Phase 2 of the BERT cross-encoder rerank feature (issue #326). Pins the
contract between `apr import --arch bert` (which routes through
`Architecture::Bert.map_name`, currently identity passthrough at
`tensor_expectation.rs:198`) and `CrossEncoder::load_from_reader` from
Phase 1 (PR #1752).

Without this contract test, a future rewrite of `bert_map_name` (e.g.
stripping the `bert.` prefix or adding a layer rename) would break the
import→load round trip silently — the produced APR would have the
wrong names and `load_from_reader` would fail with `tensor not present
in APR file`. Phase 2 makes that drift surface as a unit test failure
in the SAME crate as the rewrite.

## What this PR adds

  crates/aprender-core/src/models/bert/load.rs (+~100 LOC):
    + `expected_bert_tensor_names(&config, with_pooler, classifier_prefix)`
      — canonical HuggingFace BERT tensor-name set this loader expects.
      Acts as the SYMBOLIC import-load contract. Re-exported from
      `models::bert::expected_bert_tensor_names`.
    + 4 new falsifiers under `falsify_bert_326_phase2_*`:
      - `expected_names_count_matches_formula` — `5 + 16*num_layers +
        2*with_pooler + 2` (locks the per-layer multiplier so adding a
        new BERT component breaks the formula loudly)
      - `contract_matches_loader_reads` — the names the contract helper
        produces are EXACTLY the names the Phase 1 stub builder writes
        AND EXACTLY the names the loader reads — bidirectional pin
      - `bert_map_name_is_identity` — `Architecture::Bert.map_name(name)
        == name` for the canonical set (catches any future
        prefix-stripping rewrite)
      - `bert_base_tensor_count` — 12-layer bert-base produces 201
        tensors (5 + 16*12 + 2 + 2) — smoke for the real bert-base size

  crates/aprender-core/src/models/bert/mod.rs:
    + re-export `expected_bert_tensor_names` alongside `BertLoadError`

## What this PR does NOT do

  - Run `apr import` against a real HuggingFace SafeTensors file. That's
    Phase 3 work (needs network deps + the `safetensors` optional
    feature + a fixture caching strategy).
  - Flip `Architecture::Bert.is_inference_verified()` to true. That
    needs HuggingFace numerical-parity validation (Phase 4) against
    reference activations.
  - Touch `bert_map_name` itself. The identity passthrough is already
    correct for HF SafeTensors and verified by the new test.

## Test plan

- [x] `cargo test -p aprender-core --lib models::bert::` → 22/22 pass
      (18 existing + 4 new Phase 2 falsifiers)
- [x] `expected_bert_tensor_names` is now a public re-export
- [x] No public-API breakage on Architecture / Linear / LayerNorm / MHA
- [x] Doc-comments + symbolic contract eliminate name-duplication
      between import path and load path

## Cross-refs

- #326 Phase 1 ↑ PR #1752 (weight loading from APR) — this builds on it
- #326 Phase 3 next (apr import wire-up + real SafeTensors fixture)
- #326 Phase 4 final (HF numerical-parity + flip
  `is_inference_verified() == true`)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…e 3)

Phase 3 of the BERT cross-encoder rerank feature (issue #326). Adds the
`apr rerank <model.apr>` subcommand that wraps Phase 1's
`CrossEncoder::load_from_reader` (PR #1752) + the existing
`CrossEncoder::forward` to score a single pre-tokenised (input_ids,
token_type_ids) pair.

## What this PR adds

  crates/apr-cli/src/extended_commands.rs:
    + new `ExtendedCommands::Rerank { ... }` variant with full flag
      surface — `--input-ids`, `--token-type-ids`, BERT config
      overrides (hidden_dim, num_layers, etc.), `--with-pooler`,
      `--num-labels`, `--raw-logit`, `--json`.

  crates/apr-cli/src/dispatch_analysis.rs:
    + `ExtendedCommands::Rerank { ... } => commands::rerank::run(...)`
      arm before the `_ => unreachable!()` final arm.

  crates/apr-cli/src/commands/rerank.rs (new, ~150 LOC including 3 tests):
    + `parse_id_list(s, flag)` — comma-separated u32 parser with
      named-flag error messages.
    + `run(...)` — read APR → build BertConfig → construct + load
      CrossEncoder → forward → emit JSON or text (sigmoid score by
      default, `--raw-logit` for the raw classifier output).
    + 3 unit tests on `parse_id_list` (commas+spaces, invalid token,
      trailing comma).

  crates/apr-cli/src/commands/mod.rs:
    + `pub(crate) mod rerank;` alphabetically between
      `registry_schema` and `resume_paths`.

  crates/apr-cli/tests/cli_commands.rs:
    + `"rerank"` registered in the canonical command list (3-surface
      drift check passes).

  contracts/apr-cli-commands-v1.yaml:
    + new `rerank` entry under `inference` category, alongside `chat`
      and `run`. `requires_model: true`, no `side_effects`.

## Usage

  $ apr rerank model.apr \
        --input-ids 101,2024,102,3456,102 \
        --token-type-ids 0,0,0,1,1
  score[0] = 0.834712

  $ apr rerank model.apr \
        --input-ids 101,2024,102,3456,102 \
        --token-type-ids 0,0,0,1,1 \
        --raw-logit --json
  {
    "model": "model.apr",
    "input_ids": [101, 2024, 102, 3456, 102],
    "token_type_ids": [0, 0, 0, 1, 1],
    "logits": [1.62]
  }

## What this PR does NOT do

  - Tokenisation. Caller supplies pre-tokenised u32 arrays. A
    `--query` + `--passage` mode using the tokenizer bundled with the
    APR is Phase 3b follow-up.
  - End-to-end test against a real bge-reranker-base / MiniLM-L-6
    .apr file. Phase 4 work (needs `apr import hf://` integration
    test + cached fixture).
  - Flip `Architecture::Bert.is_inference_verified() == true`. Still
    waiting on Phase 4 HF numerical-parity check.

