0ad332bb4a9bd00600816e424f18b907eb3c39d4
768 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 vh
|
0ad332bb4a |
feat(booth): per-row link removal + render the link board as real UI
The standing link board is the one MULTI-WRITER booth -- every agent session appends operator-facing URLs to it. "Delete the folder" was the only granularity available, so removing one dead link meant hand-editing markdown. It is 32 rows and only grows. booth links row number, entry id, raw row booth unlink 3 by row number booth unlink 8b40e0a5 by entry id (what the UI's x posts) POST /b/<name>/unlink form field `entry` = content id ROWS ARE ADDRESSED BY CONTENT ID, NEVER BY POSITION. The board is append-only and multi-writer: another session can post between listing it and clicking x, and an index would then delete a neighbour. An id either matches the row you saw or matches nothing. A row number typed at the CLI is resolved to its id BEFORE anything is deleted. Appends and prunes now take the same flock on .links.lock, so a post cannot be lost inside a prune's read-modify-write. UI: a booth carrying links.md renders as rows -- description, URL, provenance, copy button, per-row x -- instead of a markdown blob. links.md is filtered out of the gallery so it does not appear twice; the header counts LINKS not files; the empty-state and the one-click "Wipe now" both stand down for a board (same rule as the kept lane: nothing durable is one click from gone). booth/links.py extracted, STDLIB ONLY. The CLI needs this logic and must not require the service venv -- importing app.py drags in FastAPI, so deleting a line from a text file would have needed a web framework installed. THREE BUGS FOUND BY TESTING, all in the shell wrapper while the module was correct throughout -- module-only tests would have caught none of them: - `[ "$n" -eq 0 ] && echo ...` as the LAST statement made `booth links` exit 1 whenever the board had rows. `unlink`'s index lookup calls it inside $( ) under `set -e`, so a successful listing killed the caller and the removal silently did nothing while reporting success. - ids are 8 hex chars and roughly one in forty is ALL DIGITS; those were read as row numbers, resolved to nothing, and removed nothing. Now disambiguated by the id's actual shape, not by "is it numeric". - filtering links.md out of the gallery left `items` empty, so a full board rendered "This booth is empty" and an empty <div class="gallery"> under 32 visible rows. 87 tests (was 76): parser tolerance of hand-written prose, content-id stability across concurrent appends, removal precision, UI branch behaviour for board/normal/empty booths, and subprocess CLI tests pinning the two shell bugs. Deployed to nh3-dev and verified against the live 32-row board read-only; board file byte-identical afterwards. |
||
|
vh
|
4be880f36c |
feat(booth): kept boards can be deleted from the UI; document the TTL-reset trap
Kept boards had no delete path in the UI at all. The kept lane deliberately omits the wipe control -- a one-click wipe next to the durable stuff is a footgun -- but "deliberate" had been implemented as "impossible": the only routes out were ssh or a hand-written API call. Now it is two deliberate acts. A `release` control on kept cards drops the sentinel, the board moves to the ephemeral lane, and the existing x wipes it from there. Release is reversible -- POST /b/<name>/keep pins it again. POST /b/<name>/unkeep release the pin POST /b/<name>/keep pin it (round-trip, so release is not a one-way door) FOUND WHILE TESTING, and it invalidates the previously-documented workaround: removing the sentinel BUMPS the booth directory's mtime, and booth age is the newest mtime in the tree -- so a released board's clock RESETS from 10,000s to 0s and it survives another full TTL. The old comment said "remove the sentinel first (it rejoins the sweep)", which is true but means the board lives another 24h, not that it gets reaped. Unkeep-and-wait is a delay, not a delete. test_releasing_a_board_RESETS_its_ttl_clock pins that behaviour deliberately so nobody re-derives the workaround. Release is what unlocks the x; the x is what deletes. CLI: `booth rm` already worked on kept boards but said nothing about it. It now announces "(was KEPT -- durable board)" so wiping something durable can never look identical to wiping run output. Not a block -- a CLI user naming a booth is being explicit. 5 new tests (67 pass). Verified live on nh3-dev: release renders on all four kept boards, the ephemeral lane keeps its x, and the links board is untouched with its sentinel intact. |
||
|
vh
|
b8a535507a |
feat(judge-bench): keep the judge harness; warn about the 7-way alias collision
Operator: keep the benchmark. It has a named second use (brokkr-smithy-dev wants gen vs a trained reward model once their tournament converges) and a demonstrated first one -- it caught a seat that had been coin-flip-grade for five weeks with nobody measuring it. Harness promoted from scratch to tools/judge-bench/: - paths de-hardcoded; runs from its own directory - proper CLI: --models (REQUIRED), --repeats, --limit, --gateway. Required on purpose: a stale default would silently benchmark a retired seat, and the original default (selene-1-mini-8b) now 400s. - README states the limitation rather than burying it: 24 items of the author's own design, a screen and not a verdict. This harness scored the same pair 83 vs 96 while brokkr's corpus ranking task scored it 47 (chance) vs 94. Both honest; absolute scoring on designed items is an easier task than ranking real text. - records brokkr's technique, which is better than anything here: a control constructed so the correct answer is DEFINITIONAL rather than judged cannot inherit the designer's error (item vs itself, response vs its own truncation, text vs its own clauses permuted). Add those before adding more judged items. Gateway: comment-only warning at the head of model_list. SEVEN aliases now resolve to the same weights (chat-judge, classifier, gen, image-judge, qwen-image-bench, summarizer, summarizer-large -> qwen3.8-27b-uncensored). That is intended under ADR-0012, but it has a sharp edge brokkr flagged: cross-checking a result against another alias measures NOTHING when they are the same model -- agreement is an echo, not corroboration. The note names the other current collisions (glm-5.2 x4, TTS x4, reranker x2), gives the /model/info one-liner to check, and records that probes should resolve alias -> backing at run start AND end because the response `model` field returns the alias, so a swap is otherwise invisible. Verified: config still parses, diff is comment-only, canonical re-synced. |
||
|
vh
|
ca3c984f93 |
feat(selene): retire the seat; chat-judge -> gen, selene-1-mini-8b 404s by design
Benchmarked selene against gen on selene's own job: 24 designed judge items with checkable ground truth, pairwise + absolute modes, 3 repeats, on BOTH a neutral JSON prompt and Selene's native Atla template. 288 calls, all free local. neutral JSON selene 20/24 (83%) gen 23/24 (96%) native Atla selene 21/24 (88%) gen 22/24 (92%) gen won on both templates and selene's BEST sat below gen's WORST. Selene was given its own fine-tuned template as a fairness check; it gained one point, not the three it needed. Decisive defect: selene cannot emit "tie" -- 0/2 on both templates, forcing a winner on every equivalent pair. For eval work that is the case that matters most. gen returned tie correctly on the JSON template. Selene also compressed the 1-5 scale (clustered at 2s and 4s) where gen used it fully. Selene's only win was ~3x latency, unexercised at ~60 calls/day with zero queueing. TWO NAMES, TWO DIFFERENT TREATMENTS, deliberately: - chat-judge -> repointed to gen. It is a ROLE alias and ADR-0012 says consumers bind the capability, not a concrete model. Sampler profile copied from image-judge (temp 0, top_p 1.0, top_k 1, thinking off) so the served config matches the benchmarked condition. - selene-1-mini-8b -> REMOVED. It 404s. It was NOT aliased to gen. A served-name is a contract about what the model IS; answering it with a different model hides a material change behind a stable string. Operator ruling: "never repoint a named model at a different model's endpoint -- that is intentionally misleading." Verified: the gateway now returns HTTP 400 "Invalid model name" for it. Reclaimed 17.2 GiB on ana-ml2 GPU 1 (free 1,818 -> 19,450 MiB) on a card that had under 2 GiB of headroom. gen already runs on GPU 0, so the judge role moved onto an existing seat rather than allocating anything new. Canonical litellm config synced from the host; ana-ml2 README and recommended-model-settings updated. compose.yaml kept for reference, not deployed. |
||
|
vh
|
a896c0a5a9 |
feat(playbooks): sweep world-readable secret-bearing .env files to 0600
Eight stacks on ana-docker kept secret-bearing compose .env files at mode
0644 -- readable by every local account on a box with four interactive
users. Verified as a real exposure, not a theoretical one, by reading one
as `nobody`. Six other stacks already used 0600, so this converges on the
existing house pattern rather than inventing one.
Swept (all verified mode 600, unreadable by nobody, compose config still
rendering as the deploy user, container untouched):
vaultwarden traefik beszel gitea-runner
miniflux news-digest searxng vor
Post-sweep the host has zero secret-bearing .env readable by nobody.
Checked before writing the playbook, and re-checked by the playbook itself
so a bad case cannot be swept in by accident:
- every target is owned by lkraven, the deploy user, so 0600 preserves the
deploy path (asserted by rendering compose config AS lkraven, not root --
checking the mode proves the bits changed, only rendering as the deploy
user proves the next deploy still resolves its variables)
- none is bind-mounted into a container. vaultwarden looked like it was;
that `- .env` is under `env_file:`, not `volumes:`. A genuinely
bind-mounted .env is read by the container UID and 0600 could break it,
so the playbook refuses that case.
Two gotchas recorded in the file:
- elway's variable regex eats any bare identifier in braces, so a docker
--format Go template containing {{end}} or {{println}} fails as an
undefined variable. Grep the raw inspect JSON instead.
