fix(GATE-PREFLIGHT-SKIP-REPORT): a skipped gate is not a green one (#998)

.agents/issue-index.md

@@ -269,4 +269,7 @@ rather than merged. `scripts/check-agent-record.py` gates both.
 | [#986](https://github.com/mudler/vllm.cpp/issues/986) | `LTX25-DFR-PIPELINE` | `DFRPipeline` (`dfr_pipeline.py` + `dfr_layout.py` @ `fd4ded7f`) has no representation in this tree — `git grep -i dfr` over `src include tests examples docs` returns ZERO product hits, against 87 `ltx2` hits in `ltx2.cpp` alone as the positive control ([#604](https://github.com/mudler/vllm.cpp/issues/604)). It matters beyond its own feature because it is the **ONLY** upstream consumer of the temporal x2 latent upsampler this project already ships: [`ltx25-temporal-upsampler.md`](specs/ltx25-temporal-upsampler.md) section 7 records the operator as ported, loader-parsed and gated but *"not reachable from any shipped pipeline"*, and `docs/FEATURES.md` carries that as `Temporal x2 ups gated, UNDRIVEN`. No issue tracked that state — `undriven` returned zero hits across open and closed issues. DFR also needs the generated-keyframe-slot READBACK that [#920](https://github.com/mudler/vllm.cpp/issues/920) refused by name and left owed after it CLOSED, so the debt had a spec bullet and no open issue; it needs the LAYOUT and the EXTRACTION but **not** the standalone single-frame decode, because DFR never decodes its slots — it hands them to the spatial upsampler (`dfr_pipeline.py:348`) and feeds them back as `initial_keyframes` (`:364`). Spec [`ltx25-dfr-pipeline.md`](specs/ltx25-dfr-pipeline.md). Campaign [#644](https://github.com/mudler/vllm.cpp/issues/644) | feature |
 | [#995](https://github.com/mudler/vllm.cpp/issues/995) | `ENG-EXPERT-STREAM` | `check-env-doc` and `test_check_env_doc` were RED on `origin/main`, so every branch cut from it inherited a preflight failure its own diff did not cause: `VT_MOE_EXPERT_STREAM`, `VT_MOE_EXPERT_STREAM_SLOTS` and `VT_MOE_EXPERT_STREAM_SLOT_BYTES` are read from `src/vllm/model_executor/models/qwen3_5.cpp` (`:5145`, `:5195`, `:5189` @ `4496ef196`) and appeared in neither `docs/ENVIRONMENT.md` (`grep -c` returned **0**) nor `scripts/env-doc-allowlist.txt`. They arrived with the `ENG-EXPERT-STREAM` W4 wiring commit `3005447f8` ([#993](https://github.com/mudler/vllm.cpp/pull/993)). Found while gating [#986](https://github.com/mudler/vllm.cpp/issues/986) and proved pre-existing with a matched-arm check rather than asserted: the three sites are in a file that branch does not touch, and `git diff origin/main...HEAD \| grep '^+.*VT_MOE_EXPERT'` returns nothing. It is a PRE-FLIGHT gate, so it failed before every edit and presented to each author in turn as a red their own diff caused -- the shape [#965](https://github.com/mudler/vllm.cpp/issues/965) and [#968](https://github.com/mudler/vllm.cpp/issues/968) both took. The discoverer deliberately did NOT fix it in flow: documenting a knob means stating its default and when to touch it, and the expert-streamer's slot accounting belongs to the row that added it, so a plausible-sounding entry written by a passer-by is how `docs/ENVIRONMENT.md` stops being trustworthy. FIXED in [#997](https://github.com/mudler/vllm.cpp/pull/997) by DOCUMENTING all three in `docs/ENVIRONMENT.md`, not by allowlisting them: a knob that changes the host memory a MoE decode reserves and disables the default-on grouped-MoE path is a deployment surface, not a kernel-internal micro-tuning switch | bug |
 | [#987](https://github.com/mudler/vllm.cpp/issues/987) | `LTX25-RETAKE` | Two `ltx-2.5` refusal messages state reasons that are no longer true. (a) `src/vllm/multimodal/ltx2_video.cpp:1608 @ 0e1bee42f` says "nothing reads `ref_video_dir` at all", and MiniMax-H3 has always consumed the directory in full (`ReadReferenceClipChw`, `src/vllm/multimodal/minimax_h3_video.cpp:135 @ 0e1bee42f`, called at `:650`); [#975](https://github.com/mudler/vllm.cpp/issues/975) inherited the wider claim from this message. The claim that holds is narrower: the LTX-2.5 engine never reads the directory's CONTENTS. (b) `ltx2_video.cpp:1636-1638 @ 0e1bee42f` says "there is no AUDIO_VAE_ENCODER key filter", and `c2019b0e3` landed `Ltx2AudioVaeEncoderKeyRules()` (`include/vllm/model_executor/models/ltx2_audio_input.h:73 @ 0e1bee42f`) with a live call through `Ltx2EncodeAudioToLatent`. Both rewritten in the `WHAT IS *NOT* THE REASON` shape in the same flow, with one assertion tied to the LOCAL fact that the LTX side now reads the directory | bug |
