[plotarmordev]

Description and motivation

I move the full-model engine pin from TensorFold d1018b31 to v1.1.9 (465e48b6). The full-model patch series is now empty. v1.1.9 already includes every patch I carried:

Old patches	In TensorFold since	Upstream
0001–0011 (prefill rows, replay fix, frame budget, controls allowlist, voice catalogs, silence guard and redraws)	v1.1.4	#1119, #1120, #1134, #1135, #1152, #1157–#1162
0012 reference-prefill reuse	v1.1.5	a06a4dff, #1237
0013/0014 request sampling controls and JSON boundaries	v1.1.6	#1277 (e19b8073, 90082556)

v1.1.9 also includes the slot-release fix (7e43ebeab, #1438), which shipped in v1.1.8. So this bump needs no local patch for it.

Patch check against v1.1.9: 0013 and 0014 no longer apply with git am, because the files they add (docs/speech-sampling.md, zig/src/server/speech_sampling*.zig) already exist there. I applied 0001–0014 to d1018b31 and compared the result with v1.1.9:

• docs/speech-sampling.md is identical.
• speech_sampling.zig and its test differ only by upstream's later fix 4a556244, which sends a temperature of -0/-1e-400 to the sampler as +0.
• v1.1.9's zig/src/server/root.zig registers both test files.

The same is true for the dialogue-speaker patch proposed as full-model 0015 in #28: v1.1.9 already ships it (#1278), so it would not apply on this pin either.

What changes:

• engine/UPSTREAM now pins v1.1.9. The 14 full-model patches are removed. engine/patches/SHA256SUMS stays as an empty file, which declares the empty series.
• scripts/build-engine.sh accepts an empty series, but only when the manifest is present and empty. A missing manifest still fails before checkout, and so does a manifest that lists a patch that is not there. A new model-free build test covers both cases.
• recipe/pilot.py passes TF_DRAMA_PREFILL_ROWS=128 for full and custom checkpoints on the Linux native backend. Upstream defaults to single-row prefill, and old patch 0001 turned batched prefill on. NVFP4 and the sglang backend are unchanged.
• README, engine/patches/README.md, CONTRIBUTING, NOTICE, the macOS and sampling docs and CHANGELOG now describe the new pin. They also name its two behaviour differences:
  • With the mid-silence rule on, X-Silence-Mid-Trips now counts only the returned take. This has been true since v1.1.4 and is unchanged through v1.1.9.
  • The -0 temperature sign fix above.

The NVFP4 pins (CUDA and Metal) and their patch series are untouched.

This replaces the earlier 1.1.4 bump branch, which I will not merge.

---

Testing

CPU only. I built and tested on a GB10 host, without using its GPU.

• Engine builds, ZIG=zig-0.17.0 NVCC=/usr/local/cuda/bin/nvcc JOBS=4 scripts/build-engine.sh --weights full <dir>:
  • A, on main db6ba7da: d1018b31 + 14 patches = e0f55c97. Exit 0 in 3:46. tensorfold-native sha256 93fc4ca1…d249, reports version 1.1.1.
  • B, on this branch cb958306: 465e48b6 + 0 patches = 465e48b6. Exit 0 in 4:32. tensorfold-native sha256 ca64be09…9c89b, drama3-generate sha256 32bbb744…6027, reports version 1.1.9.
  • The B binary's serve --help lists the guard flags the recipe uses. --voices, --allowed-controls and --max-frames don't appear in the help text on A or B; I found them in v1.1.9's zig/src/server/cli.zig.
• python3 -m unittest discover -s recipe -p 'test_*.py': 48 tests OK. The 15 skips are the explicit macOS subprocess smoke tests.
• The new build test fails against main's scripts/build-engine.sh (1 failure) and passes with this change.
• python3 bench/stream_check.py --self-test: passed.
• bash -n scripts/build-engine.sh: OK.
• zig build test -Dnvcc=/usr/local/cuda/bin/nvcc in the v1.1.9 engine tree: exit 0 in 9:23. The test output includes expected-failure lines from negative cases. The build host exposed no CUDA device, so this covers host-side tests only.

Not run yet: GPU A/B. I will compare main (A) with this branch (B) using the guard pilot: builtin and catalog probes, 24 + 24 items, checked item by item against A, plus sequential drives at 0 and 200 ms gaps on B. It runs only when the GPU is free. I will add its result here. Until then this pull request has no audio-identity or qualification evidence. Byte identity with A is not guaranteed: upstream changed the engine between d1018b31 and v1.1.9, and the A/B will show how much.

---

Performance or quality claim

None.

---

Checklist

• One change per patch, new patches at the end of the series, SHA256SUMS and engine/patches/README.md updated (series emptied; manifest kept empty)
• scripts/build-engine.sh applies the whole series and builds from a clean checkout
• Every behaviour change has a deterministic test that fails without it
• No dead code, debug output or leftovers
• No personal voices, recordings, private names, host names or private paths in code, fixtures, docs, evidence or commit messages
• Where audio should not change, compare_gate.py reports "identical": true and stream_check.py passes; where it changes on purpose, the qualification gates are reported before and after (pending the GPU A/B)

[plotarmordev]

Replaced by #33, the same change rebased onto main after #28.