- the `ana-docker` ssh alias resolves to lkraven, who needs a sudo
password; run elway against infra-ops@10.250.50.70 for NOPASSWD.
|
||
|
vh
|
9642952a54 |
docs(hrafn-ci): mirror the now-canonical vh/hrafn pipeline; record two failed runs
claude-bot holds write on vh/hrafn as of 2026-08-23, so the canonical copy of the pipeline moved there and infra-ops maintains it directly instead of routing patches through the repo holder. The files here are a verified mirror (byte-identical to live at 22e0eb9d75a6). Live state: run 9922 green, and both new content assertions executed rather than merely existing -- verify 4/5 host tree matches shipped context (a99ce748a0c9...) verify 5/5 image source matches host source (06f209fd0641...) The CI-computed context hash matching on the host is the end-to-end proof that the converge lands what CI ships. Its absence is what let the frozen-source bug survive every green deploy. Also records why the HEAD == GITHUB_SHA assertion was added and then removed: it needed the git binary (run 9920, exit 127), and installing git flipped actions/checkout@v4 from its node implementation to the git binary, which died on a missing CA bundle (run 9921). A nice-to-have assertion changed the checkout code path and broke a working pipeline; it guarded a hypothesis that proved wrong, so it went rather than getting ca-certificates bolted on. |
||
|
vh
|
b38c369313 |
fix(hrafn-ci): staging dir inside the rsync target froze host source silently
Root cause of nevermore-claude's report that v1.0.0 deployed green while the host kept serving 0.1.0. The staging dir was $compose_dir/.stage -- INSIDE the rsync target. So `rsync -a --delete $compose_dir/.stage/ $compose_dir/` deleted .stage from the destination (absent from the source listing) DURING the transfer, destroying the source mid-copy. Reproduced exactly: before: app.py="OLD" leftover.txt .stage/app.py="NEW" after: app.py="OLD" leftover.txt GONE, .stage GONE Deletion worked; the copy silently did not. So the directory looked converged while host source stayed frozen at the first manual rsync, and because the build's COPY inputs never changed, Docker full-cache-hit and every SHA tag aliased one image. The provenance guarantee was false. Nothing caught it because the verify steps asserted the marker, health, and a 200 from /readyz -- all of which pass on a frozen host. None measured content. Fixes: - stage at /tmp/hrafn-deploy-stage, outside the target - CI computes context_sha256 over the shipped file list; the playbook recomputes it on the host post-converge and fails on mismatch - compare the running container's src/**/*.py against the host's, catching a SHA tag naming layers the image does not contain - checkout clean:true + assert HEAD == GITHUB_SHA so a reused runner workspace fails the job rather than shipping a stale tree Declined --no-cache: a cache hit is correct when the context is genuinely unchanged, and the new assertions prove the property directly rather than brute-forcing it. The container-vs-host check compares only *.py -- `pip install .` generates src/hrafn.egg-info/* inside the image and __pycache__ appears at runtime, so a naive `find src -type f` compare false-fails on every healthy deploy. Verified against the live container before shipping (12 host files, 18 in container, 0 content differences). |
||
|
vh
|
bb19a96f39 |
fix(playbooks): compare image IDs, not the created-from tag; make the repin idempotent
Two defects the worldtree-pinned case exposed in the guard written an hour ago. 1. The guard compared the container's .Config.Image STRING against the tag being pinned. That string is only the tag the container was CREATED from, which can differ from what it actually runs: worldtree-pinned was created from `:latest` back when that tag pointed at 446e5807, and `:latest` has since moved to b19afd71d7cc. So the guard refused an instance whose pinning was correct and necessary. Now it resolves the target tag to an image ID and compares that against the running image ID -- asserting the thing actually cared about, that this tag names the bytes now running. It also fails closed when no such local tag exists. 2. The sed step reported CHANGED unconditionally, so a re-run on an already-pinned instance claimed work it had not done. Gated behind a `when:` that skips when the line is already correct; a second run on demo now reports "2 ok, 0 changed, 2 skipped / overall: OK". Applied to worldtree-pinned under worldtree-dev authorization. That instance needed a `docker tag` first -- its image was DANGLING (no repo tags, kept alive only by the running container), so the fleet's frozen reference was one `docker rm` from garbage collection. Tagged as :446e5807bf43, then pinned. All three instances now render a SHA with no floating tag anywhere: worldtree -> :ae88a057c0ed worldtree-personal -> :f63529168c13 worldtree-pinned -> :446e5807bf43 Nothing restarted -- pinned still Up 3 months, its start time unchanged. |
||
|
vh
|
064181a8fb |
feat(playbooks): re-pin Worldtree WORLDTREE_IMAGE off the floating :latest tag
Both corviduo-dev Worldtree instances carried `WORLDTREE_IMAGE=.../worldtree:latest` in their .env while running SHA-tagged images built the same day. The local :latest tag pointed at b19afd71d7cc, built 2026-06-14 -- 69 days stale. Any `docker compose up` on either instance, by anyone, silently downgraded that service by 69 days: the same footgun behind the 2026-06-15 outage. Applied under worldtree-dev authorization (Worldtree #410): demo -> gitea.phasefinal.com/vh/worldtree:ae88a057c0ed personal -> gitea.phasefinal.com/vh/worldtree:f63529168c13 Both runs verified compose config resolves every service to the pinned SHA with no :latest remaining, and that no container restarted. The edit is inert by design -- it changes what the NEXT recreate pulls. The playbook guards against pinning a SHA that is not the one actually running, which would re-arm the same hazard with a different image. Also records the worldtree-pinned case, deliberately NOT changed here: that instance runs a DANGLING image (sha256:446e5807, no repo tags), kept alive only by the running container. It has no tag to pin to, so it needs `docker tag` first -- and an untagged image referenced only by a container is one `docker rm` from garbage collection, which for the fleet's frozen reference instance is worth fixing on its own merits. Out of the authorized scope (demo + personal); raised with worldtree-dev. Stopgap: the durable fix is the deploy workflow stamping the deployed SHA into .env at each deploy, queued repo-side with worldtree-dev. |
||
|
vh
|
11b9d1891e |
fix(hrafn-ci): make the deploy converge instead of accrete
The first CI run shipped clean but revealed a design gap in the playbook: unpacking the context tarball in place overwrites tracked files and never removes anything. Leftovers from the pre-CI hand-rsync (tests/, docs/, ROADMAP.md, persistent-memory.md, CLAUDE.md, LICENSE) survived the deploy and had to be cleaned off ana-docker by hand. That is the same failure class that produced the mess in the first place: a deploy that only ever adds cannot return the host to a known state. - unpack to a staging dir, then rsync --delete onto the compose dir - protect host-owned .env and .deployed by name - add .env.example to the context tarball so converge does not delete it - record in the workflow that the tar list is now AUTHORITATIVE: anything omitted is removed from the host on the next deploy Re-validated with `elway --dry-run` (9 steps, 3 verify, parses clean). Not yet in vh/hrafn -- infra-ops has no write access there, so this is offered to the repo holder rather than pushed. |
||
|
vh
|
b001d0cb2e |
feat(hrafn): author the CI deploy that replaces the hand-rsync path
hrafn was handed to infra-ops for uptime ownership with no CI deploy and no commit provenance -- the image was always local/hrafn:v1 and the whole working tree lived in the compose directory. These two files fix both. They are authored here because infra-ops owns hrafn's uptime, but they belong in vh/hrafn; claude-bot is not a collaborator there, so they are handed to the repo holder rather than committed directly. - playbooks-deploy.yaml -> vh/hrafn playbooks/deploy.yaml - gitea-workflows-deploy.yaml -> vh/hrafn .gitea/workflows/deploy.yaml Design calls recorded in the README: the build context travels as one tarball rather than per-file upload steps (nevermore's pattern fails open when a new source file has no matching step), and the playbook refuses to deploy unless .env exists at 0600 -- a guard prompted by it arriving 0644 with a live bearer token in it. Validated with `elway --dry-run`, which caught a real interpolation bug during authoring. No new Actions secrets needed. |
||
|
vh
|
b6924de728 |
feat(hrafn): register the browser-fetch service and tighten its env perms
nevermore-claude handed hrafn to infra-ops for uptime ownership. Intake: verified health independently, brought it into the inventory, and fixed one security defect found during the check. - canonicalize stacks/hrafn/ (compose.yaml + .env.example + README) - list hrafn in the ana-docker running-stacks table - README records the load-bearing bits: shm_size 1gb is required for Chromium, playwright and the base image are version-coupled, SSRF denies private targets by default, and restart:unless-stopped does NOT act on healthcheck failure Security fix applied on the host, not in this tree: /opt/docker/compose/ hrafn/.env was 0644 with a live 57-char bearer token in it, readable by every local account (verified by reading it as `nobody`). Tightened to 0600; owner unchanged so the deploy path still works, confirmed via `docker compose config` as lkraven. Container untouched and still healthy. Known gaps recorded rather than silently accepted: no CI deploy, and the image builds from an rsync'd working tree living in the compose directory, so the running image has no commit provenance. |
||
|
vh
|
7bf17dd39e |
fix(filezilla): set restart: unless-stopped and canonicalize the stack
The filezilla container on vm-esh-nas shipped with no restart policy. It was SIGTERMed during the 2026-08-18 host shutdown and never came back, staying down four days while dockge/dozzle-agent/beszel-agent all recovered on their own. - add `restart: unless-stopped` (applied on the host, container recreated and verified serving 200 on :5800 with all four /NAS mounts visible) - promote the previously un-canonicalized compose into stacks/filezilla/ so the policy is version-controlled rather than host-only - record the missing-restart-policy failure mode in the host README |