+| [#998](https://github.com/mudler/vllm.cpp/issues/998) | `GATE-PREFLIGHT-SKIP-REPORT` | `scripts/agent-preflight.sh` prints `All gates green.` while a guarded block never ran: the trailer block is gated on `git merge-base --is-ancestor origin/main HEAD`, and when that is false the two gates vanish from the report with no output. Fired three times in one session, twice because `origin/main` is a remote-tracking ref every worktree of the checkout shares and another worktree advanced it MID-RUN, so the `ok` count fell from 76 to 74 and the banner did not change. Same shape in the `Committed range` block, whose unresolvable-ref arm drops three more gates. A green banner over a block that never executed is a FALSE REPORT, which the file's own `audit-live-rows` comment already calls "the one unacceptable outcome", spec [`gate-preflight-skip-report.md`](specs/gate-preflight-skip-report.md) | bug |
+| [#999](https://github.com/mudler/vllm.cpp/issues/999) | — | `scripts/check-commit-style.py` `validate_range` still raises `range base must be an ancestor of range head`, so the merge-base repair `GATE-FORK-ANCESTRY` (#773) applied to `check-commit-trailers.py` never reached it: the checker aborts before reading a commit on any branch cut before the last merge of `main`. Found auditing the guards for #998, and it is why that row reports a SKIP rather than dropping the guard and letting both checkers run. Owed by [`gate-preflight-skip-report.md`](specs/gate-preflight-skip-report.md) | bug |
+| [#1000](https://github.com/mudler/vllm.cpp/issues/1000) | `ENG-EXPERT-STREAM` | `main` is RED on `check-env-doc` at `3ce1cf7c7`: `VT_MOE_EXPERT_STREAM`, `VT_MOE_EXPERT_STREAM_SLOTS` and `VT_MOE_EXPERT_STREAM_SLOT_BYTES` arrived with `3005447f8` (#993) and are neither in `docs/ENVIRONMENT.md` nor on `scripts/env-doc-allowlist.txt`, so `check-env-doc` and `test_check_env_doc` fail on every branch cut from current main. Measured in a clean worktree at that SHA with no local edits. Found running the preflight as the gate for #998, and NOT repaired there: choosing documented knob versus internal tuning switch for each var belongs to the row that added them | bug |
 | [#1023](https://github.com/mudler/vllm.cpp/issues/1023) | `ENG-EXPERT-STREAM` | The IQ1_S (ggml 19) / IQ1_XXXS (ggml 66) decode landed in [#946](https://github.com/mudler/vllm.cpp/pull/946) with every parameter EXCEPT the grid pinned only by self-consistency. The grid seal (FNV-1a digest + lane census) works and stops one table short: `ReferenceDotF64` (`tests/vt/test_ops_quant_dot.cpp:231-236`) and the G3 NMSE reference (`:915`) both decode the weight with `vt::cpu::BlockToFloat`, the function under test, so they are independent only in the SUMMATION. Three injected defects, each applied and compiled, left the suite green with an UNCHANGED assertion count: `kIq1sDelta` `0.125F`->`0.25F` (`cpu_quant_iq_tables.h:422`, affects BOTH encodings), the IQ1_S delta sign inverted in dequant AND vec_dot, and the IQ1_S scale read from `qh` bits 13-15 instead of 12-14 in both paths. Second defect, same PR: `gguf_dequant.cpp:107-116` lists no `case 19` and no `case 66`, so the expansion path throws `unsupported ggml type` for the two encodings the target checkpoints are 96.92 % made of, and `RouteGgufTensor` (`gguf_keep_quant.cpp:122`) sends a tensor there whenever `VT_CPU_REF` is on, keep-quant is off, K is ragged, or the role is not verbatim — a refusal to load on the reference lane. **ggml 18 (IQ3_XXS) carried the same omission**, pre-existing since the DeepSeek-V4 UD-IQ2_XXS port, and all three are one shared `switch` branch. Repaired by golden vectors whose EXPECTED values come from the ORACLES themselves (`ggml_get_type_traits(type)->to_float` built from `ggml-org/llama.cpp @ 237ad9b96` for 18/19 and `unslothai/llama.cpp @ 36fe8e1cc` for 66) over REAL checkpoint bytes, which is the first reference for this encoding family that is not this tree's own decoder. Also: the `2e-3` NMSE ceiling passed the doubled-delta defect that `6e-4` fails (measured 5.240e-4 unmutated, 6.967e-4 mutated on `iq1_s`), and on `iq1_xxxs` that defect moves the statistic the WRONG WAY (3.109e-4 -> 1.420e-4), so no ceiling can catch it and only the goldens can; and both new census cases claimed TOTAL coverage of 1702 records while summing to 864, F32's 838 tensors omitted. Spec [`expert-streaming.md`](specs/expert-streaming.md) | bug |