Until now anything that could reach the client port could use every model in
the catalog. A key now resolves to an identity, and that identity decides what
it may do.
Authentication wraps the whole mux rather than checking inside each handler,
so adding a route cannot add an unauthenticated one by omission. Health stays
open, because a load balancer has no key and a health check that needs one
reports the gateway down.
Nothing on the request path reads the database. A key is resolved once and
answered from memory until the entry expires; rejections are cached too, so a
client looping with a bad key cannot turn into a database read per request.
The price is that a revocation takes up to cache_ttl to take effect, which is
the trade stated in the configuration next to the knob. A store failure is
not an authentication answer: it is never cached as one and returns 503, not
401 — sending someone hunting for a key problem that does not exist wastes the
one thing an incident is short of. A revoked key is refused with the same
message as an unknown one, because saying otherwise confirms the key was real.
With auth on the band comes from the key and the band header is ignored. The
header was trusted only while there was nothing to consult, and it let any
client promote itself into the top priority band. Tenant fairness within a
band is now per key rather than per session, so one caller cannot take a band
by opening many sessions.
Allowlists are decided per model, not per string: a model's canonical name and
every alias name the same thing, so either form works in an allowlist and no
alias can reach a model that was not allowed. The first version of that test
passed without the resolution being there at all, which is why it now checks
all four combinations.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Deployed against real llama.cpp, every scrape failed. The mapping named
llamacpp:kv_cache_usage_ratio; build b10991 serves fifteen metric families
and none is a cache ratio. Because KV usage was mandatory, that one absent
name threw away the two metrics the engine does publish, and the router
scheduled to all three replicas blind while the cluster looked healthy.
A mapping that leaves a metric unnamed now means the engine does not publish
it, and the field stays zero. Naming one the engine does not serve is still a
violation, so this does not become a way to tolerate a typo. Running and
waiting can never be omitted: an engine that reports neither what it is doing
nor what is queued cannot be scheduled against at all. For llama.cpp this
costs the KV half of the saturation signal, which is a real loss softened by
its fixed slot count — queue depth already says when it is full.
The second half is why it took a deployment to notice. A contract violation
was logged per scrape at debug level, so at the default level nothing said
anything. It is now a warning, once, with a matching line when it clears.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
llama.cpp is what makes a cluster with no cards useful: it serves the same
OpenAI API on CPU, so the whole path — placement, supervision, scraping,
scheduling, admission — can be exercised end to end on ordinary machines.
Three things had to give way for it.
A profile may now omit its GPU class, and that is how it says it runs on the
CPU. Only engines that can actually serve without a card may omit it; for
vLLM an omitted class stays an error, because otherwise a typo becomes a
replica placed on a machine with no hardware and diagnosed minutes later
during model loading. Placement spreads CPU replicas instead of bin packing
them, since unlike GPUs there is no allocation to stop two of them sharing a
machine's cores.
Metric mappings are now per engine rather than per cluster. llama.cpp calls
the same three numbers requests_processing, requests_deferred and
kv_cache_usage_ratio, and a single global mapping would leave half a mixed
fleet unmeasurable. An empty mapping still defaults to vLLM's names; one that
names its own Running metric is taken as a complete statement, so the fields
it leaves blank stay blank rather than being filled with names that engine
cannot have.
The adapter refuses multi-node and tensor-parallel profiles. llama.cpp splits
across local GPUs by a different mechanism than this adapter drives, and
accepting either would produce a replica that starts and then serves from one
machine while the catalog believes it has several.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
CI went red on Linux with two failures that never appear on macOS. Both were
worth the trip.
The first is a real bug. processAlive used kill(pid, 0), which succeeds on a
zombie — a process that has exited and is only waiting to be reaped. That
happens for real whenever an engine's parent dies before it does and nothing
reaps the orphan, which in a container is the normal case: PID 1 is usually the
workload rather than an init. The supervisor would then report a dead adopted
engine as running forever, and hold its GPUs against every future placement.
Zombies are now detected through procfs on Linux, where the answer exists, and
the check degrades to its old behaviour elsewhere rather than to something worse.