||
|
vh
|
837fa362fc |
memory: snapshot — sec rebuilt on DFlash2 + newer vLLM; quant tokenizer defect fixed fleet-wide
Rewrites the in-flight section (140 lines to 18) now that the AI-seat work has settled, promoting the durable calls into the dated decision log where they will not decay: DFlash2 measured and promoted to sec's compose stack, the calibration-truncation defect fixed at source in the quant pipeline, sec retuned after a runtime OOM, the Max-Q spread disproved by telemetry, ESH dual-stack with the Cityside static proven unprovisioned, and speaches live with the weak-gate finding. Carries forward the two things a fresh session must not get wrong: the sec degeneration question is confounded because engine and drafter changed together, and neither the 2k nor the 10k observation is evidence. Auto-archived one entry (Recent decisions: 1) to archival-memory.md. Eight further candidates were held back by the guards -- open deferred work or referenced by in-flight state. |
||
|
vh
|
6e82899ba7 |
fix(mog-sec): retune to 0.52/420K after a runtime OOM at 0.55/480K
The 0.55 configuration booted cleanly, passed every startup check, and then killed the engine on an ordinary request of roughly 20k tokens: torch.OutOfMemoryError allocating 614 MiB in the GDN causal_conv1d path with 443 MiB free. The container self-recovered via restart: unless-stopped. Context length was not the cause. gpu-memory-utilization is not a hard reservation. Weights and KV are reserved up front, but activation memory is allocated on demand and the profile that sizes it uses dummy data at max_num_batched_tokens. The profile predicted 3.62 GiB; the process sat about 1 GiB over its entire budget even at idle. With six vLLM containers sharing GPU1 there was no slack left to grow into, and a modest allocation lost the race. 0.52 leaves roughly 7.7 GiB free against 4.6 GiB at 0.55. Records a measurement that governs how max-model-len can be chosen at all: the KV pool varies between boots. Two consecutive boots at 0.52 produced 425,663 and 453,600 tokens, a 6.6 percent swing, because the pool is sized from free memory at startup and that depends on what the other tenants hold at that instant. 420,000 sits under the lower observation so the seat starts in both conditions. Sizing to the higher one would boot today and refuse tomorrow, which is why the value was measured across boots rather than estimated from one. Concurrency of about 1.0 to 1.08x means one request at full length. Shorter requests still batch normally, since vLLM schedules by tokens rather than by max-model-len. |
||
|
vh
|
8389470898 |
feat(mog-sec): promote the DFlash2 configuration into the compose stack
Operator approved after real-use testing. The experimental standalone container is retired and stacks/mog-sec is canonical again, with restart: unless-stopped so the configuration survives a reboot. Cutover verified against the container it replaces: KV pool 526,617 tokens at 1.10x concurrency, identical; zero restarts; both gateway aliases serving; DFlash2 confirmed drafting at k=7 with 231 draft tokens over 33 drafts; vision working at 2048x2048. One variable was deliberately dropped rather than carried over. The previous stack hardcoded PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True, the validated container never set it, and the quant playbook records expandable_segments corrupting retained tensors in another context. The compose now defaults it empty via MOG_ALLOC_CONF. Promoting the stack as it stood would have shipped a variable the tested configuration did not have. The speculative config moves into a single MOG_SPEC_CONFIG carrying the whole JSON, because the two shapes are not interchangeable: dflash requires a model pointing at the drafter and MTP must not have one, so a method-plus-tokens template cannot express both. Also parameterised: MOG_DRAFT_MODEL, MOG_MM_PROCESSOR_KWARGS, MOG_MAX_NUM_BATCHED_TOKENS. The mm-processor image cap is now mandatory rather than incidental. The model's own preprocessor declares 4096x4096, which expands to 16384 image tokens and kills startup on builds that enforce the image-token count check. Adds the .env.example this stack never had, carrying the measured rationale for each value and the one-line rollback. |
||
|
vh
|
20ac53052b |
memory: retract the MTP-head degeneration hypothesis; n=1 was never evidence
Operator ruling: the multi-turn degeneration lives in the un-fixed vLLM, not in the weights. The hypothesis that sec's stock-graft MTP head causes it is withdrawn. Two failures produced it. First, a false dichotomy treated as a deduction: having verified gen and sec run an identical engine, I concluded config was eliminated and therefore the weights were responsible. That does not follow. An engine bug present in both seats is not exonerated by the seats being identical; it only means the engine cannot explain a difference between them. It can still explain the failure. Second, and more instructive, the difference being explained may not exist. The premise was a single operator observation made during a session with many concurrent changes. That cannot carry a causal claim, and it became the load-bearing support for a root-cause narrative it could not hold. The same caveat now attaches to the coherent-to-10k observation on the new build: same n, same uncontrolled conditions, opposite direction. The comparison is weak at both ends, so the file no longer presents either sighting as a result. What survives as measured fact is unchanged and still recorded: sec's MTP head is byte-identical to the uncensored base across all 15 tensors, gen's was abliterated in-band, and acceptance differs slightly. None of that is shown to cause degeneration. Adds the generalisable lesson: an observation made while many things are changing cannot support a causal conclusion. It is the inverse of the warning already in the gen-seat compose file, which guards against trusting a negative result from a synthetic probe; this guards against trusting a positive sighting from an uncontrolled session. |
||
|
vh
|
ab3a0ca5bc |
docs(quant-playbook): acceptance is not throughput -- always run the depth control
Measured 2026-08-22 on one target with one instrument: raising MTP num_speculative_tokens from 3 to 7 improved accepted length from 2.753 to 3.041 per forward pass while throughput fell from 114.9 to 74.0 tok/s. Reporting acceptance alone would have recommended a 36% regression. The cause is architectural rather than model-specific. A single-module MTP head has no depth of its own, so vLLM runs it autoregressively and k draft tokens cost k sequential forward passes. Past a shallow depth the drafting cost exceeds what the extra accepted tokens save. Records the comparison rule that follows: match k when comparing two speculative methods, or the measurement is of depth rather than method. A parallel-drafting drafter at k=7 against an autoregressive MTP at k=3 is not a method comparison. In the case that produced this, the depth control showed most of the apparent acceptance advantage was depth, while the throughput advantage was real and came from parallel drafting -- our MTP was better at position 0 and still lost overall. Only the measured, model-agnostic result is recorded here. The DFlash2-specific findings, the hypotheses that remain unproven, and the wrong turns taken along the way live in persistent-memory.d/2026-08-22-dflash2-spec-decode.md with explicit epistemic labels, deliberately kept out of the playbook. |
||
|
vh
|
9f87b7c4e5 |
memory: DFlash2 spec-decode measured; sec running on it (experimental, confounded)
Records the 2026-08-22 session with measured results, hypotheses, and wrong turns explicitly separated -- the operator held this back while it was in flight specifically so conjecture would not enter the record as fact. MEASURED. DFlash2 works on an abliterated + NVFP4 compressed-tensors target on Blackwell sm_120, which the model card does not claim (it tests stock BF16 on H200). gen 2.753 -> 3.254 accepted tok/forward and 114.9 -> 131.9 tok/s; sec 2.676 -> 3.252 and 110.5 -> 130.0. The drafter is model-agnostic across two different finetunes to 0.06%, but is EAGLE3-style coupled to its target's hidden states, so the weights file is shareable while the 3.85 GB of VRAM is per-seat. The k=7 MTP control is the load-bearing result: raising MTP depth improves acceptance and collapses throughput to 74.0 tok/s, because a single-module head run autoregressively costs one forward pass per draft token. Without that control the obvious recommendation would have been wrong. CONFOUNDED. sec no longer degenerates at 2k, but the engine advanced 259 commits and the drafter changed at the same time. Isolating it means running MTP k=3 on the new build. Also recorded: #51113 is present in both builds and is therefore necessary but insufficient, since sec ran it and still degenerated. HYPOTHESES, labelled as such: that sec's stock-graft MTP head causes the degeneration, and that NVFP4 explains the gap against published acceptance figures. Neither is proven. WRONG TURNS, recorded so they are not re-derived: version strings are not lineage, Docker Hub push timestamps are not source freshness, and the claim that 1M context needs YaRN absent from config is false for the sec quant. Operationally important: sec is serving from a standalone container rather than its compose stack, which is stopped but unmodified. Rollback is two commands and is written down. |
||
|
vh
|
0755ba7d00 |
fix(quant): stop baking the calibration truncation cap into the shipped tokenizer
load_calib tokenizes with tok(..., truncation=True, max_length=seqlen). For a
fast tokenizer that mutates the Rust backend's truncation state in place, and
the subsequent tok.save_pretrained() persisted it, so every mixed-NVFP4 build
shipped a tokenizer.json carrying
"truncation": {"direction": "Right", "max_length": 2048, ...}
against a source whose value is null. Every prompt was clamped at the
calibration length, permanently.
It hid because older transformers does not enforce the text-vs-ids count
check. On a newer one the seat dies at startup with a message that names
images and never mentions tokenizers:
ValueError: Mismatch in `image` token count between text and `input_ids`.
Got ids=[2047] and text=[16384].
The cap also silently limited image resolution well before it killed
anything -- at 2048 the largest servable image is about 1448x1448, since
(edge/patch)^2 / merge^2 image tokens have to fit under it.
