Commit Graph
63 Commits
Author SHA1 Message Date
Ilker ManapandClaude Opus 5.5 e8a62b23b7 Merge features-c2: the docs portal and its links in English and Turkish
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:15:25 +02:00
Ilker ManapandClaude Opus 5.5 11231d8c2b The portal in English and Turkish: a catalogue per language, a switcher at the foot of every page, landing.language, Turkish numbers and dates
Every template and handler message in internal/web goes through a JSON
catalogue under internal/web/locales/<code>/, with English as the fallback.
The language is the person's choice (a cookie set by /_lang/{code}), else
Accept-Language, else landing.language. Tests refuse a key some language
lacks, a translation with other arguments than English, and template text
left in English.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:12:53 +02:00
Ilker ManapandClaude Opus 5.5 d41104a452 Merge C21 quality suites and gating
Conflicts: docs.go (manual, OpenAPI and suites all kept), modelserve Job
(trace and eval both kept). The eval routes are added to the OpenAPI route
table, update and promote documented with their optional body, and the
document regenerated.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:08:33 +02:00
Ilker ManapandClaude Opus 5.5 801e2d51c0 Merge C20 tracing beyond the router
Conflicts: config imports and docgen sources (both kept); agent.pb.go
regenerated with buf from the merged proto (MIG devices and trace context).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:05:29 +02:00
Ilker ManapandClaude Opus 5.5 f0477f140d Quality suites, and new weights held to one: ctl eval, model update/promote --eval, model gate
A suite is a set of cases in YAML or JSON lines, each scored by exact,
contains, regex, a number within a tolerance, a JSON Schema subset, or a
judge model with a rubric; weighed into one score against a threshold.
internal/bench/eval runs one on the control plane through Router.Replay, as
the gateway's own requests, and keeps every run and its cases in the store
(migration 0028: eval_runs, eval_cases).

- llmgw ctl eval MODEL --suite FILE|NAME, --history, --run, --suites; exits
  non-zero below the score. Suites by name from control.eval_dir, or the
  two built in from deploy/eval (arithmetic, json-format).
- model update and promote take --eval SUITE --min-score N, or a model's
  standing gate (ctl model gate, eval: in the catalog): a promote asks the
  canary first and leaves it below the score; an update tries the new
  weights as a canary given no share, then promotes or removes it.
- The console's model menu: ask a suite with its progress, its runs, its
  gate.
- The audit middleware no longer hands a handler a body cut off at 64 KiB.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:04:43 +02:00
Ilker ManapandClaude Opus 5.5 e725adc2f0 Tracing beyond the router: reconcile passes, placement and a replica's start traced down to the node
A reconcile pass that does something is a trace, with placement (where it
went, or every candidate turned down), scale-up/down, drain, stop, eviction,
preemption, reaping and restarts beneath it. A replica's start is a span open
from placement until it serves; the start command carries its context in a
new ControlMessage.trace field, and the agent continues the trace through
the weights fetch, engine launch, rendezvous and readiness wait. Stops,
drains, adoption and engine installs are traced on the node, model jobs are
a trace with a span per step linked to the replica's start, and agent.yaml
takes the same tracing block as server.yaml. Off, every span is the no-op one
and commands carry nothing.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:03:17 +02:00
Ilker ManapandClaude Opus 5.5 f48f55a866 Merge C17 response cache
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:51:19 +02:00
Ilker ManapandClaude Opus 5.5 44f3a9e31d Reusing answers: a response cache per project, exact match, opt-in with a TTL
llmgw keys cache --project P --ttl 1h [--any] | --off, and Cache answers… on
the console's project menu. The same request — project, endpoint, canonical
model and the body without stream, stream_options, user, metadata, store and
service_tier, keys sorted — is answered from the gateway's memory for the
TTL. Only reproducible answers (temperature 0 or a seed; embeddings, rerank,
score) unless --any; only a whole 200 from the model asked for, not a
fallback's, a canary's, or one a guardrail changed.