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] `cargo test -p apr-cli --lib commands::rerank::` → 3/3 pass
- [x] `cargo test -p apr-cli --test cli_commands` → 8/8 pass
      (includes the `test_all_contract_commands_exist` 3-surface drift gate)
- [x] Contract `apr-cli-commands-v1.yaml` updated with new `rerank` entry

## Cross-refs

- #326 Phase 1 → #1752 (weight loading from APR)
- #326 Phase 2 → #1753 (import-load contract helper)
- #326 Phase 3 → **this PR** (CLI surface)
- #326 Phase 4 next (HF numerical parity + flip is_inference_verified)
- Direct unlock for trueno-rag MRR push 0.952 → 0.97+ via
  cross-encoder reranking (sovereign-stack alternative to ONNX
  Runtime / fastembed)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…e 3b)

Phase 3b of the BERT cross-encoder rerank feature (issue #326). Extends
the `apr rerank` CLI from Phase 3 (PR #1755) with an in-process
WordPiece tokenisation mode so callers don't need a separate
`apr tokenize` step:

  $ apr rerank model.apr \
        --query "what is the capital of France?" \
        --passage "Paris is the capital of France." \
        --vocab vocab.txt
  score[0] = 0.94217

The two modes are mutually exclusive: pass either the ID pair
(`--input-ids`+`--token-type-ids`) OR the text pair
(`--query`+`--passage`+`--vocab`). Mixing them returns a structured
error.

## What this PR adds

  crates/apr-cli/src/commands/rerank.rs (+~120 LOC):
    + `load_vocab_txt(&Path) -> HashMap<String, u32>` — reads `vocab.txt`
      one-token-per-line.
    + `tokenize_query_passage(query, passage, vocab_path) -> (Vec<u32>, Vec<u32>)`
      — builds `[CLS] query [SEP] passage [SEP]` with
      `token_type_ids = 0` for the query side and `1` for the passage
      side. Uses existing `aprender::text::tokenize::WordPieceTokenizer`.
    + `run(...)` signature extended with `Option<&str>` query +
      `Option<&str>` passage + `Option<&Path>` vocab; mode dispatch via
      pattern match on the option tuple with a clear-error fallback
      for mixed input.
    + 4 new unit tests:
      - `load_vocab_txt_assigns_line_index_as_id`
      - `tokenize_query_passage_builds_correct_segment_pair`
      - `tokenize_query_passage_rejects_missing_cls`
      - `tokenize_query_passage_rejects_missing_sep`

  crates/apr-cli/src/extended_commands.rs:
    + `ExtendedCommands::Rerank` adds `--query`, `--passage`, `--vocab`
      flags. `--input-ids` and `--token-type-ids` flipped to `Option<String>`.

  crates/apr-cli/src/dispatch_analysis.rs:
    + Dispatch arm passes the new Option<&_> fields to commands::rerank::run.

  contracts/apr-cli-commands-v1.yaml:
    + `rerank` entry description updated to document both input modes.

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] `cargo test -p apr-cli --lib commands::rerank::` → 7/7 pass
      (3 from Phase 3 + 4 new Phase 3b)

## What this PR does NOT do

  - Validate against a real bge-reranker tokenizer. Phase 4 (HF parity)
    work — needs cached HF tokenizer.json fixture.
  - Support the HuggingFace `tokenizer.json` format (Tokenizers crate).
    Phase 3b sticks to the simpler `vocab.txt` interface — HF
    `tokenizer.json` is a Phase 3c follow-up.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (CLI surface, ID mode)
- #326 Phase 3b → **this PR** (CLI text mode w/ WordPiece)
- #326 Phase 4 next (HF numerical parity)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

#326 Phase 4)

Phase 4 of #326. Unblocks `apr import --arch bert` against real
HuggingFace SafeTensors checkpoints and ties the BERT stack together
with HF Tokenizers-format `tokenizer.json` support. Verified on
lambda-vector against `cross-encoder/ms-marco-MiniLM-L-6-v2` (86.7 MB,
6-layer 384-d MiniLM):

  $ apr pull cross-encoder/ms-marco-MiniLM-L-6-v2
  $ apr import .../57e6e922118ea840.safetensors --arch bert \
        -o /tmp/minilm-rerank.apr --allow-no-config
  ⚠ Import completed with warnings   (105 tensors, 87M output)

  $ apr rerank /tmp/minilm-rerank.apr \
        --query "what is the capital of France" \
        --passage "Paris is the capital of France" \
        --vocab .../tokenizer.json
  score[0] = 0.999805                ✅ matching pair

  $ apr rerank /tmp/minilm-rerank.apr \
        --query "what is the capital of France" \
        --passage "Cats are mammals that purr" \
        --vocab .../tokenizer.json
  score[0] = 0.000015                ✅ disjoint pair correctly ranked low

## Two defects fixed

### 1. `apr import --arch bert` panicked on `position_ids` I64 buffer

HuggingFace `transformers` registers integer buffers
(`bert.embeddings.position_ids`, optional `token_type_ids` cache)
alongside trainable f32 weights via `register_buffer`. They appear in
the SafeTensors file as `I64` tensors. The existing dequant path only
handles F32 / F16 / BF16 (see `safetensors_include_01.rs::get_tensor`)
so import aborted with:

  Failed to extract tensor 'bert.embeddings.position_ids':
  Unsupported dtype for 'bert.embeddings.position_ids': I64

Fix: add `is_non_trainable_buffer(name, dtype)` filter in
`safe_tensors_load_result.rs`. Skips tensors with integer dtype AND
HF-known buffer-suffix names (`.position_ids`, `.token_type_ids`,
`.attention_mask`, `.causal_mask`). Applied to all 3 iteration sites:
`load_safetensors_tensors`, `load_safetensors_with_f16_passthrough`,
`load_safetensors_as_f32`.

The filter is name+dtype keyed so it can't silently drop a future
quantized F32 weight named `.position_ids` (already covered by the
`position_ids_f32_is_not_buffer` falsifier).