The second was a bad test. TestTenantFairnessWithinBand asserted on the order
goroutines sent to a channel after being admitted, which is the order the Go
scheduler woke them, not the order the dispatcher chose. Under load it measured
the runtime. The rotation itself lives in bandQueue.pop, which is pure, so it is
tested there — including what happens when a tenant runs out mid-rotation and
when a cancelled waiter is removed. The controller-level test now asserts the
thing that is actually stable: nobody is starved.
Verified with three consecutive `go test -race ./...` runs in a Linux container.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
ctl talks to a management API on the admin listener, not the client-facing one.
The two have different audiences: one serves inference to whoever holds an API
key, the other lets a caller cordon nodes and read the cluster's shape.
- nodes surfaces unhealthy GPUs and why they are excluded. That is usually the
answer when a node looks idle but nothing will schedule onto it, and it was
invisible before.
- explain-placement prints every candidate considered and why it was rejected.
- replicas shows the shards a replica is made of, with per-shard errors.
- cordon, uncordon and drain are one endpoint with different targets, because
the difference between cordon and drain is exactly what an operator needs to
be sure of before running either.
Draining had to be fixed first to make ctl drain worth having. A drained replica
was stopped on the next pass, which cuts in-flight requests — the thing draining
exists to avoid. Now a node marked Draining has its replicas drained, the model
falls below its desired count, a replacement is placed elsewhere, and the
original is stopped only once the replacement is serving. A grace period bounds
it, because draining the only node that can host a model would otherwise never
finish and the node could never be taken out of service.
Verified against a two-node cluster of real binaries: draining moved a replica
to the surviving node and traffic kept returning 200 throughout.
ctl logs is deliberately absent. It needs a request/response pair the agent
protocol does not have, and the failure path already ships an engine log tail
with every status report — so the case that matters most is covered, and
reading a healthy shard's output on demand is not worth a protocol change yet.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
One bidirectional connect-go stream per node, carrying registration, heartbeats
and shard status up, and start, stop and drain down. The agent dials out: GPU
nodes sit behind firewalls far more often than a control plane does, and an
outbound connection needs no inbound rule on every node in the fleet.
- registration carries the whole hardware inventory, so there is no separate
discovery call and a reconnecting agent refreshes what the scheduler knows.
The fabric labels travel with it; they cannot be inferred from the wire, so
losing them in transit would silently disable multi-node placement.
- agentsvc is both the stream handler and the reconciler's dispatcher, because
it holds the open streams and is therefore the only thing that can deliver a
command to a node.
- the agent validates a profile before launching anything, since an engine that
refuses a profile does so after minutes of loading, then supervises the
process and reports every transition with the engine's output tail on failure.
- reconnects forever with jittered backoff. A control plane restart must not
require touching every GPU node, and a fleet must not reconnect in lockstep
and knock it over again. Engines keep serving throughout, because the router
talks to them directly.
llmgw agent is real now, and llmgw server runs a control plane whenever any
model declares a profile. The static endpoint list stays for router-only runs.
Verified with real binaries as separate processes: the agent registers, a
replica is placed, an engine launches through the vLLM adapter's actual argument
construction, streaming traffic is served, and killing the agent moves the node
through unreachable to lost with placement explaining why nothing can run.
config.Model and catalog.Model were the same thing described twice, so the
router now reads catalog entries directly and the validation rules live in one
place.
Still missing: mTLS. The stream is plaintext HTTP/2 and must stay on a trusted
network until that lands.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Ready replicas become router endpoints with no static configuration involved.
Endpoints that survive an update keep their live state — inflight counts,
breaker state, drain rate — so a replica that was already serving does not start
from cold because another one moved. The sink is an interface, so when the
router and control plane split into separate processes it becomes a watch stream
and nothing above it changes.
Phase 3's exit criterion now holds end to end. A node hosting a live replica is
killed while four clients stream continuously; the control plane marks it
unreachable, then lost, rebuilds the replica on a survivor and republishes.
Across three runs ~370 requests completed with zero failures and no replica was
left on the dead node. This proves the control logic, not the transport: the
agent fleet is simulated and the real path still needs the stream.