Looked up after the limits and the input guardrails; the output policy
judges a reused answer; no_store and stored conversations bypass it.
Streamed answers are kept put back together and streamed back as chunks.
x-llmgw-cache: hit|miss|bypass, Age on a hit, Cache-Control: no-cache or
x-llmgw-cache: no to bypass. A hit is recorded with no tokens and no cost,
marked cache_hit (migration 0027) and shown by ctl request. An LRU bounded
by router.cache.max_bytes and max_entry_bytes; llmgw_cache_requests_total,
llmgw_cache_bytes, llmgw_cache_entries.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:50:53 +02:00
Ilker ManapandClaude Opus 5.5 e81f1cba4c Merge C24 docs portal and client guide
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:47:35 +02:00
Ilker ManapandClaude Opus 5.5 bd439aca29 A docs portal at /docs and a client developer's guide
The manual the binary carries, rendered on the client port: a sidebar of
the documents in the console's reading order (now one list, llmgw.Manual,
for both), heading anchors, links between documents kept in the portal and
links to files outside the binary sent to the repository, no script.
Public by default; landing.docs_sign_in sends visitors to sign in first.

docs/clients.md shows the official OpenAI and Anthropic SDKs against
llmgw in Python, TypeScript, Go and curl, with llmgw's headers; the
portal's index, the landing page and the account page link to it.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:46:42 +02:00
Ilker ManapandClaude Opus 5.5 35657c1417 Secrets in Vault: env: and vault: references wherever a secret file is named, and the store's own secrets sealed under a master key — Vault transit or a local key
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:21:44 +02:00
Ilker ManapandClaude Opus 5.5 bce54f0941 Scaling by the clock: schedule windows with their own min and max, prewarm, control.timezone
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:16:56 +02:00
Ilker ManapandClaude Opus 5.5 10466416df server restore: an archive checked, dry-run, and put back — configuration with modes and owners, the store in SQLite or PostgreSQL; backup_copy_to copies archives off the machine
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 23:09:59 +02:00
Ilker ManapandClaude Opus 5.5 841ee21c12 Batches: OpenAI's Files and Batch APIs, served at the lowest priority under a store lease, each line a request of the key that made it
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 21:00:01 +02:00
Ilker ManapandClaude Opus 5.5 29a7347df2 Requests can be tagged: metadata, x-llmgw-tags and the user field on the usage record, and counted by the tags router.tag_labels names
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 19:45:37 +02:00
Ilker ManapandClaude Opus 5.5 1b71c38f89 Notifications: webhooks for a parked model, a lost node, a spent budget and new weights; Alertmanager receiver templates
notify.webhooks sends signed JSON or Slack-compatible messages, queued,
retried, de-duplicated hourly; ctl notify test checks each webhook.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 16:58:11 +02:00
Ilker ManapandClaude Opus 5.5 8866a1ea0f Key lifecycle: lifetime limits by scope, rotation with overlap, kinds and expiry in the listing
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 16:45:05 +02:00
Ilker ManapandClaude Opus 5.5 14ea59d83f Provisioning through SCIM 2.0: accounts and groups kept in step by the identity provider
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 16:40:15 +02:00
Ilker ManapandClaude Opus 5.5 4cf40644c9 Single sign-on through OpenID Connect: accounts, staff roles and memberships from the provider
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 16:36:15 +02:00
Ilker ManapandClaude Opus 5.5 13e6f19301 Attach guard policies to scopes: store, admin API and ctl guard; run the gate when server.yaml defines policies
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 12:34:47 +02:00
Ilker ManapandClaude Opus 5.5 7b6276901a Keep llmgw's internal ports to the cluster's networks with an nftables table of its own
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 11:03:46 +02:00
Ilker ManapandClaude Opus 5.5 12efb7d085 Encrypt backups to backup_recipients with age
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 10:38:47 +02:00
Ilker ManapandClaude Opus 5.5 fe5b7f88f0 Believe X-Forwarded-* only from router.trusted_proxies
A new internal/clientip says who sent a request and how: the connection's
address, scheme and Host, or through a configured proxy what it forwarded.
The base URL in pages and setup scripts, isHTTPS for cookies, and the
per-address limits of auth and the sign-in forms use it. /setup scripts are
no-store.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 10:29:02 +02:00
Ilker ManapandClaude Opus 5.5 f1b49d0251 Bound idle time, header size and request reading on every listener, and connections on the client port
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 10:21:15 +02:00
Ilker ManapandClaude Opus 5.5 c0421bc7ee Guard the admin API and pprof with a token only root and the server can read
The admin listener answered any local process: models added, nodes
upgraded, engine keys listed, the heap dumped. /api and /debug now demand
the token the server writes 0600 to its state directory on first start;
ctl, the console and node add send it (sudo, LLMGW_ADMIN_TOKEN or
--token-file). pprof is off unless debug_pprof. admin_listen off loopback
is refused unless admin_remote. Dashboard pages, /metrics and /health are
unchanged.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 10:02:44 +02:00
Ilker ManapandClaude Opus 5.5 c522e8b2aa Refuse to open the agent port without TLS unless agent_insecure says so
Without agent_tls the control plane served plaintext h2c on every
interface, and any machine reaching it could register as any node. The
server now refuses to start that way unless agent_insecure: true, and then
binds loopback when agent_listen names only a port.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 09:51:37 +02:00
Ilker ManapandClaude Opus 5.5 44425193bd Track the registry's new weights for served models, and move a model to them or back
A model served from the registry records its origin: repository, commit and
each file's checksum; one served before is worked out from the mirror's
record of where it fetched the file. Every mirror.update_check (6h) the
control plane asks whether those files changed there. ctl model updates
lists it, ctl model update fetches beside the old files, checks, swaps and
replaces replicas one at a time, ctl model rollback goes back. The console
shows it on Models and offers the same.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:12:20 +02:00
Ilker ManapandClaude Opus 5.5 ce006a6e6f Publish per-tenant request and budget series, and alert on them
Requests by outcome, tokens and first-token time per tenant, at the level
router.tenant_label names (team by default), and every budget's share spent
this period. Rules alert on budgets at 80% and 100%, tenants hitting limits,
failing, spiking past their weekly average, or waiting on first tokens.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 19:55:24 +02:00
Ilker ManapandClaude Opus 5.5 4454e1322c Read usage from sums kept as it is written, not from every request
Charts, totals and budgets summed the request table on every view. Usage is
now also summed in the writing transaction into five-minute, hourly and daily
tables per key, person, project and model, with latency and first-token
histograms. Charts read the coarsest tier their slices allow; totals and
budgets compose rows, slices, hours and days, and stay exact. Request records
can be given a retention without moving any total.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 19:43:10 +02:00
Ilker ManapandClaude Opus 5.5 e313f32696 Decide engines per node, and let a node join without one it cannot run
engine_overrides give nodes picked by GPU class, id or labels their own
engine versions; node add --disable-engine keeps one off a node; what
vLLM cannot do on a node is a warning rather than a refused node; the
CUDA requirement follows the version; a hand-named binary is no longer
replaced by an installed one.

