `pgrep`-based kills match the calling shell.
+  `start_workers.sh` with its `MIOPEN_ENV` prefix. A `pgrep` kill matches the calling shell.
 - `POST /characters/reset` returns `restart_identity_worker: true`. Honour it, the worker caches the
   registry.
 - `identity_assignments` has no `method` column. The `merged_from:` stamps live in
-  `identity_assignment_sources`.
+  `identity_assignment_sources`. `chapters` has no `title` column. The orchestrator image has no numpy.
-- `chapters` has no `title` column.
+- A heredoc piped into `docker exec` over `/usr/bin/ssh` silently produces no output. Write the script to a
+  file, `scp` it, `docker cp` it, then run it.
+- Mixing `echo` with a `tar cf -` stream over ssh corrupts the archive. Separate the calls.
+- `panel_order` and the panel filename differ by one: `panel_order` 10 is `p009.png`.

JOURNAL.md

@@ -644,3 +644,38 @@ labels, which is item 1.
 
 Panel 7 got worse, not better: 5 of its 6 detections carry `has_face = False`, and `person_6`, the one that
 does, went unassigned. The previous run bound its colleague. That is the cost of requiring a face, item 4.
+
+## 2026-08-12, sixth session, later — the lead was over-merged, and cosine cannot fix it
+
+The user checked the lead's crops in the review UI. `LIM SEONHO`'s 36 assignments cover at least six
+different men, a chibi, and a cat. So 36 of 68 is a bug, not a protagonist.
+
+Split by mechanism: 22 native resolves, 14 from reconcile merges. Both are broken, for different reasons.
+
+**The tracklet linker chained across the chapter.** `window=8` bounds each pair, transitivity was
+unbounded. The 22 native assignments came from 3 tracklets spanning 0, 22 and 30 panels, visible as two
+confidence blocks of eleven rows at 0.95 and ten at 1.0. Fixed by capping the merged group's span
+(`decisions/identity-bbox.md#tracklet-span-cap`).
+
+**Both tokenizers linked on words that are not identity.** Whole chains hung on `short`; one pair linked on
+the word `hair` itself. There is now one tokenizer with a `GENERIC` stopword set, shared with reconcile's
+pre-filter (`decisions/identity-bbox.md#generic-tokens`).
+
+Measured on the same 22 real crops, candidate overlap forced to pass: 3 tracklets at worst span 30 becomes
+9 at worst span 8.
+
+**Then the obvious next fix was ruled out by measurement.** Pulled all 22 crop embeddings from MinIO and
+computed the pairwise cosine. The cat scores up to 0.82 against men, two different men score 0.93, and the
+highest pair in the matrix is 0.96. No threshold exists, so crop-to-crop cosine is not a link signal, and
+the `candidates` overlap condition is close to noise. Filed as
+`caveats/audit-open.md#cosine-not-identity`. Inference: identity embeds the whole person box, so cosine
+measures scene and style, not face.
+
+Also seen: vision boxes cats as people and dresses them. `p081` and `p108` are cats, described
+`short brown / yellow plaid shirt` and `short brown / white t-shirt`.
+
+Checks: `tracklets.py` self-check ok, orchestrator 118 passed. Both new asserts confirmed to fail with
+their fix disabled. Nothing deployed, nothing re-run on a GPU.
+
+Artefact: `lead_tracklets.png`, the 22 panels with boxes, insets and tracklet grouping. Session scratchpad
+only, not committed.

NEXT.md

@@ -13,38 +13,55 @@ Three GPU cycles ran on 2026-08-12, the last 18:07-18:13 UTC on a reset registry
 parked at `dialogue waiting`. Everything from `dialogue` down is cleared and stale. All 9 workers are
 current.
 
-Eight changes are now proven on real panels. The fourth session contributed four. The fifth added the
+Eight changes are proven on real panels. The fourth session contributed four. The fifth added the
 roster-hint removal, merge-chain flattening and `name_claims` reset. This session added bbox corner
-ordering. The registry after the 18:07 run holds 18 rows, 9 live and 9 carrying `merged_into`:
+ordering.
 