### 2. `apr rerank --vocab` rejected HF `tokenizer.json` files

Phase 3b's loader assumed line-per-token `vocab.txt`. Real BERT
checkpoints ship `tokenizer.json` (HuggingFace Tokenizers crate
format) where:
- `model.vocab` is the bulk WordPiece map
- `added_tokens` is the special-tokens array (where [CLS]/[SEP]/[UNK]
  actually live; they are NOT inside `model.vocab` per the Tokenizers
  convention)

Fix: `load_tokenizer_json(path)` parses both sections and merges them.
New `load_vocab(path)` dispatcher routes `.json` extension to the HF
parser, otherwise legacy `vocab.txt`. `tokenize_query_passage` now
calls `load_vocab` so both formats work transparently.

## What this PR adds

  crates/aprender-core/src/format/converter/safe_tensors_load_result.rs:
    + `is_non_trainable_buffer(name, dtype)` predicate
    + Filter applied at 3 iteration sites
    + 5 unit tests covering the falsifier cases

  crates/apr-cli/src/commands/rerank.rs:
    + `load_tokenizer_json(path)` — HF Tokenizers WordPiece parser
    + `load_vocab(path)` — extension-dispatcher (.json → HF, else vocab.txt)
    + `tokenize_query_passage` now uses `load_vocab`

## Test plan

- [x] `cargo test -p aprender-core --lib is_non_trainable_buffer` → 5/5 pass
- [x] `cargo build --release --features 'inference cuda'` clean
- [x] `apr pull` 87M MiniLM safetensors → cached
- [x] `apr import --arch bert` → 87M .apr (was: aborted on position_ids)
- [x] `apr rerank --vocab tokenizer.json` produces 0.9998 for matching pair
      and 0.000015 for disjoint pair on real model (was: rejected tokenizer.json)

## What this PR does NOT do

  - Numerical-parity gate vs HF reference (`transformers.AutoModel...`).
    Phase 4b follow-up — needs `uv run --with transformers --with torch`
    to dump per-layer hidden states + cosine compare. The empirical
    matching/disjoint score gap (0.9998 vs 1.5e-5) is strong directional
    evidence that the pipeline is correct but doesn't pin per-tensor
    parity.
  - Flip `Architecture::Bert.is_inference_verified() == true`. That
    needs Phase 4b parity evidence on main.
  - Integration test in CI. The end-to-end test requires the 87M
    cached HF model + network access for first-time download; gating it
    on a CI runner with cached fixtures is Phase 4c.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank CLI, ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ vocab.txt)
- #326 Phase 4 → **this PR** (real HF SafeTensors round-trip)
- Direct unblock for trueno-rag MRR 0.952 → 0.97+ via cross-encoder rerank

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…ed (#326 Phase 4b)

Phase 4b of #326. Demonstrates end-to-end numerical parity between
`apr rerank` and the HuggingFace reference `AutoModelForSequenceClassification`
for `cross-encoder/ms-marco-MiniLM-L-6-v2` and flips
`Architecture::Bert.is_inference_verified() == true`.

## Empirical parity (lambda-vector RTX 4090, 2026-05-17)

  | Pair                        | HF score | apr score | abs diff   |
  |---|---|---|---|
  | "France" + "Paris..."       | 0.999805 | 0.999805 | 2.98e-7   |
  | "France" + "Cats..."        | 0.000015 | 0.000015 | 1.67e-7   |
  | "ML" + "neural networks..." | 0.000020 | 0.000020 | 1.54e-7   |

  WordPiece tokenization: bit-identical input_ids for all 3 prompts.
  Raw logits: agree within ~4e-4 (f32 round-off). Sigmoid maps both to
  identical 6-decimal scores; the parity falsifier asserts < 1e-4
  absolute score diff (observed: < 3e-7).

## What this PR adds

  crates/apr-cli/tests/falsification_bert_326_hf_parity.rs (new):
    + `falsify_bert_326_phase4b_hf_parity` — `#[ignore]`-gated
      integration test that:
      1. checks for the cached MiniLM SafeTensors at the canonical path
      2. invokes `apr import --arch bert` to produce a fresh `.apr`
      3. invokes `apr rerank --query --passage --vocab tokenizer.json`
         for each canonical pair
      4. asserts |apr_score − hf_score| < 1e-4 (observed: < 3e-7)
    + 3 canonical `(query, passage, hf_score)` triples captured from
      HF reference via uv (`uv run --with transformers --with torch`)

  crates/aprender-core/src/format/tensor_expectation.rs:
    + `Architecture::Bert` now matched by `is_inference_verified()`
    + Doc-comment refreshed with the parity matrix

  crates/aprender-core/src/format/converter/tests/pmat_round19.rs:
    + `apr_import_strict_unverified_arch_test` updated: BERT now
      verified post-#326 Phase 4b (was: asserted NOT verified)

  crates/aprender-core/src/format/converter/tests/coverage_types_arch_functions.rs:
    + `test_is_inference_verified_false_gh219` no longer lists BERT
    + new `test_is_inference_verified_true_bert_gh326_phase4b`

## Test plan

- [x] `cargo test -p aprender-core --lib is_inference_verified` → 4/4 pass
- [x] `cargo build -p apr-cli --tests` clean
- [x] `cargo test --test falsification_bert_326_hf_parity -- --ignored --nocapture` → PASS
      with all 3 pairs at < 3e-7 score diff vs HF reference

## What this PR does NOT do (Phase 4c+ scope)

  - CI integration. The parity falsifier is `#[ignore]`-gated because it
    needs the 87 MB cached fixture AND the `apr` release binary on PATH;
    wiring a CI runner with both is Phase 4c.
  - Per-layer hidden-state cosine vs HF. The final-logit parity already
    verifies the full forward chain numerically; per-layer dumps would
    pin specific layers if drift ever appears, but aren't needed today.
  - HF parity for full-size models like `BAAI/bge-reranker-base` (109M).
    Should work mechanically (same architecture); test fixture sizing
    is Phase 4c work.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank CLI, ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ vocab.txt)
- #326 Phase 4 → #1759 (real HF SafeTensors round-trip)
- #326 Phase 4b → **this PR** (HF numerical parity + is_inference_verified)
- Direct unblock for trueno-rag MRR 0.952 → 0.97+ via verified BERT
  cross-encoder rerank (sovereign-stack alternative to ONNX Runtime)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

 Phase 5)

Phase 5 of #326. Adds the canonical cross-encoder use case: rank
multiple candidate passages against a single query. Single-pair mode
was the smoke test; batch mode is the actual production interface
(first-stage retrieval → second-stage rerank).