Refs #2 (items 4 and 7).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-01 12:07:25 +02:00
Ilker ManapandClaude Opus 5.5 3d3c96e422 Displace the newest lowest-band request when the gateway queue is full
Release / notes (push) Successful in 3s
Release / build (push) Successful in 1m9s
CI / test (push) Successful in 3m50s
A total bound across bands (admission.queue_capacity_total, default half of
all bands' capacity together); reached, a request is not refused while a
lower band has requests queued, and the newest of the lowest band gets a 503
with Retry-After instead.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 23:07:53 +02:00
Ilker ManapandClaude Opus 5.5 62657f4c2a Release v0.10.4: CPU threads, tracing, and the rest of the review
Release / notes (push) Successful in 3s
CI / test (push) Successful in 4m57s
Release / build (push) Successful in 4m11s
CPU replicas start on half the machine's CPUs, not all of them: two busy
llama.cpp servers each spinning on all 8 vCPUs fell to 0.8 tok/s apiece,
where at 4 threads they keep 5.5. llamacpp.threads sets it per node.

Inference requests can be traced over OTLP/HTTP (tracing.endpoint), with
admission, schedule and upstream spans and traceparent sent to the engine.

Security: onboarding no longer puts the cluster root in the system trust
store and removes it where it was; the mirror's mutual-TLS API can be
limited to named certificates (--api-client); init.log no longer keeps the
administrator's password; a warning when auth is off on a public listen;
the recorded actor is sanitised and sudo-aware; Ray's dashboard is off, and
the remaining engine gaps are documented.

reconciler.go and agent.go are split by topic, the status mapping of each
failure is tested, and the plan's checklist is brought up to date.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 04:00:35 +02:00
Ilker ManapandClaude Opus 5.5 116e75f8cb Upgrade the cluster with one command, over the agents' own streams
Release / build (push) Successful in 1m5s
Release / notes (push) Successful in 3s
CI / test (push) Successful in 3m42s
Every upgrade so far has been a script of mine copying a binary to each
machine over ssh, restarting it and polling until it came back — which is
the job, but not something the product could do, and which needed ssh into
every node.

`sudo llmgw ctl upgrade VERSION` on the control plane does it. This machine
first: the release for its platform, checked against the release's
checksums, the old binary kept beside it, llmgw-server restarted, and a wait
until every node that was ready has reconnected. Then each node in turn: the
control plane tells its agent the version over the stream it already holds;
the agent fetches and checks the release itself, swaps it in with a rename,
answers, and exits with status 75 so systemd starts the new binary. Engines
keep running, as for any agent restart, and are adopted again.