-- `LIM SEONHO`, 36 assignments, the lead, one row, named from the p010 caption.
+**The registry is not trustworthy.** `LIM SEONHO`'s 36 assignments cover at least six different men, a
-- `character_b112d4`, 23 assignments, the woman, correct and unnamed.
+chibi and a cat, confirmed by eye in the review UI. 22 of those are native resolves and 14 came from
-- `Seonho`, still the wrong man, still named off in-panel text.
+reconcile merges, so both mechanisms are wrong.
 
-Coverage is 57%, from 50%, 61% and 70% before it, and it is now the `has_face` gate and nothing else. All 68
+Two fixes are written and tested but NOT deployed and NOT run on a GPU, both in the orchestrator repo:
-assignments landed on face-bearing detections and none on a gated one. Recall among face-bearing detections
-is 68 of 71, or 96%, up from 82%. Degenerate boxes went from 1 in 117 to 0 in 119, and the merge
-chain is flat with 22 assignments stamped `merged_from`.
 
-The open question moved. The lead holds 36 of 68 assignments, 53%, which `audit_registry.py` flags as
+- `link_tracklets` caps a tracklet's panel span (`decisions/identity-bbox.md#tracklet-span-cap`)
-absorbing. Nothing separates a protagonist in half the panels from an over-merge
+- one shared appearance tokenizer drops generic words (`decisions/identity-bbox.md#generic-tokens`)
-(`caveats/audit-open.md#coverage-trend`).
+
+On the same 22 crops, 3 tracklets at worst span 30 becomes 9 at worst span 8.
+
+Coverage was 57% on the 18:07 run, and it is the `has_face` gate and nothing else. All 68 assignments
+landed on face-bearing detections, so recall among them is 68 of 71. Degenerate boxes are 0 in 119 and the
+merge chain is flat with 22 `merged_from` stamps.
 
 ## Next
 
-1. **Decide whether the lead absorbing 53% of assignments is real.** It needs labels this chapter lacks.
+1. **Deploy the two tracklet fixes and run the fourth cycle.** Neither has touched a GPU. Rebuild the
-   The resolver is cleared: recall among face-bearing detections is 96%. What is unmeasured is precision.
+   orchestrator image, reset the registry, run vision/identity/reconcile, then re-check the lead's crops.
-   The lead went from 25 of 59 to 36 of 68 as the merge count rose from 7 to 9.
+   Expect roughly 30 tracklets over 64 crops instead of 12, so identity goes from about 1m25s to 3 or 4
+   minutes. Watch the lead's assignment count against 36.
 