## Usage

  $ apr rerank model.apr \
        --query "what is the capital of France" \
        --passages "Paris is the capital of France" \
        --passages "Berlin is the capital of Germany" \
        --passages "Lyon is a city in France" \
        --passages "Cats are mammals that purr" \
        --vocab tokenizer.json --sort --json
  {
    "model": "model.apr",
    "query": "what is the capital of France",
    "num_passages": 4,
    "returned": 4,
    "sorted": true,
    "results": [
      { "index": 0, "passage": "Paris is the capital of France",   "logit":  8.540365, "score": 0.999805 },
      { "index": 2, "passage": "Berlin is the capital of Germany", "logit": -3.200321, "score": 0.039154 },
      { "index": 3, "passage": "Lyon is a city in France",         "logit": -3.570795, "score": 0.027364 },
      { "index": 1, "passage": "Cats are mammals that purr",       "logit":-11.118653, "score": 0.000015 }
    ]
  }

Note the ranking quality: Paris (correct match) → Berlin (also a
capital, wrong country) → Lyon (also in France, wrong city) → Cats
(disjoint). That's exactly the semantic ordering a cross-encoder is
supposed to produce.

## What this PR adds

  crates/apr-cli/src/extended_commands.rs:
    + `--passages <TEXT>` flag (repeatable, `Vec<String>`)
    + `--sort` (descending by score)
    + `--top-k N` (implies `--sort`; limit output to top N)

  crates/apr-cli/src/dispatch_analysis.rs:
    + dispatch threads through the new flags

  crates/apr-cli/src/commands/rerank.rs:
    + new `run_batch` function — loads the cross-encoder ONCE then
      scores N (query, passage_i) pairs in a loop
    + sort + top-k logic with `partial_cmp` fallback
    + JSON output preserves original `index` so callers can map back
      to their first-stage retrieval ordering even after sort

## What this PR does NOT do

  - True batched forward (one matrix-of-pairs call instead of N
    sequential calls). The MiniLM forward is fast enough at 87M that
    sequential N=10..100 ranking takes < 1s on lambda-vector. True
    batching is a Phase 5b optimisation if N gets larger.
  - Streaming output for large N. The full ranked list is materialised
    in memory before printing — fine for typical RAG rerank (N ≤ 100).

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] End-to-end batch test on lambda-vector against real MiniLM:
      4-passage ranking produces correct semantic ordering
- [x] `--top-k 2` correctly truncates to top 2

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank single-pair ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ WordPiece)
- #326 Phase 4 → #1759 (real HF SafeTensors round-trip)
- #326 Phase 4b → #1765 (HF numerical parity + is_inference_verified)
- #326 Phase 5 → **this PR** (batch ranking — the actual production use case)

Direct unblock for trueno-rag: a typical RAG pipeline returns
top-50 BM25/dense candidates then reranks down to top-5. This PR
ships the second-stage API in one CLI call.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

 Phase 5) (#1767)

* feat(bert): cross-encoder weight loading from APR v2 (#326 Phase 1)

Phase 1 of the BERT cross-encoder rerank feature (issue #326). Adds
weight-loading from APR v2 files into the existing `BertEncoder` /
`BertEmbeddings` / `CrossEncoder` scaffolding (already in-tree per the
pre-existing 585 LOC).

After this PR, the previously-zero-init `CrossEncoder::new(config, ...)`
can be hydrated with real `BAAI/bge-reranker-base` /
`cross-encoder/ms-marco-MiniLM-L-6-v2`-style weights via a one-call
loader:

  let mut model = CrossEncoder::new(&config, 1, true);
  model.load_from_reader(&apr_reader, &config)?;
  let score = model.score(&input_ids, &token_type_ids);  // ∈ [0, 1]

## What this PR adds

  crates/aprender-core/src/models/bert/load.rs (new, ~280 LOC including tests):
    + `BertLoadError { tensor, reason }` typed error
    + `read_tensor(reader, name, expected_shape)` — single-tensor read
      with dequant + shape-validation
    + `load_embeddings_from_reader` — 3 embedding tables + LayerNorm
    + `load_layer_from_reader` — 6 weight/bias pairs per encoder block
      (Q/K/V/O proj + 2 LayerNorms + intermediate + output)
    + `load_encoder_from_reader` — iterates over all encoder layers
    + `load_cross_encoder_from_reader` — embeddings + encoder + optional
      pooler + classifier head with prefix fallback
      (`classifier` → `score` → `rank_head`)
    + 3 falsifier tests using synthetic AprV2 stubs:
      - `falsify_bert_326_phase1_load_full_cross_encoder` (happy path)
      - `falsify_bert_326_phase1_missing_classifier_returns_structured_error`
      - `falsify_bert_326_phase1_shape_mismatch_returns_structured_error`

  crates/aprender-core/src/models/bert/mod.rs:
    + `pub mod load;` + `pub use load::BertLoadError;`

  crates/aprender-core/src/models/bert/embeddings.rs:
    + Fields promoted `private` → `pub(crate)` so the loader can mutate
      them in place (3 embedding tensors + LayerNorm). No public-API
      change.

  crates/aprender-core/src/models/bert/layer.rs:
    + `attention_mut`, `attention_norm_mut`, `intermediate_mut`,
      `output_dense_mut`, `output_norm_mut` — 5 mutable accessors for
      the loader. Pattern matches existing `Linear::placeholder +
      set_weight + set_bias` lazy-load convention.

  crates/aprender-core/src/models/bert/encoder.rs:
    + `BertEncoder::layer_mut(idx)`

  crates/aprender-core/src/models/bert/cross_encoder.rs:
    + cached `num_labels` field on the struct (avoids coupling the
      loader to `Linear::out_features`)
    + `embeddings_mut`, `encoder_mut`, `pooler_mut`, `classifier_mut`
    + `load_from_reader(&mut self, reader, config)` public one-shot

  crates/aprender-core/src/nn/normalization/mod.rs:
    + `LayerNorm::set_weight(weight)` + `LayerNorm::set_bias(bias)`
      — mirrors `Linear::set_weight` / `set_bias` for symmetry with
      the existing lazy-load convention.

  crates/aprender-core/src/nn/transformer/mod.rs:
    + `MultiHeadAttention::{q,k,v,out}_proj_mut` — 4 mutable accessors
      on the inner Linear projections so the BERT loader can install
      Q/K/V/O weights without re-constructing MHA.