A node is done when it is back on the new version, ready, with as many ready
replicas as before; one that is not within the timeout stops the run before
the next node, so a bad release reaches one machine. Nodes already on the
version are skipped, so running it again resumes.

The fetch-and-verify is one package now, shared with onboarding's idea of
what a release version looks like.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 02:54:36 +02:00
Ilker ManapandClaude Opus 5.5 9bf8256577 Keep backups where the control plane can see them
Release / build (push) Successful in 1m1s
Release / notes (push) Successful in 2s
CI / test (push) Successful in 3m35s
The first backup on the live control plane was written, and the control
plane reported none: /var/backups/llmgw already existed, made by an earlier
move to PostgreSQL for its own dumps, owned by postgres and 0700. MkdirAll
leaves an existing directory as it is, so the archive landed where the
llmgw user could not list it, and llmgw_backup_last_success_timestamp_seconds
said 0.

Opening that directory up would have exposed the dumps already in it, so
backups get their own, /var/backups/llmgw-server. And `llmgw server backup`
now warns when the directory it wrote to is one the control plane cannot
list, rather than leaving that to be found from an alert.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 01:50:33 +02:00
Ilker ManapandClaude Opus 5.5 1da4a2e1ef Back up the store and the certificate authority, and alert when it stops
Release / build (push) Successful in 1m1s
Release / notes (push) Successful in 3s
CI / test (push) Successful in 3m32s
There were no backups: docs/install.md gave a pg_dump command, and nothing
ran it. The store holds every key, person, quota and usage record, the models
added at runtime, and now the secret each engine's key is derived from; the
certificate authority's key sits in /etc/llmgw/pki beside it. Losing the disk
lost all of it.

`llmgw server backup` writes both to one archive: pg_dump's custom format, or
a VACUUM INTO snapshot for SQLite, plus /etc/llmgw. The archive holds the CA's
key, so it is 0600; the directory is listable, so the control plane — not
root — can see when the newest was written. pg_dump is given the connection
through its environment, since a DSN carries the password and a process's
arguments are readable by every user. Written beside its name and renamed,
so an interrupted backup is never the newest; the newest 14 are kept, and
nothing the command did not write is ever removed.

llmgw-backup.timer runs it nightly and catches up after downtime. The control
plane publishes the newest archive's time, and BackupTooOld fires past 26
hours — or when there has never been one. The install guide now covers
restoring, and says to copy archives off the machine, since they share its
disk.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 01:44:32 +02:00
Ilker ManapandClaude Opus 5.5 9853936e0b Give every engine a key only the router holds
Engines listen on every address their node has, with no key. Checked on the
live cluster: from a neighbouring node, a request straight to an engine's
port was answered — past the gateway's authentication, quotas and
accounting, by anyone who could reach the node.

Each replica's engine is now started with a key and refuses requests without
it. The key is derived from the replica id with an HMAC over a secret kept
in the store, rather than stored per replica: the router has to send the
right key to replicas this process never started — adopted after a restart,
or placed by the other control plane — and a function of a shared secret
gives that without a table to keep in step. A key taken from one node opens
that replica only. The secret is made on first use and copied with the rest
of the store when moving to PostgreSQL; a new one would lock the router out
of every running engine at the moment of the move.

The key reaches llama.cpp and vLLM through their environment
(LLAMA_API_KEY, VLLM_API_KEY) rather than their command line, which every
user on the node can read; SGLang only takes it as an argument. The agent's
readiness check, the router's proxy and its metrics scrape send it, the
client's own Authorization still never reaches the engine, and `ctl bench`
fetches the key of the replica it is pointed at from the admin API.

Engines started before this keep running without a key until their replica
is next started. With no store there is nowhere to keep the secret, and
engines start without one, with a warning.

Also formats two files that went in unformatted.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 00:38:29 +02:00
Ilker ManapandClaude Opus 5.5 4c5a2fd6da Install vLLM on every GPU node that can run it, as llama.cpp is
vLLM was installed by hand and named in each agent's configuration. The
agent now installs it: a Python 3.12 environment built by uv, which is
itself a GitHub release checked against its checksum, from PyPI resolved as
it stood a day after that vLLM was published and installed with
--require-hashes. The resolved list is kept in the environment. The
environment is built relocatable under a scratch name and renamed into place
once it runs, like an archive.