Fix saves a pristine tokenizer re-read from the source rather than the
mutated calibration object, and then asserts truncation is null so the
defect fails the build instead of shipping again.
Playbook gains section 3.14 with the symptom, the cause, the audit one-liner
and a table of which builds were affected, plus a fourth mandatory post-step.
The transferable lesson is called out: this is the third case of an artifact
carrying config authored against an older transformers that a newer one
begins enforcing, so an image bump is a config-compatibility event rather
than just a version change.
|
||
|
vh
|
ad21302474 |
memory: ESH internal IPv6 live on two LANs; Cityside v4 static proven unprovisioned
Operator-directed IPv6 enablement on ESH-UDMPM: esh-userland (VLAN 10, SSID PVC) and esh-server flipped from ipv6_interface_type=none to pd against the delegated 2607:73c0:402:1d00::/56. Verified esh-docker-vm egresses over v6 as its own address with no NAT, against v4 which still egresses as the shared CGNAT pool. No disruption through either write; originals backed up. NH3 stays v6-off deliberately -- its single /64 is reserved for network meshing, so nh3-dev having no v6 egress is correct rather than a fault. The v4 static is NOT provisioned, and this is now proven rather than inferred. A full gateway reboot -- verified by observed down-transition and an uptime reset from 140,846s to 183s -- forced a fresh DHCP DISCOVER and Cityside returned the identical address. Recorded alongside it: a DHCP renew could never have surfaced a new address in the first place, since renewal preserves the lease by design. Next step is a carrier ticket, not more testing. The v6 firewall posture was audited and is correct -- default-deny inbound for both IP versions, only four hand-written policies, none WAN-facing. My earlier warning that v6 removes CGNAT's accidental shielding was overstated and is retracted in the record. The audit's limitation is stated: it read rules, it never probed from outside, because no v6 vantage exists. Flat-zone lateral-movement finding parked as id 44 rather than actioned -- operator's call, moot until the mesh and segmentation design settle. |
||
|
vh
|
c7e21879ae |
memory: speaches ASR live on irv-ml1 — and no_speech_prob is a weak gate
Records the deployment plus the finding that outlives it: no_speech_prob alone does not carry a hallucination threshold on this stack. Silence and room tone both hallucinated 'Thank you.' at no_speech_prob under 0.11, where a conventional >0.6 gate passes them through; avg_logprob separates ~6x better. Any future consumer asking for a Whisper hallucination gate should be pointed at the composite, not the single field. Also banks the digest-pin rationale (the VAD flag is an upstream-declared unstable variable name, so a floating tag can move gate semantics silently), the two deployment gotchas, the docker-vs-native GPU index inversion on this host, and Eyra's future diarization VRAM claim on the same A6000. Adds speaches to the irv-ml1 stack table alongside parakeet, with the reason both exist. |
||
|
vh
|
aa5863c9a3 |
feat(speaches): OpenAI-compatible faster-whisper ASR seat on irv-ml1 A6000
Deployed for Eyra (meeting recorder) per the eyra-dev request. Serves
large-v3 (batch tier) + distil-large-v3 (low-latency tier) on :8204,
fp16, both resident, ~5.9 GB VRAM against 20 GB still free.
Sits alongside the existing parakeet stack (:8765) deliberately: parakeet
is a TDT/transducer returning bare {"text": ...} and has no no_speech_prob
concept, so it structurally cannot serve this consumer.
The load-bearing requirement -- segments[].no_speech_prob surviving
response_format=verbose_json -- is VERIFIED on both tiers.
Measured finding worth more than the deployment: no_speech_prob alone is a
WEAK hallucination gate on this stack. Pure silence and pink room tone both
produced the classic Whisper 'Thank you.' hallucination while no_speech_prob
stayed under 0.11 -- a conventional >0.6 threshold passes both through.
avg_logprob separates the same cases ~6x more decisively (-0.11 speech vs
-0.65/-0.72 non-speech) and compression_ratio splits 1.141 vs 0.556.
Consumers should gate on a composite, not no_speech_prob alone. Table in
the README.
VAD pinned OFF at the consumer's request (they VAD-gate upstream on the
capture edge). Consequence stated plainly in the README: with VAD off this
service will transcribe silence into text and is not defending itself.
Image pinned BY DIGEST rather than :latest-cuda, because the VAD-off
setting rides on _UNSTABLE_VAD_FILTER -- a variable upstream explicitly
marks unstable. A floating tag could rename it on any bump, silently
restoring VAD and moving no_speech_prob semantics under a calibrated gate
with no error and no log line.
Two deployment gotchas recorded: PRELOAD_MODELS only loads models already
cached (it does not download -- use POST /v1/models/{id}), and the bind-
mounted cache needs a hub/ subdir or every /v1/models call 500s with
CacheNotFound while /health still returns 200.
|
||
|
vh
|
ff5ce212da |
memory: OWUI credential state — password reset, admin-scoped API key vaulted (operator-ruled)
Two OWUI credential facts worth surviving a context reset:
- The reported lockout was NOT a broken account. The vaulted password returned
200 from POST /api/v1/auths/signin immediately before the reset, so the cause
was client-side. Test the vaulted credential against signin before concluding
an account is broken -- this is the second lockout here traced to an assumed
rather than verified credential.
- The operator-minted API key is ADMIN-scoped, inherited from the owning user,
and that is the INTENDED shape per operator ruling: infra-ops manages the
instance, so the key needs the rights the management work requires. A
least-privilege dedicated-user split was offered and declined. Do not
re-propose it.
Both credentials vaulted at esh-docker-vm/open-webui-{admin,api-key}; key verified
against /api/v1/auths/ (admin identity) and /api/models (33 models), with an
unauthenticated 401 control. Plaintext copies shredded.
Also folds in an unadjudicated drift found in passing: the running image is the
floating ghcr.io/open-webui/open-webui:main, not the v0.11.0 the stack notes
claim. Replaces the now-resolved 'operator's OWUI password change' follow-up.
|
||
|
vh
|
b8e5022a1a | memory: snapshot — three AI seats settled (orcarouter gen / MeroMero dual-mode RP / sec pen-test), Open WebUI deployed | ||
|
vh
|
5e47a59b32 |
feat(meromero): MeroMero-v2 dual-mode (prose + streaming CoT) live on one seat — no re-quant
The multi-turn Gemma-4 CoT problem is solved. One MeroMero-v2 seat, one weight set,
two aliases: char-rp (prose) + char-rp-reasoning (streaming chain-of-thought).
The winning stack, traced from vLLM source by the four-arm brokkr/dwarf panel:
- vllm/vllm-openai:v0.26.0 — ships transformers 5.14.1 natively, below the
head_dim guard, so Gemma-4-31B loads with no pin and no custom image. It also
carries the #48217 streaming pre-arm fix.
- A patched chat template whose enable_thinking:true branch force-opens a BARE
<|channel> (not <|channel>thought\n -- full-open defeats _preprocess_feed's
injection). --chat-template override, no re-quant.
- Two served-names char-rp / char-rp-thinking; --reasoning-parser gemma4;
default enable_thinking:false. LiteLLM char-rp -> prose, char-rp-reasoning ->
the thinking served-name with enable_thinking:true.
Verified: streaming CoT split 6/6 direct on :8016 and 3/3 through the gateway;
char-rp prose clean on both transports with no trailing-token leak.
Two hard-won facts recorded in persistent-memory:
- STREAMING ONLY. Non-streaming can't split -- extract_reasoning never receives
prompt_token_ids so the pre-arm can't fire (a vLLM one-shot bug unchanged
across v0.24-0.27). Fine here: Lobe/OWUI stream. Upstream PR #49797 fixes
non-streaming too, landing ~v0.28.0 -- then it's a clean image bump.
- KEY-NAME TRAP: vLLM streams reasoning in delta.reasoning; LiteLLM normalizes
to delta.reasoning_content. I lost two false-negative test rounds to this.
Canonical: stacks/meromero-charrp/ (compose + patched_chat_template.jinja) and
stacks/litellm/conf/config.yaml. Rollback is the .env image line + dropping
--chat-template.
|
||
|
vh
|
76834777a4 |
feat(open-webui): deploy env-declarative chat bake-off on esh-docker-vm:3211
Stand up Open WebUI v0.11.0 parallel to lobe-chat (:3210) as an operator-approved candidate replacement. Env-declarative config (ENABLE_PERSISTENT_CONFIG=False = the deploy is the config source of truth), model picker auto-tracks the LiteLLM gateway with no pins, background task model pinned to summarizer, TTS routed direct at the dots gateway (:8198). Gates verified on the box: G1 (declarative config, both directions), G2 (picker == live gateway roster, no hand-listing), G3 (models/sync genuinely reconciles create+delete), G5 (task model pinned). G4 (TTS) handed to tts-dev. Credential posture (G6): fresh capped LiteLLM key open-webui-esh (all-proxy-models, $50/1mo budget) rather than inheriting the uncapped lobe-chat-esh key; signup locked off after admin creation. Secrets vaulted under esh-docker-vm/open-webui-*. Note: the API-key toggle env var is ENABLE_API_KEYS (plural); a var only reaches the container if compose names it in environment:. lobe-chat is untouched. |
||
|
vh
|
f01ee28cea |
memory: gemma4 CoT test on v0.27.1 blocked by config incompatibility (reverted)
Tried serving the MeroMero NVFP4A16 quant on vllm/vllm-openai:v0.27.1 to test the
per-request enable_thinking hypothesis. Couldn't even load it:
- v0.27.1's stricter transformers raised AmbiguousGlobalPerLayerAttributeError
on the Gemma-4 config's head_dim (now a per-layer attribute).