## What this PR does NOT do (Phase 2+ scope, separate PRs)

  - apr import path for BERT SafeTensors → APR v2 (Phase 2). Today the
    loader only consumes APR; the test uses a synthetic AprV2Writer to
    build a stub APR. Real `apr import hf://cross-encoder/...` work
    lives in Phase 2.
  - `apr rerank` CLI subcommand (Phase 3)
  - HuggingFace numerical-parity validation (Phase 4)
  - `Architecture::Bert.is_inference_verified()` still returns false;
    flipping it to true requires Phase 2 (real APR file) + Phase 4
    (HF parity check)

## Test plan

- [x] `cargo test -p aprender-core --lib models::bert::` → 18/18 pass
      (15 existing + 3 new falsifiers)
- [x] No public-API breakage on Linear / LayerNorm / MHA / BERT structs
      (only additive mutable accessors + 1 new struct field with
      Default-friendly cached integer)
- [x] Build clean on `cargo build -p aprender-core`

## Cross-refs

- #326 BERT cross-encoder reranking — this is Phase 1 per the
  #326 comment-4470811613 scope plan
- Unblocks trueno-rag MRR 0.952 → 0.97+ push via real cross-encoder
  reranking (sovereign-stack alternative to ONNX Runtime)
- Architecture::Bert.bert_map_name passthrough (tensor_expectation.rs
  line 198) preserves HF tensor names unchanged — no APR-side
  renaming required.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(bert): import-load contract helper + 4 falsifiers (#326 Phase 2)

Phase 2 of the BERT cross-encoder rerank feature (issue #326). Pins the
contract between `apr import --arch bert` (which routes through
`Architecture::Bert.map_name`, currently identity passthrough at
`tensor_expectation.rs:198`) and `CrossEncoder::load_from_reader` from
Phase 1 (PR #1752).

Without this contract test, a future rewrite of `bert_map_name` (e.g.
stripping the `bert.` prefix or adding a layer rename) would break the
import→load round trip silently — the produced APR would have the
wrong names and `load_from_reader` would fail with `tensor not present
in APR file`. Phase 2 makes that drift surface as a unit test failure
in the SAME crate as the rewrite.

## What this PR adds

  crates/aprender-core/src/models/bert/load.rs (+~100 LOC):
    + `expected_bert_tensor_names(&config, with_pooler, classifier_prefix)`
      — canonical HuggingFace BERT tensor-name set this loader expects.
      Acts as the SYMBOLIC import-load contract. Re-exported from
      `models::bert::expected_bert_tensor_names`.
    + 4 new falsifiers under `falsify_bert_326_phase2_*`:
      - `expected_names_count_matches_formula` — `5 + 16*num_layers +
        2*with_pooler + 2` (locks the per-layer multiplier so adding a
        new BERT component breaks the formula loudly)
      - `contract_matches_loader_reads` — the names the contract helper
        produces are EXACTLY the names the Phase 1 stub builder writes
        AND EXACTLY the names the loader reads — bidirectional pin
      - `bert_map_name_is_identity` — `Architecture::Bert.map_name(name)
        == name` for the canonical set (catches any future
        prefix-stripping rewrite)
      - `bert_base_tensor_count` — 12-layer bert-base produces 201
        tensors (5 + 16*12 + 2 + 2) — smoke for the real bert-base size

  crates/aprender-core/src/models/bert/mod.rs:
    + re-export `expected_bert_tensor_names` alongside `BertLoadError`

## What this PR does NOT do

  - Run `apr import` against a real HuggingFace SafeTensors file. That's
    Phase 3 work (needs network deps + the `safetensors` optional
    feature + a fixture caching strategy).
  - Flip `Architecture::Bert.is_inference_verified()` to true. That
    needs HuggingFace numerical-parity validation (Phase 4) against
    reference activations.
  - Touch `bert_map_name` itself. The identity passthrough is already
    correct for HF SafeTensors and verified by the new test.

## Test plan

- [x] `cargo test -p aprender-core --lib models::bert::` → 22/22 pass
      (18 existing + 4 new Phase 2 falsifiers)
- [x] `expected_bert_tensor_names` is now a public re-export
- [x] No public-API breakage on Architecture / Linear / LayerNorm / MHA
- [x] Doc-comments + symbolic contract eliminate name-duplication
      between import path and load path

## Cross-refs

- #326 Phase 1 ↑ PR #1752 (weight loading from APR) — this builds on it
- #326 Phase 3 next (apr import wire-up + real SafeTensors fixture)
- #326 Phase 4 final (HF numerical-parity + flip
  `is_inference_verified() == true`)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(apr-cli): apr rerank — BERT cross-encoder scoring CLI (#326 Phase 3)

Phase 3 of the BERT cross-encoder rerank feature (issue #326). Adds the
`apr rerank <model.apr>` subcommand that wraps Phase 1's
`CrossEncoder::load_from_reader` (PR #1752) + the existing
`CrossEncoder::forward` to score a single pre-tokenised (input_ids,
token_type_ids) pair.