-   The previous plan pointed at `identity_labels` and its 145 rows. Measured this session: every one of
+   Neither fix is sufficient. Bare hair colour still links different men, and the cat still joins its
-   those rows belongs to chapter `8ca8249b`, a different manga. Chapter `7c944dd4` has zero labels, so
+   neighbours. Do not add a crop-to-crop cosine to close that: measured on this run's 22 embeddings,
-   `/review/identity` reports `labeled: 0, accuracy: null`. Scoring `8ca8249b` gives 7/138 on an identity
+   different people reach 0.93 while the same person reaches 0.96, so no threshold exists
-   run that predates all eight fixes. The eval plumbing works and the ground truth is missing.
+   (`caveats/audit-open.md#cosine-not-identity`).
-   Labelling `7c944dd4` by hand is the only path to a precision number
+
-   (`caveats/audit-open.md#coverage-trend`).
+   Agreed next step after the cycle, chosen by the user and not started: **stop letting cosine pick the
+   gallery.** There are 9 live characters. `run_stage_identity` builds `union_cands` from the members'
+   cosine top-k shortlists, so a metric that cannot separate people decides who is even considered. Send
+   the live cast instead, gender-gated, capped and logged when truncated. Note two traps found while
+   reading it: `/vision/resolve` sends up to 3 reference images per candidate
+   (`worker_vision.py:1057`), so 9 candidates is 27 images plus the query and needs a cap; and only a crop
+   with a non-empty cosine shortlist enters `shortlists` at all, so an empty top-k currently drops the crop
+   from resolution entirely.
+
+   Then, separately, test embedding the FACE box rather than the person box. `face_detect` already finds
+   the face and pairs it for `has_face`. That is the likely root cause of cosine measuring scene instead of
+   person, and the test is to re-embed these same 22 detections and recompute the matrix.
 2. ~~**Order the corners in `_bbox_to_pixels`.**~~ **Done 2026-08-12, run and verified on a GPU.** 0
    degenerate boxes over 119 detections (`decisions/identity-bbox.md#bbox-corners-ordered`).
-3. **Detection still names from in-panel text and can hit the wrong body.** p011 and p026 emit
+3. **Vision boxes animals as people and dresses them.** `p081` and `p108` are cats, described
+   `short brown / yellow plaid shirt` and `short brown / white t-shirt`. A detection prompt problem, not a
+   linker one, and it feeds every stage below.
+4. **Detection still names from in-panel text and can hit the wrong body.** p011 and p026 emit
    `name: "Seonho"` on `person_2` with the roster hint gone. That is the residue of the naming defect and
    the reason the glasses man is named at all
    (`decisions/identity-bbox.md#roster-does-not-name`, "not covered").

caveats/CLAUDE.md

@@ -43,3 +43,4 @@ a complaint, so give it one or drop it.
 | [Vision does not separate a background extra from cast](speaker-attribution.md#extras-as-cast) | 2026-08-12 panel 7 |
 | [Cast reference profiles are enrolled from wrong crops](speaker-attribution.md#poisoned-reference-set) | 2026-08-12 panel 7 |
 | [Identity coverage has fallen on every run since the gate landed](audit-open.md#coverage-trend) | before the next downstream run |
+| [Embedding cosine on a person crop cannot tell two people apart](audit-open.md#cosine-not-identity) | before building on cosine |

caveats/audit-open.md

@@ -212,3 +212,28 @@ The plumbing works, the labels are missing. Precision and recall on the current
 pass over `7c944dd4` first, via `POST /review/identity/label` per detection. Label against the bbox, not
 the `local_id`. Vision is non-deterministic and reassigns `local_id` top-to-bottom every run. A label
 taken before a vision rerun then points at whoever now occupies that slot.
+
+## Embedding cosine on a person crop cannot tell two people apart {#cosine-not-identity}
+
+Measured 2026-08-12 on the 18:07 run's 22 crops for `character_2367d70c`, the embeddings pulled from
+`manga/<manga_id>/characters/_crops/*.npy` and L2-normalised. 1152 dimensions.
+
+| pair | cosine |
+| --- | --- |
+| the cat at `p098` against any man | up to 0.82 |
+| the red-robe chibi at `p088` against any man | up to 0.75 |
+| two visibly different men (`order 60~80`, `88~110`) | 0.93, 0.92 |
+| the highest pair in the matrix (`47~51`, one man, one shirt) | 0.96 |
+
+Different people reach 0.93 and the same person reaches 0.96. No threshold separates them. So a
+crop-to-crop cosine link is not available, and the `candidates` overlap condition in `link_tracklets` is
+close to noise for the same reason: the top-k is chosen by this metric, so every crop shortlists the same
+few rows.
+
+Inference, not yet tested: identity embeds the whole person box, which holds background, clothing and pose.
+Those change between scenes while every crop shares one art style, so cosine measures "manga crop of a
+person in an office". `face_detect` already finds the face and pairs it to the person box for `has_face`,
+so embedding the face region instead is a small change.
+
+Revisit trigger: before building anything else on cosine. The test is to crop the faces of these same 22
+detections, embed them, and recompute this matrix. If a threshold appears, embed faces.