- Setting allow_global_per_layer_attribute_access on text_config downgraded that
to a warning, but then gemma4.py load_weights asserted:
"Attempted to load weight (512) into parameter (256)". Gemma-4-31B is
genuinely heterogeneous -- some layers have head_dim 512, not a uniform 256 --
so forcing the global value built wrong-shaped parameters. The guard was right.
So the MeroMero quant's config was authored for v0.24.0's Gemma4 loader and cannot
load on v0.27.x without a config migration or a re-quant against newer transformers.
The per-request-kwargs hypothesis was never reachable -- the model wouldn't load.
Consequence worth carrying: the eventual gen-seat move to v0.27.2 stable must
re-verify config-compat for any Gemma-4 seat of this vintage.
Fully reverted: config.json restored (flags removed), image back to latest
(v0.24.0), gateway char-rp-reasoning removed, char-rp prose verified. char-rp stays
on v0.24.0; MeroMero CoT remains undelivered. For RP-with-CoT use gen-reasoning, or
re-quant MeroMero against v0.27.x (real work, unproven payoff).
|
||
|
vh
|
7ebbcec5bb |
memory: vLLM release status for #51113 — no stable yet; gemma4 CoT is decoupled
Checked upstream. Latest stable is v0.27.1 (Aug 11) and it does NOT contain #51113 -- the v0.27.0..v0.27.1 compare is only "DSpark Markov heads" plus three CI commits. The #51113 cherry-pick (khluu, Aug 9, "v0.27.0 cherry picks" milestone) is staged on the release-0.27 branch but no v0.27.2 stable has been cut; only v0.27.2rc1 / the pinned nightly carries the fix. So the standing follow-up (move gen off the nightly) still waits on a v0.27.2 stable cut. Key decoupling: #51113 fixes the Qwen3.8 MTP + prefix-caching accuracy drop (#43559). It is irrelevant to Gemma-4 seats, which have no MTP head. So the meromero/gemma4 CoT test does NOT need the nightly and does NOT need #51113 -- it can run on the latest stable v0.27.1, which is newer than the seat's current v0.24.0 and where per-request chat_template_kwargs is expected to work. |
||
|
vh
|
b84ad888d6 |
memory: CORRECT the MeroMero-CoT finding — not a hard wall, not MeroMero-specific
My prior entry claimed the gemma4 reasoning parser is process-wide and the CoT
was architecturally blocked. Reading the actual code proves that wrong:
- Template (chat_template.jinja:347-352): thinking is a PER-REQUEST toggle.
enable_thinking:false prefills an empty <|channel>thought<channel|> to
suppress; true omits the prefill so the model can emit a real thought channel.
- Parser (vllm/reasoning/gemma4_utils.py): splits on <|channel>/<channel|> tag
presence, "works with or without enable_thinking" -- NOT a process-wide flag.
The stale compose comment I trusted cited an old parser API (vllm/parser/
gemma4.py:439) this container doesn't run.
So the mechanism is gemma4-GENERAL (any gemma4 finetune on this template family),
and the two-served-name gen pattern should work. What actually failed the test was
that meromero runs vllm/vllm-openai:latest (v0.24.0), where per-request
chat_template_kwargs.enable_thinking didn't take effect -- whereas the gen seat's
pinned nightly demonstrably applies it. That's a version/plumbing issue, not the
model and not the architecture, and it would hit any gemma4 finetune on that image.
Unverified fix (needs a GPU window): re-serve meromero on the nightly image with no
process default and per-request enable_thinking. Currently reverted to known-good.
|
||
|
vh
|
a260b57974 |
memory: MeroMero-v2 CoT via vLLM gemma4 parser is not achievable (tried + reverted)
Operator asked to serve MeroMero (char-rp) with reasoning as char-rp-reasoning.
The model genuinely reasons (GRPO-trained with thinking; ships Think/NoThink
SillyTavern presets), but two facts kill the vLLM path:
- it's byte-identical to the weights we already serve (same zerofata repo,
chat_template sha 94899c0f matches our on-disk quant), so re-quanting adds
nothing; and
- the gemma4 reasoning parser's enable_thinking is PROCESS-WIDE, not per-request.
The seat's --default-chat-template-kwargs sets the parser state machine; a
per-request chat_template_kwargs.enable_thinking reaches the template but not
the parser (unlike the qwen3 parser the gen seat uses). So the two-served-name
gen/gen-reasoning trick can't work.
Verified empirically: added a char-rp-thinking served-name and removed the process
default; enable_thinking:true per request still produced pure prose, 0
reasoning_content. Per the seat's own comment, a dedicated thinking-on process
dumps all prose into reasoning_content with null content -- no clean split.
MeroMero reasons only client-side in SillyTavern, not through vLLM.
Fully reverted to known-good: single served-name, process default restored,
char-rp prose verified end-to-end. GPU0 both seats healthy, gen untouched.
Kept one change: MEROMERO_GPU_MEM_UTIL 0.52 -> 0.51. 0.52 no longer boots because
orcarouter gen (the GPU0 neighbor) is marginally bigger than the old heresy seat
(free 49.02 < needed 49.38 GiB); 0.51 fits at KV 2.00x @ 262K.
For real RP-with-CoT: gen-reasoning (orcarouter, uncensored, thinks) or a dedicated
Qwen-based RP-thinking seat, which needs a GPU slot.
|
||
|
vh
|
3d30a6530b |
feat(lobe-chat): pass every chat-capable model through the picker
Operator: "pass everything through, lobe is a test surface for me." The picker goes from 11 curated seats to all 25 chat-capable models the gateway serves, paid passthroughs included. Membership is derived from LiteLLM's declared `mode` rather than by taste: chat (15) and completion (1) are in, and the nine GLM/frontier entries whose mode is unset are chat models in practice. Out: audio_speech (ext-tts, tts-1, tts-1-hd, gpt-4o-mini-tts), embedding (qwen3-embedding) and rerank (reranker, reranker-a3-bge-v2-m3) — seven models that cannot answer a chat request at all, so listing them would recreate the visible-but-dead entry this list just got fixed for. Every candidate was probed live from inside the container before being pinned, which corrected an earlier claim in this file. char-rp and char-rp-reasoning are NOT retired: they are configured and their upstream seat (ana-ml2:8016) is refusing connections while under maintenance, which is a 500, not a 400. Both are retained deliberately — dropping a name because its seat is bouncing makes the list rot in the other direction. Only char-rp-fable is genuinely gone (400, absent from model_info). The comment now spells out the 400-vs-500 distinction so the next editor does not repeat the mistake. Also corrects the credential-posture header, which still described the key as scoped to free local models and cited the glm/kimi rejection as current verification. The key now carries the all-proxy-models access group with no budget ceiling, so that block had become a false security claim in the most load-bearing comment in the file. |
||
|
vh
|
303fb7a5aa |
feat(lobe-chat): add the sec seats to the picker, drop two retired ones
Two independent gates kept the new `sec` family out of Lobe, and only one of
them was visible from the symptom.
The picker never auto-discovers. `OPENAI_MODEL_LIST=-all,+<names>` clears
Lobe's built-in OpenAI catalogue and re-adds one model per `+name`, so anything
added to LiteLLM stays invisible until this list is edited and the container
bounced. That pin is deliberate — an unpinned picker offers models that fail on
click — but it means the list rots in both directions, and it had:
- `sec` / `sec-reasoning` missing (hosted_vllm/mog-sec-27b{,-thinking} on
ana-ml2:8019, added to config.yaml earlier today), and
- `char-rp-reasoning` / `char-rp-fable` still listed after being retired
upstream, i.e. two picker entries that 400 on click. Verified: a call to
char-rp-fable now returns 400 Bad Request.
The list is now curated to live, chat-capable, free-local seats — eleven, each
round-tripped through the container after the bounce. The paid family stays out
deliberately; that is now a picker decision rather than a key one.
Which is the other half of this commit: the `lobe-chat-esh` key is no longer
scoped to free local models. On the operator's instruction infra-ops swapped its
explicit array for the `all-proxy-models` access group, so it now reaches the
paid passthroughs with `max_budget: None`. The README documented the old posture
as current, which made it a security claim that was no longer true; it now
carries the change, what it costs, and the fact that the picker is the only
remaining gate.
|
||
|
vh
|
564f5ae4f6 |
chore(litellm): rename mog-sec aliases to sec / sec-reasoning
Operator's call: the pen-test seat is reached as `sec` (non-thinking) and `sec-reasoning` (thinking). Backend and served-model-names (mog-sec-27b[-thinking] on :8019) are unchanged; only the gateway alias name changes. Old mog-sec / mog-sec-reasoning now 404. |
||
|
vh
|
36c173c6a1 |
feat(mog-sec): quant + serve M.O.G.-SEC pen-test seat; PPL on gen; retire fable
Autonomous overnight run under the operator's full-autonomy grant. End state:
fleet up, gen seat untouched, a new verified pen-test seat serving where fable was.
PPL on the orcarouter gen seat (fable downed to free GPU1 for a nospec probe,
probe torn down after): mean 7.07 / median 5.76, within noise of heresy 6.910 /
5.625 and identical to our recipe's usual 7.059. The gen-seat search is settled.