The default is 0.30.0, whose flags were checked against the ones llmgw
builds. It is built for CUDA 13, so it needs driver 580 and a Turing GPU or
newer, and 25 GB free while it installs; a node lacking one says which, and a
node with no GPU skips it without being shown as a fault. gcc comes with it
because Triton compiles its launcher at the first model load. SGLang
installs the same way when the control plane names a version. llmgw doctor
reports whether vLLM can be installed on the node.

Checked by installing 0.30.0 this way on a test node: 7.7 GB, torch 2.13 for
CUDA 13.0, importing cleanly; the node has no GPU, so vLLM was not started.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-29 13:15:54 +02:00
Ilker ManapandClaude Opus 5.5 80e0dd252f Document what changed since v0.9.2, and fabrics for the sites that have them
The changelog's unreleased section had stopped at refusing unloadable
weights; it now covers the rest: telling independent fabrics apart,
their subnet managers and maps, NVLink on every build and across nodes,
the multi-node launch fixes and vLLM's new default, doctor, node load,
editors and the Responses API, the chat and mirror pages, a person's own
use, the admin pages, the new metrics, and how to upgrade.

docs/fabrics.md is new, for a site with InfiniBand or NVLink: what
llmgw does with them, what each node and fabric needs first, declaring
fabrics, checking a node with doctor, what the pages and metrics show
and which to alert on, what an engine is given, and where to look when
a replica spanning nodes will not run. It says plainly that none of it
has yet run on such hardware.

install.md, node-onboarding.md, onboarding.md, the README and the
example agent configuration no longer say the portable binary cannot
see NVLink or that a fabric's name cannot be checked, and describe the
account page and connecting an editor.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-29 10:14:58 +02:00
Ilker ManapandClaude Opus 5.5 098886e0e4 Let a person belong to many places, or to none
A person was in exactly one project, chosen at approval, and could not
use the gateway before that. People belong to several teams and to
none, so:

- memberships: a person is a member of any number of organizations,
  teams and projects, or of none; a member of a team or organization
  may use every project in it. users join/leave, and the people page
  adds and takes out from either side. Approval no longer needs a
  project.
- personal keys: a key may have an owner and no project. /profile asks
  what a new key spends against; keys create --for does the same.
  auth.personal sets default limits for personal use or turns it off.
- limits for people: --scope user holds a person across every key,
  project and the chat page; --per-member on an org, team or project
  gives each member their own share there. Resolution folds the tree,
  each per-member limit for the key's owner, and the owner's own, each
  in its own pool; the quotas page shows and sets both.
- the chat page asks what to spend against and checks it per message.
- usage records who spent it, so a person's budget survives a restart,
  personal use and chat included; restore no longer drops rows with no
  project.

Leaving a project revokes the keys made there unless another membership
still reaches it. A personal key keeps no threads or notes, which are
per project, and is refused rather than dropped into the anonymous pool.

Migration 0010 turns each person's project into a membership, adds
usage.user_id and backfills it, and makes api_keys.project_id nullable.
SQLite cannot drop NOT NULL, so the table is rebuilt; that needs foreign
keys off, which only works outside a transaction, so migrations marked
for it run on one connection with foreign_key_check before commit.
Tested on a populated SQLite store with claims, and on a copy of the
cluster's PostgreSQL store: 5 people became members, 17 keys and 3
claims intact, 145 of 577 usage rows and all 69 chat rows attributed.
The PostgreSQL store tests, including new membership cases, pass on 16.

users move is gone; join and leave replace it.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 19:03:46 +02:00
Ilker ManapandClaude Opus 5.5 6dba6bd93a Run a control plane when there is nothing else to run
A configuration with no static endpoints and no models was refused as
having nothing to serve. That is every new cluster: under systemd the
unit restarted every two seconds and nothing ever listened on 8080.

With no endpoints a router-only process has nothing it could serve, so
such a configuration is now a control plane with an empty catalog.
Static endpoints without profiled models remain router-only.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 13:06:29 +02:00
Ilker ManapandClaude Opus 5.5 7d97c6b74f Install a node's engines on the node, instead of trusting what is there
A node ran whatever llama-server somebody had once unpacked on it. Onboarding
checked an engine only when told its path, installed none, and a node with
nothing on it registered as ready. The one time that went wrong it went wrong
invisibly: the binary was there, executable, and could not start for want of
libgomp1, while the node reported healthy.