decisions/CLAUDE.md

@@ -48,3 +48,5 @@ still live belongs in `caveats/`.
 | [A roster name is a guess, so it never reaches detection](identity-bbox.md#roster-does-not-name) | closed |
 | [`merged_into` is exactly one hop deep](identity-bbox.md#merge-chains-flatten) | closed |
 | [`_bbox_to_pixels` orders the corners, because the model sometimes swaps them](identity-bbox.md#bbox-corners-ordered) | closed |
+| [A tracklet is bounded by span, not only by pairwise distance](identity-bbox.md#tracklet-span-cap) | closed, GPU pending |
+| [A generic word is not identity evidence, and one tokenizer serves both consumers](identity-bbox.md#generic-tokens) | closed, GPU pending |

decisions/identity-bbox.md

@@ -243,3 +243,62 @@ does not already enforce. The self-check feeds the real swapped box in and asser
 which fails without the sort.
 
 Proven on the 18:07 run: 0 degenerate boxes over 119 detections.
+
+## A generic word is not identity evidence, and one tokenizer serves both consumers {#generic-tokens}
+
+**Closed, 2026-08-12, not yet run on a GPU.**
+
+The tracklet linker and reconcile's pair pre-filter each carried their own copy of the appearance
+tokenizer, and both linked on words that describe a person without distinguishing them. Measured over the
+18:07 run's 22 crops for the lead:
+
+```
+p056~p057  hair=['short']   cloth=-        two different men
+p047~p054  hair=['hair']    cloth=-        "brown hair" vs "dark hair", the field name in its own value
+p109~p110  hair=-           cloth=['shirt','white']
+```
+
+`tracklets.appearance_tokens` is now the single implementation and subtracts a `GENERIC` set: length words
+(`short`, `long`, `medium`, `shoulder`, `length`), `hair`/`haired`, garment words (`shirt`, `top`,
+`jacket`, `coat`, `sleeve`), and filler (`plain`, `casual`, `none`, `unknown`). `service._appearance_tokens`
+delegates to it, so reconcile's pre-filter is fixed by the same change. That pre-filter is what let the
+pink tank top reach `/vision/same` at all.
+
+Four asserts cover it and all four fail with `GENERIC` emptied.
+
+Measured effect on those 22 crops, with candidate overlap forced to pass (the shortlists are not stored,
+so this is the most permissive assumption and the real split can only be finer):
+
+| | tracklets | worst span |
+| --- | --- | --- |
+| as it ran | 3 | 30 panels |
+| span cap only | 8 | 8 |
+| span cap + `GENERIC` | 9 | 8 |
+
+The stopwords alone split out `p054`, the beige-jacket man, and `p089`, the red-robe chibi.
+
+**Not fixed by this.** Bare hair colour still links different men: `order 56` through `62` stay in one
+five-crop tracklet on `brown`, and the cat at `p098` still joins its neighbours the same way. The obvious
+next lever, a crop-to-crop cosine, is ruled out by `caveats/audit-open.md#cosine-not-identity`.
+
+## A tracklet is bounded by span, not only by pairwise distance {#tracklet-span-cap}
+
+**Closed, 2026-08-12, not yet run on a GPU.**
+
+`window=8` bounded each PAIR, and linking is transitive, so nothing bounded the group. The 18:07 run
+resolved 12 tracklets over 64 crops, and the lead's 22 native assignments fell into two of them spanning
+panels 47-69 and 80-110. One gemma answer then covered a grey blazer, a denim jacket, a red robe and a cat.
+The two blocks are visible in the stored confidences: eleven rows at 0.95 and ten at 1.0.
+
+`link_tracklets` now rejects a merge whose resulting group would span more than `window` panels:
+
+```python
+orders = [dets[m].get("panel_order", m) for m in gi + gj]
+if max(orders) - min(orders) > window:
+    continue
+```
+
+This makes the module docstring's claim true. The self-check links three compatible detections at panels 1,
+9 and 17 and asserts they do not land in one tracklet; it returns `[[0, 1, 2]]` with the cap disabled.
+
+Cost: 3 resolve calls become 8 for this character, so identity should go from about 1m25s to 3 or 4 minutes.