M.O.G.-SEC: chose Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-BF16 (rev deede677)
over the pre-made ModelOpt NVFP4, which was disqualified on W4A4 4-bit activations
(the AEON degradation mode, catastrophic on a 1M-context model), zero MTP tensors,
and ModelOpt format. Pulled, format-screened (P(<think>) 1.11e-05, clean), quanted
in-house to mixed NVFP4+FP8 (23.4 GB, MTP + vision preserved), and served in the
retired fable slot.
stacks/mog-sec ana-ml2 GPU1 :8019, KV 418,218 tok / 1.60x @ 262K
aliases mog-sec (non-thinking), mog-sec-reasoning (thinking)
gates surface 6/6, MTP 55.3%, format 0/15 leak, vision 7/3/1,
capability 4/4 (delivers offensive-security content)
Served at native 262K, NOT the card's 1M -- the 1M needs YaRN (absent from the
weights' config) plus the SGLang/DFlash2 path the repo ships a deployment kit for,
neither of which is our vLLM surface. A real 1M seat is a separate SGLang project.
Retired char-rp-reasoning + char-rp-fable (zero traffic, pointed at the downed
fable :8019; now 404 cleanly, not repointed -- a security model is not an RP model).
char-rp (meromero) untouched. Vision preprocessor built from the model's own
image_processor block, same trick as the MeroMero seat.
GPU0 seats (gen, meromero) were untouched and healthy throughout. The quant ran in
GPU1 free space with no production seat stopped except fable, which was replaced.
|
||
|
vh
|
e4576f0989 |
test(gen-seat): PPL on orcarouter — mean 7.07 / median 5.76, within noise of heresy
Measured against a spec-decode-free probe on GPU1 (fable downed to free the VRAM, probe torn down after). eval_quality.py aborts PPL under --speculative-config, so a nospec probe is the only way to read it. orcarouter mean 7.0655 median 5.758 heresy mean 6.910 median 5.625 (+2.2% mean) our recipe's usual mixed-quant PPL: 7.059 -- orcarouter is identical to it So orcarouter matches heresy on fidelity and wins on every other axis: MTP acceptance 58.4% vs 47.2%, zero think-leak, vision 7/8. The gen-seat search that ran through Cold-Fusion, heresy, and preetpatel is settled on orcarouter. |
||
|
vh
|
ce09ac4fa6 |
test(gen-seat): add a real vision battery — orcarouter scores 7/8
surface_test.py's vision check is one image and one word. It proves the tower loads; it does not prove the tower works. This battery uses generated images with known ground truth so every answer is objectively gradeable. Against orcarouter NVFP4-mixed on the `gen` alias: T1 OCR, 5 lines incl. one at 18px PASS all 5 exact T2 counting + attribute binding PASS 7 circles / 3 triangles / 1 square T3 bar chart, 6 values + max/min PASS 6/6 exact T4b occlusion, star behind rectangle PASS T4c aspect ratio of a 160x140 rectangle FAIL called it taller than wide T5 two images, which has text PASS T6 four images, the seat's cap PASS all four named T7 five images, one over the cap PASS rejected with HTTP 400 No <think> leak on any vision call. The single miss is fine-grained relative-dimension estimation on a near-square shape, and it reproduced across two runs (the longer T4 called the same rectangle "equal width and height"). Counting, OCR, chart values and occlusion ordering are all solid, so this is a precise-geometry weakness, not a broken tower. Recorded so nobody builds a feature on this model judging relative sizes. T7 earns its place separately: it confirms the per-prompt image cap fails loudly with a 400 rather than silently dropping the extra image. |
||
|
vh
|
f85d102813 |
test(gen-seat): orcarouter passes every gate — in-band MTP head delivers +11 points
Gates run against the live seat while the operator tested in parallel. <think> leak (n=30, 4 prompt types + multi-turn) 0/30, 0 empty MTP acceptance 58.4% @ 117.11 tok/s median surface 6/6 abliteration survival 4/4 compliance deterministic quality gens coherent and correct PPL still blocked For scale on the leak gate, the abandoned h300 build scored 8/30 on this exact instrument, and its abliteration-survival samples had 2 of 4 open with "<think>Ok, let's figure this out:". Orcarouter has none. The headline is MTP acceptance. 58.4% against heresy's byte-identical base head at 47.2% is +11 points, and it sits level with our own in-band L35 at 59.1%. That is the additive in-band-vs-graft delta the entire Cold-Fusion experiment was built to measure and never cleanly delivered -- orcarouter handed it over for free because the author had already done the Robinson edit on the head. Surface 6/6 covers plain chat, vision, tool calling, the thinking split, a 36,042-token long-context retrieval, and streaming. PPL remains blocked on a spec-decode-free probe seat: it needs ~22 GB and GPU1 has ~16 GB free. Comparison target is heresy at 6.910. |
||
|
vh
|
ba53c30192 |
feat(gen-seat): cut over to orcarouter — live, 7/7 aliases, vision intact, no think-leak
Operator directive was seat-first so he can test while the gates run. GEN_MODEL -> /tank/aimodels/qwen38-27b-orcarouter-nvfp4-mixed. Healthy in ~4 min. KV pool 401,550 tok / 1.53x. MTP drafter detected and wired, sharing embedding and lm_head with the target. 7/7 gateway aliases 200. Vision correct on the shape probe. Live decode observed at 102-133 tok/s under load. Critically, <think> does not appear in the top-20 first tokens on the live seat. That is the Cold-Fusion failure mode measured absent in production, matching the pre-quant screen on the bf16 (1.23e-06, rank 52). Rollback is one line to .env.bak-heresy-restored-20260821. Full gates were still running when this landed; PPL stays blocked on a spec-decode-free probe seat, which needs ~22 GB against GPU1's ~16 GB free. |
||
|
vh
|
c8f128bdff |
feat(gen-seat): quant orcarouter — its MTP head is already Robinson-abliterated in-band
Pulled orcarouter/Qwen3.8-27B-Uncensored at rev 9878936b (55.5 GB, gated, our token has access) and built /tank/aimodels/qwen38-27b-orcarouter-nvfp4-mixed (23.4 GB, mixed NVFP4+FP8). Verified, not yet cut over. The operator asked whether we could apply the Robinson path to the MTP head. We cannot, because the author already did. compare_mtp_head.py against the verbatim base graft: 13 of 15 tensors byte-identical, exactly 2 differ -- mtp.layers.0.self_attn.o_proj.weight and mtp.layers.0.mlp.down_proj.weight, which are precisely the two residual writers our own abliterate.py targets (EXPECT_MTP_WRITERS = 2). Reverse-engineered the edit from the weights alone (mtp_delta.py, added here): sigma2/sigma1 = 0.0164 on BOTH tensors rank-1, a single-direction projection |cos| between the two recovered dirs = 1.0000 ONE shared direction ||delta||/||W|| = 1.42% and 1.41% a gentle, consistent projection sink energy dim 3994 = 0.0000% sink-clean; Heretic's was 6.18% That is the Robinson in-band MTP abliteration, already applied, with a direction that passes our sink screen outright. Nothing to do but preserve it, and the quant carries it byte-identically. This is the configuration the entire Cold-Fusion experiment was designed to test and never cleanly delivered. The new format screen paid for itself on its first real use: think_prior.py on the bf16 BEFORE any GPU time gave P(<think>) = 1.23e-06 at rank 52, against Cold-Fusion stock 0.1850 and h300 0.2216. Roughly 150,000x cleaner. Two durable findings about the pipeline itself: The quant needs ~17 GB, not a whole card. It ran entirely in GPU1's spare 16 GB with ZERO production seats stopped -- the h300 run's "stop BOTH GPU0 seats" was never necessary, it simply had a free card by coincidence. The first attempt OOM'd by 2.37 GiB at layer 64 of 65 with 3.57 GiB reserved-but-unallocated, which is fragmentation, and PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True closed it. post_quant.py now builds a missing output index from the safetensors headers. A sub-23 GB quant saves one bare shard with no index, and post_quant needs one; this has broken three separate rounds and been hand-fixed every time. The header is read by struct-unpacking the u64 length and parsing the JSON -- never safe_open, which mmaps the whole 22 GB shard and ENOMEMs on ZFS. Artifact verified: mixed-precision, 1968 tensors, 15 mtp, 333 visual, re:^mtp.* present in the ignore list (llm-compressor pruned it as always), preproc restored. Imatrix deferred per operator; the log confirms the usual uniform-MSE fallback, so this build stays apples-to-apples with heresy's PPL 6.910. |
||
|
vh
|
bf65d0254d |
docs(pfi): evaluate the two gen-seat replacement candidates
preetpatel/Qwen3.8-27B-Uncensored-NVFP4 is disqualified on two independent hard
failures, both read directly off the artifacts via HTTP Range requests against the
safetensors header (about a megabyte, not a 20 GB download):
- ZERO mtp tensors. The author's recipe.yaml asks to ignore re:.*mtp.*, but the
written config.json has no mtp ignore entry while re:.*visual.* expanded to 110
explicit ones. That asymmetry is llm-compressor pruning a pattern that matched
nothing, i.e. the MTP head was never loaded. Costs roughly half our decode.
- NVFP4 W4A4, 4-bit activations. Precisely the AEON failure mode: the fidelity
gradient is W4A4 < W4+FP8 < W4+bf16, W4A4 drove ~15-20% stochastic degeneration,
and it collapses past ~30k context. The gen seat serves 262K.
orcarouter/Qwen3.8-27B-Uncensored checks out as a quant source: stock-Qwen base
rather than a reasoning-compression finetune, Arditi-style single-direction
abliteration, 15 mtp and 333 visual tensors verified present, chat template
byte-identical to the heresy build we are serving, and the gate is already accepted
on our token.