## What this PR adds

  crates/apr-cli/src/extended_commands.rs:
    + new `ExtendedCommands::Rerank { ... }` variant with full flag
      surface — `--input-ids`, `--token-type-ids`, BERT config
      overrides (hidden_dim, num_layers, etc.), `--with-pooler`,
      `--num-labels`, `--raw-logit`, `--json`.

  crates/apr-cli/src/dispatch_analysis.rs:
    + `ExtendedCommands::Rerank { ... } => commands::rerank::run(...)`
      arm before the `_ => unreachable!()` final arm.

  crates/apr-cli/src/commands/rerank.rs (new, ~150 LOC including 3 tests):
    + `parse_id_list(s, flag)` — comma-separated u32 parser with
      named-flag error messages.
    + `run(...)` — read APR → build BertConfig → construct + load
      CrossEncoder → forward → emit JSON or text (sigmoid score by
      default, `--raw-logit` for the raw classifier output).
    + 3 unit tests on `parse_id_list` (commas+spaces, invalid token,
      trailing comma).

  crates/apr-cli/src/commands/mod.rs:
    + `pub(crate) mod rerank;` alphabetically between
      `registry_schema` and `resume_paths`.

  crates/apr-cli/tests/cli_commands.rs:
    + `"rerank"` registered in the canonical command list (3-surface
      drift check passes).

  contracts/apr-cli-commands-v1.yaml:
    + new `rerank` entry under `inference` category, alongside `chat`
      and `run`. `requires_model: true`, no `side_effects`.

## Usage

  $ apr rerank model.apr \
        --input-ids 101,2024,102,3456,102 \
        --token-type-ids 0,0,0,1,1
  score[0] = 0.834712

  $ apr rerank model.apr \
        --input-ids 101,2024,102,3456,102 \
        --token-type-ids 0,0,0,1,1 \
        --raw-logit --json
  {
    "model": "model.apr",
    "input_ids": [101, 2024, 102, 3456, 102],
    "token_type_ids": [0, 0, 0, 1, 1],
    "logits": [1.62]
  }

## What this PR does NOT do

  - Tokenisation. Caller supplies pre-tokenised u32 arrays. A
    `--query` + `--passage` mode using the tokenizer bundled with the
    APR is Phase 3b follow-up.
  - End-to-end test against a real bge-reranker-base / MiniLM-L-6
    .apr file. Phase 4 work (needs `apr import hf://` integration
    test + cached fixture).
  - Flip `Architecture::Bert.is_inference_verified() == true`. Still
    waiting on Phase 4 HF numerical-parity check.

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] `cargo test -p apr-cli --lib commands::rerank::` → 3/3 pass
- [x] `cargo test -p apr-cli --test cli_commands` → 8/8 pass
      (includes the `test_all_contract_commands_exist` 3-surface drift gate)
- [x] Contract `apr-cli-commands-v1.yaml` updated with new `rerank` entry

## Cross-refs

- #326 Phase 1 → #1752 (weight loading from APR)
- #326 Phase 2 → #1753 (import-load contract helper)
- #326 Phase 3 → **this PR** (CLI surface)
- #326 Phase 4 next (HF numerical parity + flip is_inference_verified)
- Direct unlock for trueno-rag MRR push 0.952 → 0.97+ via
  cross-encoder reranking (sovereign-stack alternative to ONNX
  Runtime / fastembed)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(apr-cli): apr rerank --query/--passage WordPiece mode (#326 Phase 3b)

Phase 3b of the BERT cross-encoder rerank feature (issue #326). Extends
the `apr rerank` CLI from Phase 3 (PR #1755) with an in-process
WordPiece tokenisation mode so callers don't need a separate
`apr tokenize` step:

  $ apr rerank model.apr \
        --query "what is the capital of France?" \
        --passage "Paris is the capital of France." \
        --vocab vocab.txt
  score[0] = 0.94217

The two modes are mutually exclusive: pass either the ID pair
(`--input-ids`+`--token-type-ids`) OR the text pair
(`--query`+`--passage`+`--vocab`). Mixing them returns a structured
error.

## What this PR adds

  crates/apr-cli/src/commands/rerank.rs (+~120 LOC):
    + `load_vocab_txt(&Path) -> HashMap<String, u32>` — reads `vocab.txt`
      one-token-per-line.
    + `tokenize_query_passage(query, passage, vocab_path) -> (Vec<u32>, Vec<u32>)`
      — builds `[CLS] query [SEP] passage [SEP]` with
      `token_type_ids = 0` for the query side and `1` for the passage
      side. Uses existing `aprender::text::tokenize::WordPieceTokenizer`.
    + `run(...)` signature extended with `Option<&str>` query +
      `Option<&str>` passage + `Option<&Path>` vocab; mode dispatch via
      pattern match on the option tuple with a clear-error fallback
      for mixed input.
    + 4 new unit tests:
      - `load_vocab_txt_assigns_line_index_as_id`
      - `tokenize_query_passage_builds_correct_segment_pair`
      - `tokenize_query_passage_rejects_missing_cls`
      - `tokenize_query_passage_rejects_missing_sep`

  crates/apr-cli/src/extended_commands.rs:
    + `ExtendedCommands::Rerank` adds `--query`, `--passage`, `--vocab`
      flags. `--input-ids` and `--token-type-ids` flipped to `Option<String>`.

  crates/apr-cli/src/dispatch_analysis.rs:
    + Dispatch arm passes the new Option<&_> fields to commands::rerank::run.

  contracts/apr-cli-commands-v1.yaml:
    + `rerank` entry description updated to document both input modes.