The control plane now says which engines every node has, at which version —
`engines:` in server.yaml, defaulting to the llama.cpp build this release was
checked against — and each agent converges on it. What only the node can
know, the node works out: the build for its processor and driver (CUDA with
its runtime when an NVIDIA driver is loaded, CPU otherwise), the OS packages
that build needs from its own package sources, and whether the result runs.
Every archive is checked against the sha256 GitHub publishes for it and
unpacked refusing any path or link that leaves the install directory. ldd
names a missing library outright; running `--version` proves the rest. Only
then is a directory marked installed, and it is checked again every ten
minutes, because an unrelated upgrade can remove a library.

An engine is reported only once installed and seen to run, or when the
agent's configuration names it on purpose — never because something happened
to be on PATH. The agent now says when it has probed, so an empty list means
"has none" rather than "too old to say": a node rebuilt from nothing is no
longer a candidate for every model at the moment it can run none of them.
Placement's refusal carries the node's own words, "installing: downloading
llama-b10991-bin-ubuntu-x64.tar.gz (16 MB)", and so do `ctl nodes` and the
cluster page, along with a warning for a CPU without AVX2 — the VM CPU type
that makes everything five times slower and nothing look wrong.

Agents also report their OS, architecture, vector extensions and NVIDIA
driver. Onboarding installs llmgw itself from the CI release for the node's
architecture, checked against the release's checksums, rather than copying
whatever binary the operator's machine had.

vLLM and SGLang are not installed yet: they are Python environments of
several gigabytes, not an archive, and still have to be named in the agent's
configuration.

Also fixes a race on the weights fingerprint, which two heartbeat loops touch
during a failover.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 10:59:59 +02:00
Ilker ManapandClaude Opus 5.5 20deb22dfa Let a node describe itself instead of being described by hand
CI / test (push) Successful in 1m47s
Every agent file on the cluster named its own node, its own address, the
path to llama-server and two weight directories — different on every node,
kept true by hand, and not true: node05 carried "ram: 32g" beside a measured
31 GB, looked for weights in an empty directory while fetching them into
another, and the other four never looked in theirs at all, so four nodes
reported no disk. Growing a node's RAM would have gone unnoticed, because
memory was read once, at registration.

The agent now finds these out. Its id is the hostname, which is also the
certificate's common name. Its address is the one on the route to the
control plane, which the kernel picks for a UDP dial without sending
anything. llama-server is looked for on PATH and then where release archives
are unpacked. A missing nvidia-smi is a node without NVIDIA cards rather
than a failed discovery — which also cut discovery short before InfiniBand
on every CPU node not told to skip GPUs. Fetched weights land in
/var/lib/llmgw-weights by default, and wherever they land is always looked
in.

Memory is read on every heartbeat, and installed engines are probed again
each minute and sent when they change, so a VM given more RAM or a node
given vLLM becomes a candidate without anyone restarting its agent. The
control plane logs both changes, since "the node now qualifies" is the
answer to why a model placed an hour after it was asked for.

What is written still wins. The agent file shrinks to the control plane's
addresses and the TLS files, the same on every node; onboarding writes only
the overrides it was given. What cannot be found stays configuration: which
fabric an adapter is on, because OpenSM's default prefix is the same on all
of them.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 10:13:42 +02:00
Ilker ManapandClaude Opus 5 c6df0659af Put the cluster's own charts on its own admin page
CI / test (push) Successful in 1m50s
The dashboard charted what the cluster had been billed for — requests, tokens,
spend, all from llmgw's own store — and nothing about whether it was healthy.
Saturation, queue depth, cache occupancy and replica counts were numbers in a
table at the instant the page loaded, with no way to see that one of them had
been climbing for an hour.

Four line charts now, read back from wherever the metrics were scraped to.

Read back rather than kept twice. llmgw publishes these already; what a gauge
cannot do is remember, and a ring buffer in this process would be a rival copy
of the same numbers with its own retention, lost on every restart and
disagreeing with the one an operator has on screen elsewhere. monitoring.prometheus
is empty by default and the panels are then absent rather than empty.

One axis per chart, always. Two measures of different scale belong in two
charts: a second y-axis lets any two lines be made to cross wherever the author
likes and the reader cannot tell it happened.

Four colours, handed out in fixed order, never cycled. A fifth series is summed
into "other" and drawn in grey — dropping it would make a chart that does not
add up, and inventing a hue for it would put two lines on the page that nobody
can tell apart. The fold is by timestamp, not by position: the tail's series do
not share sample times, and adding them by index slides points sideways onto
each other's clock.

A legend for every chart with more than one line, because colour alone is not
an encoding a reader can rely on.