The race detector caught a genuine bug while this went in. startReplica read the
replica's fields after publishing it to the map, and scaleUp walked replica
pointers outside the lock; both raced with agent status reports, which arrive
from another goroutine and mutate exactly those fields. Against the simulated
fleet the reports came back fast enough to hit the window on every run. State is
snapshotted under the lock now and those functions work from values.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Inserted between quota checks and scheduling: admission answers when a request
may proceed, the scheduler still answers where it goes. Keeping them apart is
the point — an engine queue is FIFO and knows nothing about tenants, so once a
batch job is in it, no endpoint selection rescues the request behind it.
- saturation detector: one number per pool, the worse of queue depth and KV
occupancy, since either alone misleads.
- priority bands with per-band saturation ceilings, so the cluster degrades from
the bottom up.
- tenant round-robin within a band: one caller sending a thousand requests takes
one slot in the rotation, not a thousand.
- bounded queues with capacity (503) and TTL (504); cancelled requests leave the
queue instead of holding capacity.
- metrics for queue depth, wait time, rejections and pool saturation.
Exit criterion, measured in test/e2e: with 500 concurrent bronze requests
running continuously, interactive p99 in the platinum band stays at 1.04-1.24x
idle against a 1.5x budget. With admission off the same load pushes it to
55-60x. Both directions are asserted, so the test fails if admission regresses
and also if the load generator stops being a real load.
Two lags had to be closed, and they needed different answers. Engine metrics are
scraped and lag an interval; router inflight does not, but it counts running
requests, and treating those as queue makes a healthy engine look overloaded
every interval. What is actually queued is inflight minus batch capacity, and
capacity is not in the metric contract, so it is learned as the high-water mark
of observed running. Separately, between admission granting a request and the
router dispatching it the request is invisible everywhere, so a simultaneous
burst passed the check en masse; the controller now counts its own outstanding
leases against dispatched inflight.
One plan correction: a saturation ceiling of 1.0 was documented as "never held
back". It is not — it means "flow up to the healthy limit". A band that must
never wait needs a ceiling above 1. Plan §7.2.2 updated.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
llmgw server is real now. It fronts a static set of engine replicas with an
OpenAI-compatible API, scoring endpoints through the pipeline added in the
previous commit.
- proxy: SSE relayed event by event with a flush after each, cancellation
propagated upstream, and separate deadlines for dial, headers, first token,
inter-token idle and total. The idle watchdog is what distinguishes a wedged
engine from a slow one.
- router: dispatch with retry and model fallback. Retry only happens while
nothing has reached the client; after that, splicing two responses together
would be worse than the short stream the client already sees.
- config: YAML via koanf overlaid on defaults, with LLMGW_ env overrides.
Validation rejects duplicate endpoint ids and aliases that shadow a model,
because both misroute silently at request time rather than failing loudly.
- metrics: requests, duration, TTFT, tokens, plus per-scorer values and
per-filter drops on a separate admin listener with health and pprof.
Phase 1 exit criterion, measured in test/e2e: 1000 concurrent streams across
3 sim-engines complete at ~6800 req/s; every client disconnect frees the KV
blocks on every engine; router overhead p99 is about 0.9 ms against the plan's
2 ms budget.
The handlers live in internal/router rather than an internal/router/openai
package as the plan's tree sketched: they need the dispatch loop, and splitting
them apart would have meant an interface with exactly one implementation. Plan
§4 updated to match.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The code behind plan §7.3-7.6:
- breaker: folds cooldown and circuit breaking into one component
(FailureThreshold=1 gives LiteLLM-style cooldown), with exponential backoff
and half-open probes.
- endpoint: live state registry. Inflight counting, staleness detection, drain
rate derived from counters. A scrape failure does not trip the breaker — the
engine may be serving fine while only its metrics endpoint is down.
- scrape: parses the §7.6 metric contract. Errors when any of the mandatory
three is missing; the metric name mapping is overridable, since names drift
between versions (plan §14).
- scheduler: the filter -> score -> pick pipeline. A "strategy" is now just a
set of scorer weights; chat, batch and long-context are the same code with
different weights. Scorers: queue, kv (hard penalty above the ceiling),
inflight, load, weight, session (bounded-load consistent hashing). Pickers:
max-score, p2c, softmax, round-robin.
Decision carries the rationale — which scorer produced what, which filter
dropped how many. Tuning the weights without that is guesswork.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>