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] `cargo test -p apr-cli --lib commands::rerank::` → 7/7 pass
      (3 from Phase 3 + 4 new Phase 3b)

## What this PR does NOT do

  - Validate against a real bge-reranker tokenizer. Phase 4 (HF parity)
    work — needs cached HF tokenizer.json fixture.
  - Support the HuggingFace `tokenizer.json` format (Tokenizers crate).
    Phase 3b sticks to the simpler `vocab.txt` interface — HF
    `tokenizer.json` is a Phase 3c follow-up.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (CLI surface, ID mode)
- #326 Phase 3b → **this PR** (CLI text mode w/ WordPiece)
- #326 Phase 4 next (HF numerical parity)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(bert): apr import + rerank work end-to-end on real HF SafeTensors (#326 Phase 4)

Phase 4 of #326. Unblocks `apr import --arch bert` against real
HuggingFace SafeTensors checkpoints and ties the BERT stack together
with HF Tokenizers-format `tokenizer.json` support. Verified on
lambda-vector against `cross-encoder/ms-marco-MiniLM-L-6-v2` (86.7 MB,
6-layer 384-d MiniLM):

  $ apr pull cross-encoder/ms-marco-MiniLM-L-6-v2
  $ apr import .../57e6e922118ea840.safetensors --arch bert \
        -o /tmp/minilm-rerank.apr --allow-no-config
  ⚠ Import completed with warnings   (105 tensors, 87M output)

  $ apr rerank /tmp/minilm-rerank.apr \
        --query "what is the capital of France" \
        --passage "Paris is the capital of France" \
        --vocab .../tokenizer.json
  score[0] = 0.999805                ✅ matching pair

  $ apr rerank /tmp/minilm-rerank.apr \
        --query "what is the capital of France" \
        --passage "Cats are mammals that purr" \
        --vocab .../tokenizer.json
  score[0] = 0.000015                ✅ disjoint pair correctly ranked low

## Two defects fixed

### 1. `apr import --arch bert` panicked on `position_ids` I64 buffer

HuggingFace `transformers` registers integer buffers
(`bert.embeddings.position_ids`, optional `token_type_ids` cache)
alongside trainable f32 weights via `register_buffer`. They appear in
the SafeTensors file as `I64` tensors. The existing dequant path only
handles F32 / F16 / BF16 (see `safetensors_include_01.rs::get_tensor`)
so import aborted with:

  Failed to extract tensor 'bert.embeddings.position_ids':
  Unsupported dtype for 'bert.embeddings.position_ids': I64

Fix: add `is_non_trainable_buffer(name, dtype)` filter in
`safe_tensors_load_result.rs`. Skips tensors with integer dtype AND
HF-known buffer-suffix names (`.position_ids`, `.token_type_ids`,
`.attention_mask`, `.causal_mask`). Applied to all 3 iteration sites:
`load_safetensors_tensors`, `load_safetensors_with_f16_passthrough`,
`load_safetensors_as_f32`.

The filter is name+dtype keyed so it can't silently drop a future
quantized F32 weight named `.position_ids` (already covered by the
`position_ids_f32_is_not_buffer` falsifier).

### 2. `apr rerank --vocab` rejected HF `tokenizer.json` files

Phase 3b's loader assumed line-per-token `vocab.txt`. Real BERT
checkpoints ship `tokenizer.json` (HuggingFace Tokenizers crate
format) where:
- `model.vocab` is the bulk WordPiece map
- `added_tokens` is the special-tokens array (where [CLS]/[SEP]/[UNK]
  actually live; they are NOT inside `model.vocab` per the Tokenizers
  convention)

Fix: `load_tokenizer_json(path)` parses both sections and merges them.
New `load_vocab(path)` dispatcher routes `.json` extension to the HF
parser, otherwise legacy `vocab.txt`. `tokenize_query_passage` now
calls `load_vocab` so both formats work transparently.

## What this PR adds

  crates/aprender-core/src/format/converter/safe_tensors_load_result.rs:
    + `is_non_trainable_buffer(name, dtype)` predicate
    + Filter applied at 3 iteration sites
    + 5 unit tests covering the falsifier cases

  crates/apr-cli/src/commands/rerank.rs:
    + `load_tokenizer_json(path)` — HF Tokenizers WordPiece parser
    + `load_vocab(path)` — extension-dispatcher (.json → HF, else vocab.txt)
    + `tokenize_query_passage` now uses `load_vocab`

## Test plan

- [x] `cargo test -p aprender-core --lib is_non_trainable_buffer` → 5/5 pass
- [x] `cargo build --release --features 'inference cuda'` clean
- [x] `apr pull` 87M MiniLM safetensors → cached
- [x] `apr import --arch bert` → 87M .apr (was: aborted on position_ids)
- [x] `apr rerank --vocab tokenizer.json` produces 0.9998 for matching pair
      and 0.000015 for disjoint pair on real model (was: rejected tokenizer.json)

## What this PR does NOT do

  - Numerical-parity gate vs HF reference (`transformers.AutoModel...`).
    Phase 4b follow-up — needs `uv run --with transformers --with torch`
    to dump per-layer hidden states + cosine compare. The empirical
    matching/disjoint score gap (0.9998 vs 1.5e-5) is strong directional
    evidence that the pipeline is correct but doesn't pin per-tensor
    parity.
  - Flip `Architecture::Bert.is_inference_verified() == true`. That
    needs Phase 4b parity evidence on main.
  - Integration test in CI. The end-to-end test requires the 87M
    cached HF model + network access for first-time download; gating it
    on a CI runner with cached fixtures is Phase 4c.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank CLI, ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ vocab.txt)
- #326 Phase 4 → **this PR** (real HF SafeTensors round-trip)
- Direct unblock for trueno-rag MRR 0.952 → 0.97+ via cross-encoder rerank

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(bert): HF numerical parity verified, is_inference_verified flipped (#326 Phase 4b)

Phase 4b of #326. Demonstrates end-to-end numerical parity between
`apr rerank` and the HuggingFace reference `AutoModelForSequenceClassification`
for `cross-encoder/ms-marco-MiniLM-L-6-v2` and flips
`Architecture::Bert.is_inference_verified() == true`.

## Empirical parity (lambda-vector RTX 4090, 2026-05-17)

  | Pair                        | HF score | apr score | abs diff   |
  |---|---|---|---|
  | "France" + "Paris..."       | 0.999805 | 0.999805 | 2.98e-7   |
  | "France" + "Cats..."        | 0.000015 | 0.000015 | 1.67e-7   |
  | "ML" + "neural networks..." | 0.000020 | 0.000020 | 1.54e-7   |

  WordPiece tokenization: bit-identical input_ids for all 3 prompts.
  Raw logits: agree within ~4e-4 (f32 round-off). Sigmoid maps both to
  identical 6-decimal scores; the parity falsifier asserts < 1e-4
  absolute score diff (observed: < 3e-7).