Also records the author's FP8 release as a noted-but-not-recommended third option:
far more traction, but 30.9 GB against NVFP4's 22 GB, and on a zero-sum GPU0 that
+9 GB comes out of the KV pool and breaks 262K context.
And states the imatrix constraint plainly. Our recipe has always requested
imatrix_mse and always silently fallen back to uniform MSE; playbook 3.13 warns
against assuming an imatrix would help before verifying llm-compressor can consume
external importance data at all. The W4A16 portions are data-free by construction
and cannot use it regardless.
|
||
|
vh
|
48410a6a90 |
chore(coldfusion-abliteration): delete the Cold-Fusion bf16 weights — ~154 GB reclaimed
Operator directive following the decision to abandon the Cold-Fusion base.
Removed with explicit literal paths, one at a time:
qwen38-27b-coldfusion-bf16 stock DavidAU base
qwen38-27b-coldfusion-abliterated-L35-bf16 Robinson L35
qwen38-27b-coldfusion-h300-mtp-bf16 Heretic-300 + MTP graft
qwen38-27b-coldfusion-heretic300-bf16 raw Heretic export
Verified against ZFS used, not df: 4.48T -> 4.33T, ~154 GB. No snapshots were
holding the blocks, all four paths confirmed gone, gen seat unaffected.
The last two were hardlink twins -- same inode, links=2, because the MTP graft
hardlinked every unchanged shard -- so deleting only one would have freed
nothing. `du` across several paths in a single invocation dedupes hardlinks and
reported heretic300-bf16 as 2.5K, which would have made a size estimate wrong in
both directions. Check `stat -c %h` before sizing a delete.
Kept deliberately, so the research record outlives the weights:
qwen38-27b-coldfusion-bf16.PROVENANCE.txt pinned HF revision 9c44193f
coldfusion-abliteration/ harness, 300-trial Optuna
journal, catatonia-T260.json
With those two, every deleted build is reproducible: re-pull stock at the pin and
replay the winning config.
Held back pending an explicit call: the two NVFP4 quants, h300-nvfp4-mixed (the
only remaining servable copy of the Heretic-300 result) and L35-nvfp4-mixed. The
directive named bf16 weights; these are quants, and there is no storage pressure
arguing for haste at 4.26T free.
|
||
|
vh
|
37e9e1ca7f |
revert(gen-seat): abandon Cold-Fusion, roll back to heresy — the leak is in the base
Operator directive, given before the result was in: if it's the base, abandon h300 and the base too. The dose-response said base (18.5% of 22.2%), so it fired. Live gen seat is /tank/aimodels/qwen38-27b-heresy-nvfp4-mixed again, restored from .env.bak-coldfusion-L35-20260820. The h300 env is preserved at .env.bak-h300-abandoned-20260821. The clincher, same probe pointed at heresy: Cold-Fusion stock P(<think>) 0.1850 Cold-Fusion L35 0.2048 Cold-Fusion h300 0.2216 heresy (restored) not in the top 20, <0.002 A >100x gap between the families, which is why no rollback inside Cold-Fusion would have helped -- stock and L35 leak at nearly the h300 rate. Verified after rollback: 0/30 leaks and 0 empty on the same instrument that scored h300 at 8/30, with the EXISTING enable_thinking:false config; KV pool 403,065 tok / 1.54x, heresy's exact documented baseline; 7/7 aliases; vision intact. No LiteLLM change was needed, so the chat_template_kwargs fix is left unapplied -- it worked, but it was a workaround for a base we no longer serve. Cost, stated plainly: 8/100 refusals becomes 29/100, a 3.6x regression on the axis the whole Heretic-300 run existed to move. Accepted deliberately. What carries forward is the methodology, none of which lived in the Cold-Fusion weights: direction_scope=0 beating per-layer on a merged base, aggression not being the lever, PR #317 silently dropping the MTP head on save, the MPOA and sink-screen reasoning, the graft/KL/catatonia/export harnesses, and the finding that a pristine MTP graft accepts as well as an in-band edit. New acceptance gate earned here: run think_prior.py on a candidate's STOCK weights before committing GPU time. It is a ~10s CPU measurement and it would have disqualified Cold-Fusion before the 300-trial study ever started. Heretic's objective has no format-compliance term at all -- the same blindness that removed the self-harm guardrail. Nothing deleted. Every Cold-Fusion artifact, the 300-trial Optuna journal and catatonia-T260.json remain on disk. Abandon means stop serving, not rm. |
||
|
vh
|
5ee2325820 |
feat(coldfusion-abliteration): dose-response settles the <think> leak — base 83%, our abliteration 17%
Answers "how likely is it that our abliteration caused this?" with a measurement instead of a prior. P(<think>) at the first generated token, template rendered enable_thinking=false so the prompt already carries a CLOSED think pair -- the exact event behind the leak. Raw softmax, bf16, CPU-only, one process per model. Deterministic: stock reproduced to 17 significant figures across two runs. coldfusion-bf16 none (stock) 0.1850 rank 3 coldfusion-abliterated-L35-bf16 Robinson L35, mild 0.2048 rank 2 coldfusion-h300-mtp-bf16 Heretic-300, heavy 0.2216 rank 2 The stock, untouched base already puts 18.5% of first-token mass on opening a think block the template had closed. Abliteration adds a real, monotonic, dose-dependent +3.7 points -- a nudge on a pre-existing base, not the cause. Cold-Fusion is a reasoning-token-compression finetune, i.e. a model trained to think briefly, and the leak's text shape agrees: a compact correct trace with a trained transition marker, which is trained behavior rather than damage. This changes the options. Rolling back to L35 or stock does NOT fix the leak -- at 18.5% under temp 0.7 / top_p 0.8 they leak at nearly the h300 rate. Only leaving the Cold-Fusion family escapes it, at the cost of the 8/100 refusal result. The chat_template_kwargs fix is the correct lever. Durable methodology point: a forward-KL budget cannot catch this. Heretic minimizes forward KL(stock||abliterated), which is near-blind to the model putting new mass on tokens stock barely used -- that is reverse KL's job, and we measured exactly that asymmetry on L35 (reverse 1.43 vs forward 0.70). h300's KL of 0.0136 is not evidence of innocence. For any "did the abliteration break behavior X" question, measure P(token) directly. Ran CPU-only deliberately: 96 EPYC cores and 265 GB of RAM make a 27B forward pass cheap, so this cost no GPU window and no seat downtime, where the obvious route was stopping both GPU0 seats. Also normalizes two more abliteration output dirs from root-owned 0600 to llmuser 0664. The unreadable-model failure surfaces as FileNotFoundError rather than a permission error, which is worth knowing before it wastes a run. |
||
|
vh
|
91f4cf22e1 |
fix(gen-seat): diagnose the unterminated-<think> leak — model defect, temp-triggered
Operator reported the new Heretic-300 gen seat "sends CoT but never completes
the turn" through Lobe. Diagnosed; not yet fixed (the fix changes gen's
semantics, so it is the operator's call).
The Qwen3.8 chat template appends a pre-closed <think>\n\n</think>\n\n when
enable_thinking is false. The h300 model opens a fresh <think> anyway and never
closes it. Because the prompt already closed the block, vLLM's qwen3 reasoning
parser is not in reasoning state, so the tag passes through as ordinary text --
reasoning_content empty, reasoning_tokens 0, and the whole reasoning-plus-answer
blob lands in content. Lobe then correctly treats the unterminated tag as
still-thinking and renders no answer. The client and the serving stack are both
behaving correctly; the model is not.
The trigger is TEMPERATURE, not presence_penalty (n=12 per arm):
temp 0.7, pp 1.5 (current gen) 4/12
temp 0.7, pp 0.0 4/12
temp 0.7, pp 0.5 3/12
temp 0, pp 1.5 0/12
That falsifies the standing hypothesis, recorded in the litellm config comment
and in the operator's own 2026-08-16 note, that presence_penalty 1.5 is the
first dial to move. It is not this bug's cause.
It also explains the blast radius: only the two temp-0.7 aliases leak, `gen`
and `summarizer-large`. summarizer, classifier, image-judge and qwen-image-bench
all run at temp 0 and are clean, so nevermore's summarizer path is unaffected.
Candidate fix, validated n=30 over 4 prompt types plus a 3-turn conversation:
chat_template_kwargs {enable_thinking: true, reasoning_effort: low} takes 8/30
leaks to 0/30, at ~+27% completion tokens and a ~3% empty-content residual.
The tell appears in eval_coldfusion_h300.json and in none of the aeon, heresy,
mixed or w4a16 evals, so it is new with this build -- but L35 was never evaled,
so this does not separate a Cold-Fusion base trait from a Heretic-300
abliteration artifact.
Reproducers and the full method land in bench/think-leak/. Note in particular
that the 7/7 alias smoke test run at cutover structurally could not catch this:
trivial prompts never invite reasoning, so they never sample the leaking token.
|
||
|
vh
|
1d3b80169a |
fix(nevermore): repoint onto live aliases — its LLM pass had been dead 8 days
nevermore pinned LLAMA_SWAP_MODEL=granite-4.1-8b, an alias retired with the
granite seat on 2026-08-12. Every summarization call since then failed: 67
consecutive status=failure rows, 0 tokens, twice daily, entirely silently. The
briefing had been rendering with no LLM pass at all. Nothing alerts on
status=failure in the spend logs, so it took an unrelated question about
reranker VRAM to surface it.
