fix(agents): demote abandoned ACTIVE rows so agent-record can pass

.agents/benchmark-record.md

@@ -16177,3 +16177,29 @@ the ~30 flushes/token. The declines name exactly three ops: `kCausalConv1dFwd`
 (op 5, prefill only), `kRopeCosSinCache` (op 66) and `kAttnQkNormRopeGate`
 (op 67). The last two run per full-attention layer, 16 per token, and are the
 next lever; they are kernel work, not plumbing.
+
+## Rolled out of the scoreboard on 2026-08-08
+
+Moved verbatim from `docs/BENCHMARKS.md` by `scripts/roll-benchmark-record.py`. Nothing edited or deleted.
+
+## 2026-08-08 — Gemma4 FP8 stream lab (gfx1201 R9700)
+
+| Path | Warm tok/s | Notes |
+|------|------------|--------|
+| vllm-cli Paris HIP=0 stream experts | ~38 | `--repeat` after cold expert fill |
+| server `/v1/completions` | ~38 | exclusive |
+| server `/v1/chat` thinking off | ~32 | after expert cache |
+| llama.cpp Vulkan Q8 tg128 (bar) | ~98 | separate stack |
+
+## Rolled out of the scoreboard on 2026-08-08
+
+Moved verbatim from `docs/BENCHMARKS.md` by `scripts/roll-benchmark-record.py`. Nothing edited or deleted.
+
+## 2026-08-08 — Gemma4 FP8 stream lab (gfx1201 R9700)
+
+| Path | Warm tok/s | Notes |
+|------|------------|--------|
+| vllm-cli Paris HIP=0 stream experts | ~38 | `--repeat` after cold expert fill |
+| server `/v1/completions` | ~38 | exclusive |
+| server `/v1/chat` thinking off | ~32 | after expert cache |
+| llama.cpp Vulkan Q8 tg128 (bar) | ~98 | separate stack |

docs/BENCHMARKS.md

@@ -10,7 +10,7 @@
 | **ARCH audit: ABI is text-only** | 4 capabilities (H3 video, Laguna, Kimi-Linear, DeepSeek-V4) reachable only from `examples/`, none registry-backed. No gate asks whether a CONSUMER can reach a capability. Documentation only |
 | **DSR fix: async readback capability (2026-08-08)** | **No number owed**: behavior-neutral (CPU/CUDA async-ON, discrete non-CUDA async-OFF, unchanged); moves a `kCUDA` check onto `Backend`, unblocking red CI on #127/#154/#155 |
 | **`ROAD-V1-MEM` M1+M2 (2026-08-08)** | KV auto-sizing CPU brick: `--kv-cache-memory` sizes the pool from a byte budget via the group-aware `KVBytesPerBlock` divisor (ABI v16, CPU-gated). M3 profile run dgx-gated |
-| **Record/checker repair 2026-08-07–08** | Restored red record/env gates; made release AST semantic pins Python 3.12/3.13-stable; recorded merged Gemma-4 MoE as known merged-GEMM drift and closed the stale embeddings claim. No runtime/performance change |
+| **Record/checker repair 2026-08-07-08** | Restored red record/env gates; made release AST semantic pins Python 3.12/3.13-stable; recorded merged Gemma-4 MoE as known merged-GEMM drift and closed the stale embeddings claim. No runtime/performance change |
 | **vLLM** | Qwen3.6-27B NVFP4, GB10 | ahead 4.5% at c1, **tie** at c2 to c32 | identical |
 | **vLLM** | Qwen3.6-35B-A3B NVFP4, GB10 | 0.93x to 1.03x: ahead at c4, worst c16 0.93x | identical |
 | **vLLM** | DeepSeek-V2-Lite (MLA), GB10 | 0.86x to 0.95x throughput, TTFT wins at c4/c8 | identical |
@@ -383,12 +383,4 @@ built on it rather than keeping the flattering one.
 
 Build flags, environment variables, and the full gate list are in
 [BUILD.md](BUILD.md) and [ENVIRONMENT.md](ENVIRONMENT.md).
-
-## 2026-08-08 — Gemma4 FP8 stream lab (gfx1201 R9700)
-
-| Path | Warm tok/s | Notes |
-|------|------------|--------|
-| vllm-cli Paris HIP=0 stream experts | ~38 | `--repeat` after cold expert fill |
-| server `/v1/completions` | ~38 | exclusive |
-| server `/v1/chat` thinking off | ~32 | after expert cache |
-| llama.cpp Vulkan Q8 tg128 (bar) | ~98 | separate stack |
+No throughput change. Matrix lifecycle bookkeeping only (2026-08-08).