## What this PR adds

  crates/apr-cli/tests/falsification_bert_326_hf_parity.rs (new):
    + `falsify_bert_326_phase4b_hf_parity` — `#[ignore]`-gated
      integration test that:
      1. checks for the cached MiniLM SafeTensors at the canonical path
      2. invokes `apr import --arch bert` to produce a fresh `.apr`
      3. invokes `apr rerank --query --passage --vocab tokenizer.json`
         for each canonical pair
      4. asserts |apr_score − hf_score| < 1e-4 (observed: < 3e-7)
    + 3 canonical `(query, passage, hf_score)` triples captured from
      HF reference via uv (`uv run --with transformers --with torch`)

  crates/aprender-core/src/format/tensor_expectation.rs:
    + `Architecture::Bert` now matched by `is_inference_verified()`
    + Doc-comment refreshed with the parity matrix

  crates/aprender-core/src/format/converter/tests/pmat_round19.rs:
    + `apr_import_strict_unverified_arch_test` updated: BERT now
      verified post-#326 Phase 4b (was: asserted NOT verified)

  crates/aprender-core/src/format/converter/tests/coverage_types_arch_functions.rs:
    + `test_is_inference_verified_false_gh219` no longer lists BERT
    + new `test_is_inference_verified_true_bert_gh326_phase4b`

## Test plan

- [x] `cargo test -p aprender-core --lib is_inference_verified` → 4/4 pass
- [x] `cargo build -p apr-cli --tests` clean
- [x] `cargo test --test falsification_bert_326_hf_parity -- --ignored --nocapture` → PASS
      with all 3 pairs at < 3e-7 score diff vs HF reference

## What this PR does NOT do (Phase 4c+ scope)

  - CI integration. The parity falsifier is `#[ignore]`-gated because it
    needs the 87 MB cached fixture AND the `apr` release binary on PATH;
    wiring a CI runner with both is Phase 4c.
  - Per-layer hidden-state cosine vs HF. The final-logit parity already
    verifies the full forward chain numerically; per-layer dumps would
    pin specific layers if drift ever appears, but aren't needed today.
  - HF parity for full-size models like `BAAI/bge-reranker-base` (109M).
    Should work mechanically (same architecture); test fixture sizing
    is Phase 4c work.

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank CLI, ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ vocab.txt)
- #326 Phase 4 → #1759 (real HF SafeTensors round-trip)
- #326 Phase 4b → **this PR** (HF numerical parity + is_inference_verified)
- Direct unblock for trueno-rag MRR 0.952 → 0.97+ via verified BERT
  cross-encoder rerank (sovereign-stack alternative to ONNX Runtime)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(apr-cli): apr rerank --passages batch mode + --sort + --top-k (#326 Phase 5)

Phase 5 of #326. Adds the canonical cross-encoder use case: rank
multiple candidate passages against a single query. Single-pair mode
was the smoke test; batch mode is the actual production interface
(first-stage retrieval → second-stage rerank).

## Usage

  $ apr rerank model.apr \
        --query "what is the capital of France" \
        --passages "Paris is the capital of France" \
        --passages "Berlin is the capital of Germany" \
        --passages "Lyon is a city in France" \
        --passages "Cats are mammals that purr" \
        --vocab tokenizer.json --sort --json
  {
    "model": "model.apr",
    "query": "what is the capital of France",
    "num_passages": 4,
    "returned": 4,
    "sorted": true,
    "results": [
      { "index": 0, "passage": "Paris is the capital of France",   "logit":  8.540365, "score": 0.999805 },
      { "index": 2, "passage": "Berlin is the capital of Germany", "logit": -3.200321, "score": 0.039154 },
      { "index": 3, "passage": "Lyon is a city in France",         "logit": -3.570795, "score": 0.027364 },
      { "index": 1, "passage": "Cats are mammals that purr",       "logit":-11.118653, "score": 0.000015 }
    ]
  }

Note the ranking quality: Paris (correct match) → Berlin (also a
capital, wrong country) → Lyon (also in France, wrong city) → Cats
(disjoint). That's exactly the semantic ordering a cross-encoder is
supposed to produce.

## What this PR adds

  crates/apr-cli/src/extended_commands.rs:
    + `--passages <TEXT>` flag (repeatable, `Vec<String>`)
    + `--sort` (descending by score)
    + `--top-k N` (implies `--sort`; limit output to top N)

  crates/apr-cli/src/dispatch_analysis.rs:
    + dispatch threads through the new flags

  crates/apr-cli/src/commands/rerank.rs:
    + new `run_batch` function — loads the cross-encoder ONCE then
      scores N (query, passage_i) pairs in a loop
    + sort + top-k logic with `partial_cmp` fallback
    + JSON output preserves original `index` so callers can map back
      to their first-stage retrieval ordering even after sort

## What this PR does NOT do

  - True batched forward (one matrix-of-pairs call instead of N
    sequential calls). The MiniLM forward is fast enough at 87M that
    sequential N=10..100 ranking takes < 1s on lambda-vector. True
    batching is a Phase 5b optimisation if N gets larger.
  - Streaming output for large N. The full ranked list is materialised
    in memory before printing — fine for typical RAG rerank (N ≤ 100).

## Test plan

- [x] `cargo build -p apr-cli` clean
- [x] End-to-end batch test on lambda-vector against real MiniLM:
      4-passage ranking produces correct semantic ordering
- [x] `--top-k 2` correctly truncates to top 2

## Cross-refs

- #326 Phase 1 → #1752 (weight loading)
- #326 Phase 2 → #1753 (import-load contract)
- #326 Phase 3 → #1755 (apr rerank single-pair ID mode)
- #326 Phase 3b → #1756 (apr rerank text mode w/ WordPiece)
- #326 Phase 4 → #1759 (real HF SafeTensors round-trip)
- #326 Phase 4b → #1765 (HF numerical parity + is_inference_verified)
- #326 Phase 5 → **this PR** (batch ranking — the actual production use case)

Direct unblock for trueno-rag: a typical RAG pipeline returns
top-50 BM25/dense candidates then reranks down to top-5. This PR
ships the second-stage API in one CLI call.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>