It was also pinned to NEVERMORE_RERANK_MODEL=qwen3-reranker -- the incumbent
Brokkr R43 measured harming 80/90 fleet queries -- and was its ONLY caller,
while the production `reranker` alias sat at 0 calls for 4 days. The R43
cutover repointed the alias but never moved the consumer.
nevermore/.env LLAMA_SWAP_MODEL granite-4.1-8b -> summarizer
NEVERMORE_RERANK_MODEL qwen3-reranker -> reranker
(server-only; .env is excluded from the mirror both ways)
Verified against nevermore's exact call shape: summarizer returns clean content
with 0 reasoning chars at temperature 0.2 / max_tokens 4000; reranker scores
0.95 on-topic vs ~1e-5 off-topic; embedding returns dim-1024.
Retired alongside it:
vllm-rerank :8002 Qwen3-Reranker-0.6B + the qwen3-reranker alias
vllm-rerank-a4 :8014 gte-reranker-modernbert + its alias
vllm-granite :8004 Exited 8 days, dead service block
and vllm-rerank-a3 was promoted from a throwaway `docker run` into this stack
(the selection ledger's own open follow-up). Healthy in 55s. It keeps the
bake-off arm name so the ledger, memory and R43 record stay valid.
VLLM_VERSION is pinned latest -> v0.24.0. Every service in the stack shares that
one variable, so a bare `compose up -d` could have silently upgraded all of
them at once; both tags resolved to the same local image (4091d5593f77), so the
pin changed nothing at runtime.
GPU1 is down to 81,448 of 97,887 MiB -- 13.9 GB reclaimed tonight.
Correction: an earlier claim that A4 had no gateway alias was wrong. It did.
LiteLLM serves both config-defined and DB-defined models -- live showed 32
against config.yaml's 26 -- and grepping the file cannot see the difference.
/v1/models and /model/info (which flags db_model) are the ground truth. DB
models delete hot via POST /model/delete with no restart.
Left alone: reranker-a3-bge-v2-m3, a zero-call duplicate of `reranker` on the
same backend. It is Brokkr's cutover-verification handle -- redundant rather
than broken, and another agent's tooling is not mine to delete unilaterally.
|
||
|
vh
|
b990951d80 |
chore(vllm): retire LFM2.5-2.6B permanently; audit finds nevermore on the harmful reranker
Operator directive: lfm2.5-2.6b goes down permanently.
- stacks/vllm/compose.yaml vllm-lfm25 service removed (replaced by a
tombstone comment), pushed live to ana-ml2
- ana-ml2 container docker rm -f'd, 8,721 MiB freed on GPU1
(95,388 -> 86,667 of 97,887)
- litellm config lfm2.5-2.6b alias deleted, live + canonical,
28 -> 27 models
It was an EVAL-ONLY bake-off seat against granite-4.1-8b that never received
the operator ruling it was pending; the comparator was retired from the roster
on 2026-08-15; it was deliberately never wired into any default or fallback
routing chain; and spend logs show 0 calls in the 4-day window to 2026-08-21.
Weights stay in the shared HF cache -- nothing deleted from disk.
The gateway restart that makes the alias deletion take effect is HELD so it can
batch with a pending reranker change. Until then the name is still routable
in-memory and will error against a dead backend.
Auditing the three reranker seats while answering "why do we have three" turned
up a real problem. The design is one production, one rollback, one fallback --
but the traffic is backwards:
:8013 A3 bge-v2-m3 PRODUCTION, backs `reranker` 0 calls / 4 days
:8002 Qwen3-Reranker RETIRED incumbent, rollback only 7 calls, 12-hourly
:8014 A4 gte-modernbert "fallback" no alias at all
nevermore is hard-wired to the incumbent by name (NEVERMORE_RERANK_MODEL=
qwen3-reranker), so the R43 cutover never moved it -- the cutover repointed the
`reranker` alias and correctly left `qwen3-reranker` naming the Qwen model.
Brokkr R43 measured that model harming 80/90 fleet queries, so nevermore's
twice-daily rerank pass is likely degrading its own briefing.
Fix is one line in nevermore's .env plus a nevermore restart, and it must land
before :8002 is retired. Recorded in persistent-memory with the A4 alias also
noted as absent (global CLAUDE.md names reranker-a4-gte-modernbert; it does not
exist).
|
||
|
vh
|
e3ce713f7f |
feat(gen-seat): cut over to Heretic-300 — 7/7 aliases, vision intact, MTP 59.7%
Live GEN_MODEL is now qwen38-27b-coldfusion-h300-nvfp4-mixed (ana-ml2 GPU0 :8015). Served-name left unchanged so all 7 LiteLLM aliases route without a gateway edit. Verification: KV pool 401,550 tok / 1.53x (baseline 403k / 1.54x) LiteLLM aliases 7/7 green vision 3/3 shapes, colour+form+position correct MTP acceptance 59.7% median @ 118.37 tok/s quality gens 4/4 correct abliteration 4/4 compliance PPL NOT measured (see below) The roadmap predicted ~47% acceptance for a pristine MTP graft versus L35's 59.1% in-band edit. Measured 59.7% on the same harness: there is no acceptance penalty, which removes the throughput argument for reimplementing MPOA. A single long-prose generation read 47.5% off the same counters -- below the 8-run minimum of 49.0% -- and would have "confirmed" the prediction by coincidence. Acceptance must be read from quickbench.py, never one sample. PPL is blocked on VRAM, not on the model: eval_quality.py aborts with "prompt_logprobs look uniform" under --speculative-config, and the probe-seat workaround needs ~22 GB while both cards sit at ~96% committed. Also normalizes the quant dir from root:0600 to llmuser:llmuser 0664 to match every other model dir, and records that config.json sha256 is byte-identical across the h300 and L35 quants and is therefore useless for confirming which weights are mounted (mtime and a head-hash are the discriminating views). Rollback is one line to .env.bak-pre-h300-20260820. |
||
|
vh
|
407ca017ae |
memory: snapshot — Heretic-300 built, quantized and verified; gen-seat cutover is the next step
8/100 refusals at KL 0.0136, hand-verified coherent, beating the absolute-heresy bar 3.6x. NVFP4 quant complete: 21 GB, 1968 tensors, MTP head grafted back after PR #317 dropped it, and re:^mtp.* re-injected into quantization_config.ignore after llm-compressor pruned it. Self-harm guardrail is gone on this build and is the operator's own next work item; the four-dwarf panel is stood down. |
||
|
vh
|
f90a5025de |
feat(coldfusion-abliteration): Heretic-300 — 8/100 refusals at KL 0.0136, beats the heresy bar 3.6x
Ran Heretic v1.4.0's 300-trial TPE search on Cold-Fusion. Best trial scores 8/100 refusals at KL 0.0136 against a 98/100 base, versus absolute-heresy at 29/100 and our hand-tuned Robinson L35 at 72/100 / KL 0.0116 — i.e. 64 fewer refusals for the same damage. Hand-verified coherent: correct arithmetic with shown working, clean code, 66-167 word prose across nine probes. Durable findings: - direction_scope=0 (single shared direction) is decisive on this merged base: n=129, best 8/100. Per-layer directions n=131 never beat 52/100 despite a better median. Points against the multi-direction intuition for a diffuse direction (our two-template |cos| is 0.62 vs Robinson's 0.99 on stock). - Aggression is not the lever. r(KL, refusals) = -0.561 over 261 trials; the KL<0.02 band contains both the worst results (median 87/100) and the single best. A KL 0.3554 trial scored worse than one at 0.0193. - PR #317 confirmed: Heretic silently drops the MTP head on save. Source 1199 tensors -> export 1184, all 15 mtp.* gone, vision 333/333 intact, exit 0, no warning. This is also why absolute-heresy ships a byte-identical MTP head — a bug, not a design choice. Always diff tensor keys after a Heretic export. - Heretic's recovered direction carries 6.18% of its energy in sink dim 3994, versus 0.094% for our L35 and 1.97% for the L39 we rejected as brick-inducing. It survives that only because of magnitude-preserving ablation (row_normalization=FULL); our plain projection has no such protection, so the sink screen correctly refused the in-band MTP graft. Same direction, different operation. MPOA is the prerequisite for in-band MTP on a Heretic trunk. - Heretic's edit is recoverable from weights: delta is rank-1 (s2/s1 ~ 0.010), SVD gives the direction, norms give per-layer weights (1.08 -> 1.34, i.e. over-projection). Cross-layer |cos| agreement 0.9903 independently confirms the single-direction result. New tooling in services/coldfusion-abliteration/: kl_divergence.py first-token KL, class-split, zero noise floor catatonia_gate.py 12 probes x 220 tokens, prints every completion heretic_export.py PTY driver; selects by measured value, never by menu position — Heretic's resume prompt puts "delete the checkpoint and all results" one arrow-key from the target graft_mtp.py recovers the trunk direction by SVD; --pristine for the safe path when the sink screen refuses Also adds quant playbook 3.13: the NVFP4 recipe sets observer="imatrix_mse" but llm-compressor has always silently fallen back to uniform MSE for want of importance data — on this build and on the incumbent. Existing A/B comparisons stay valid since every build shares the fallback. Parked as id 42. Guardrail note: this build has lost the self-harm guardrail that the Robinson L35 build retained. Restoration is the operator's own work item. |