A flat zero is drawn along the bottom rather than left blank: nothing happening
is a real answer, and an empty frame reads as a broken chart. A single sample
is not a line and says so instead of putting a dot in the corner.

One failed query fails all four panels. Three drawn and one blank invites
reading the blank one as "nothing is happening there".

NaN is dropped rather than plotted. Prometheus sends it as a string for a
sample it has no value for, Go's ParseFloat accepts it happily, and one NaN
coordinate is an SVG path that does not draw at all — taking the rest of the
line with it.

Axis maxima are rounded to a number a person would pick. An axis topping out at
0.8347 makes every gridline unreadable, and the shape is what a chart is for.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-27 18:25:56 +02:00
Ilker ManapandClaude Opus 5 ed530133b6 Find a model in the registry instead of pasting a URL into a box
CI / test (push) Successful in 1m41s
Mirroring anything meant knowing a repository existed, knowing which of its
thirty files were the weights, and assembling a resolve URL by hand. The mirror
page had a text box for that URL and no way to find one.

It now searches Hugging Face and lists a repository's weight files with their
sizes and published checksums, each with a button that fills the fetch form.

Only weight files. A repository is mostly a README and a tokenizer, and listing
those buries the four entries somebody came for.

The size shown is the LFS size, not the plain one. For an LFS-stored file —
every weights file — the plain field is the size of the pointer, so the other
one reports a gigabyte model as 133 bytes, and that is the number somebody
would then plan disk against.

The source URL is pinned to the commit the listing came from rather than to a
branch, so what the mirror fetches is what was on screen. A repository
re-uploaded under the same branch otherwise leaves two different sets of
weights with identical provenance and no way to tell them apart. The version
defaults to that revision for the same reason.

The registry's own failures are reported on their own line. It is somebody
else's server on the other side of the internet, and it being down says nothing
about the mirror — which is what the page is for and has to keep working
regardless. With no registry configured there is no search box at all, rather
than one that can only time out.

Gating decodes from a bool or a string, because the field is documented as the
first and is the second in practice: strict decoding fails the whole response,
so one gated model would hide the other nineteen in a page of results.

And a bug this made obvious: downloads were keyed by model and version, so the
second shard of a sharded model was refused as "already fetching" until the
first had finished. A fifteen-shard model had to be pulled one file at a time,
each waiting on the last. Keyed by file now — which is what the single-flight
was ever protecting, since the race is two writers on one .part. A version made
of several files reports as the worst of them: it is not present until every
shard is, and one shard failing makes the version unusable however many others
arrived.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-27 15:18:57 +02:00
Ilker ManapandClaude Opus 5 10e323132c Let a control plane whose models all live in the database start
Control plane mode was inferred from the config file alone: a model with
profiles meant "control plane", nothing meant "router only". So a deployment
that manages its catalog at runtime could not start at all — the file declares
no models, the process refuses for want of anything to serve, and the stored
models it would have loaded are never read. A cluster unmanageable at runtime
because it is managed at runtime.

control.enabled says so outright. AgentListen cannot carry the signal: it has a
default, so every deployment would silently become a control plane.

The inference stays, so nothing already working has to add a flag.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-27 11:24:49 +02:00
Ilker ManapandClaude Opus 5 cd7eedf09e Give the mirror a page, so managing it is not a curl command
CI / test (push) Successful in 1m49s
/admin/mirror, behind the same admin session as the other admin pages. What is
held, what is arriving with its byte count, what failed and why; start a fetch,
retry a failed one, remove a version.

Not mounted at all without a mirror configured. The right page for a deployment
with no mirror is no page, rather than an empty one pointing at nothing.

It reloads itself only while something is downloading. A reload at any other
moment takes with it whatever is half-typed into the fetch form, and there is
nothing to watch when nothing is moving.

A failed row offers Retry, not Remove. A fetch that failed left nothing on disk,
so the remove could only answer "the mirror holds nothing for this" — a button
whose single outcome is a confusing error. Starting the same download again is
what somebody looking at that row wants, and the mirror allows it: only a
download still running is refused.

An unreachable mirror is said outright instead of rendering as an empty table.
The two look nearly identical and mean opposite things: one is a mirror waiting
to be filled, the other is a machine to go and look at.

Dashboard takes NavExtras rather than a second bool. Two adjacent booleans at a
call site get swapped silently and are discovered by somebody clicking the
wrong link.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-27 10:17:12 +02:00
Ilker ManapandClaude Opus 5 5b5e61cb97 Stop a second control plane from placing work behind the first's back
CI / test (push) Successful in 1m35s
The first thing HA needs that a shared store does not give. Two control planes
against one store both reconcile: both see a model wanting two replicas and
none running, and both place. The model ends up with twice what it asked for,
each replica holding GPUs the other's inventory believes are free — and nothing
crashes to say so.