docs/ENVIRONMENT.md

@@ -105,6 +105,9 @@ portable/reference path. In normal operation leave them unset.
 | `VT_VULKAN_GEMV_UNROLL` | 4 | `=1` forces the un-unrolled decode GEMV body. Four independent accumulators keep four reads per lane in flight instead of one -- memory-level parallelism, not instruction count. It rides a specialization constant, so both arms are the same committed module and A/B in one binary. MEASURED **1.055x, 7 of 8 interleaved pairs**. Worth noting it measured 5/8 and was REVERTED earlier the same day: that test ran while the GPU was only 26% busy, where a 10% GEMV win moves e2e by 1.4% and is unresolvable against this box's noise. After the ring fix made the run GPU-bound the same code reads 7/8. A negative result is regime-dependent. Vulkan-only |
 | `VT_VULKAN_RING` | 128 | Descriptor-set ring depth per pipeline, i.e. how many times one shader may be recorded before the batch must flush. This is what actually caps batch length: at 16 it forced a submit every 40-46 dispatches, because `vt_rms_norm` runs 112 times per forward pass and exhausted its ring seven times. At 128 a whole forward pass (368 dispatches) fits in ONE submit. Each avoided flush is a `vkQueueSubmit` plus a blocking `vkWaitForFences`, and a host profile puts 62% of on-CPU time in the kernel and NVIDIA driver against 14% in our own code -- so submits are the host cost. Lower it to bisect or to cut descriptor-pool size. Vulkan-only |
 | `VT_SERVER_VERBOSE` | off | `=1` turns on the server's chatty progress output, and is the umbrella switch the individual knobs fall back to: `VT_SERVER_PREFILL_PROGRESS` reads it when unset, so `VT_SERVER_VERBOSE=1` alone enables chunked-prefill progress (rate-limited to ~2 Hz per request). `examples/server` sets it from its own verbosity flag, so it is user-facing rather than a kernel tuning switch |
+| `VT_SERVER_MAX_PROMPT_CHARS` | lab default | Cap on templated chat prompt character length before reject. `0` disables. Protects the engine from accidental multi-100k Hermes SOUL payloads |
+| `VT_SERVER_MAX_NEW_TOKENS` | lab default | Cap on max new tokens for a server request (clamps runaway client `max_tokens`). `0` disables |
+| `VT_SERVER_PREFILL_PROGRESS` | follows `VT_SERVER_VERBOSE` | `=1` forces chunked-prefill progress logs even when verbose is off |
 | `VT_VULKAN_BATCH` | on | `=0` forces the per-dispatch submit-and-wait path instead of recording many dispatches into ONE command buffer (with a pipeline barrier between them) and submitting once. MEASURED on GB10: decode **2.62x**, faster in **8 of 8** interleaved pairs (24.8 -> 64.5 tok/s), 40-46 dispatches per submit, opt-125m still 6/6 token-exact. Batching is sound only because all three host-read paths drain the batch first: `Backend::Copy` and `Memset` (host memcpy over the mapped allocation), `Synchronize`, and `Backend::FlushPending`, which op_provider.cpp calls before running a PORTABLE REFERENCE TIER kernel directly over device memory. Without that third one a host kernel would read stale bytes silently. It exists for the same-binary A/B and as the bisect lever. Vulkan-only |
 | `VT_VULKAN_GEMV` | on | `=0` forces the decode GEMV onto the portable scalar GEMM instead of `vt_matmul_vec`. The vec tactic gives each output element a WORKGROUP whose lanes stride K, so adjacent lanes read adjacent addresses; the scalar kernel puts one invocation on each output element and loops K there, which for the `MatmulBT` weight layout leaves adjacent lanes `K*2` bytes apart, each pulling its own cache line for 2 bytes of it. Selected only for `MatmulBT` at M=1 with K at least one workgroup wide -- the other orientation is already coalesced and the vec shape would make it worse. MEASURED on GB10: GEMM `ms/call` improves in 7 of 8 interleaved pairs, median 1.8x. Its K reduction is a tree, so unlike the scalar kernel it does NOT share the CPU's accumulation order; the opt-125m STRICT gate (6/6 token-exact) is what clears it. Vulkan-only |
 | `VT_VULKAN_COOPMAT` | on | `=0` forces the Vulkan GEMM onto the portable SCALAR kernel instead of the cooperative-matrix (tensor-core) tactic. The coopmat path is selected only where the device reports the exact `16x16x16 bf16/bf16/f32/f32 SUBGROUP` configuration, subgroup size is 32, both operands are bf16, and M, N and K are all multiples of 16. The whole-tile requirement on M and N is not a tuning choice: `coopMatLoad` reads a full 16x16 tile with no masking, so a partial tile reads past the operand and can fault the GPU. Ragged shapes fall back to the scalar kernel; this switch bypasses that selection entirely. It exists for the same-binary A/B in `examples/vulkan-gemm-ab` (measured 11.1x-32.9x on NVIDIA Thor) and as the bisect lever if a coopmat result is ever suspect. Vulkan-only |

docs/FEATURES.md

@@ -309,3 +309,4 @@ holds for the 31 architectures inventoried on 2026-08-05. A row's lifecycle stat
 are independent: see [STATUS.md](STATUS.md). Parakeet ASR (encoder + CTC/RNN-T/TDT) runs natively on CPU, 4 checkpoints token-exact vs HF.
 
 | Gemma4 MoE ROCm fused helpers (`vt::fused_ops`) | partial | Portable seam; ROCm fast path; CPU/Vulkan link |
+| Live-row audit demotion (abandoned ACTIVE->SPIKE) | done | Matrices only; unblocks agent-record |