A lease in a table rather than a lock held by a connection. PostgreSQL has
advisory locks and SQLite has nothing like them, and this store keeps one set
of queries for both; a row with an expiry works everywhere, and it survives a
leader being powered off rather than asked to stop, which is the case that
matters. Taking and renewing are the same statement, so the two cannot disagree
about what a held lease looks like, and it is one statement, so two processes
racing cannot both believe they won.

The owner id is random rather than the hostname. A hostname would let a
restarted process match its own stale lease and believe it had been leading all
along — including through the gap that made it restart, during which somebody
else may have taken over and started placing.

A store that cannot be reached is not evidence that somebody else is leading,
so an unreachable store keeps the claim. Two leaders is worse than one, but no
leader means nothing is placed and nothing is evicted, and a brief database
blip should not stop a cluster healing itself.

Unset means leader. Every deployment that existed before this, every
single-control-plane install and every test acts unconditionally, with nothing
to configure.

The same seven assertions run against both backends, which is how the test
harness was caught inheriting a lease between subtests — it passed on SQLite,
where each subtest gets a fresh file, and failed only on PostgreSQL.

What this does not yet do is move agents. A standby holding an agent's stream
is one the leader cannot command, so failover is degraded rather than clean
until agents know more than one address.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-25 18:24:06 +02:00
deniz 2eb79f3400 agenta memory eklendi
CI / test (pull_request) Successful in 2m31s
2026-09-24 04:04:03 +03:00
Ilker ManapandClaude Opus 5 1ea067d08e Give metrics a door that does not also open onto pprof
CI / test (push) Successful in 1m38s
The metrics existed and nothing could record them. They shared a listener
with pprof, the management API and the dashboard, and pprof can dump the
process heap where API keys sit in plaintext — so a fleet could be monitored
or keep its heap private, and not both. That is not a choice anyone should
have to make, and it is why every previous answer to "how do I scrape this"
was a tunnel.

metrics_listen serves metrics and health and nothing else, so it can be
reached from wherever Prometheus lives. Metrics stay on the admin listener
too: adding a door is not the same as moving one, and anything already
scraping keeps working.

While there: admin_listen defaulted to :9090, every interface, with a
comment beside it saying not to expose it. A default that contradicts its
own documentation is a footgun, so it is loopback now and someone who wants
otherwise says so.

The handler is nil until the registry is built, and says so rather than
serving an empty page. Ordering has already caught this exact area once —
a collector registered after AdminHandler published nothing at all, silently
— and an empty scrape target looks like a working one.

deploy/monitoring/prometheus.yml has a starting configuration and the alerts
worth having: a node that has stopped reporting, a model that should be
serving and is not, a card kept out of placement by a fault, and a fleet
holding models nobody is asking for.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 18:12:10 +02:00
Ilker ManapandClaude Opus 5 7fe59bd5fb Load a model when someone asks for it, and stop it when nobody does
CI / test (push) Successful in 1m29s
The feature the idle tracking was for. A cluster with more models than GPUs
can now hold every model in its catalog and only the wanted ones in its
cards: min 0 with a max above it means load on demand, and once nobody has
asked for idle_timeout the replicas stop and the cards go back.

No new field, because min 0 max 1 already reads correctly — keep none
running, allow up to one. Which made min 0 max 0 meaningful for the first
time: configured and deliberately not running. normalize() used to fill a
zero max in, on the reasonable ground that a model with no maximum cannot
run; that would now silently turn every switched-off model into an
on-demand one, including the ones already written that way in this
cluster's own configuration. A model with no scaling stanza stays off for
the same reason — defaulting it to on-demand would let any client request
start a 70B nobody intended to run.

The one real decision is what happens to the request that triggers a load.
Refusing makes the feature useless, since the first request for every model
fails; waiting without a bound turns a request into a job, and a client that
budgeted thirty seconds holds a connection for ten minutes. So it waits
briefly and then says what is happening — 503 with Retry-After and "the
model is loading", which is a different answer from "no endpoint serves
this" and produces different client behaviour. An unknown model still gets
the unknown-model error, or on-demand would turn every typo into "loading"
and the useful message would disappear.

Use keeps a model alive rather than only the request that started it,
without which the timer measures time since the load and a busy model is
evicted on schedule however hard it is working.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 17:44:00 +02:00