ea4dd37f80af44432cedc856b67b8f5fba577366
16
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
1c57a4e378 |
Let the catalog change while the cluster is running
Adding a model was an operator procedure with downtime: edit a file on the control plane, restart it, wait out the settling window, watch replicas churn while adoption catches up. I did that eight times in a day, and one of the restarts cost two minutes of outage while stalled replicas timed out. None of it was necessary. The reconciler already compares desired against actual on every pass, so a new catalog is simply a different desired. A Catalog stays immutable — New is the only way to build one and it refuses an invalid one — and what changes is which immutable catalog is current. Readers take the pointer and finish their operation against it, so a swap mid-request is invisible rather than a race. The router is told rather than asked, the same shape as the endpoint list and for the same reason: a push happens once per change, a pull would happen once per request. The router still seeds from configuration as well as being pushed to. A router with a static endpoint list and no control plane is a supported mode and has nothing to push it a catalog; without seeding it would resolve no model at all. Which turned up a bug that was latent while catalogs were fixed. reconcileModel only ever visits models that are in the catalog, so a replica whose model had been removed was visited by nothing: it kept its GPUs, kept counting, and kept running an engine for a name no client could ask for. The endpoint publisher skipped such a replica with the comment "the reconciler will tear it down", which was not true. It is now, and the comment says what actually happens instead of what was assumed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
9d8cd5e284 |
Track which replicas are actually being used, and summarise the fleet
Two things a cluster with many nodes and many GPUs needs that were missing, and they are the same thing seen from two distances. Idle tracking. The control plane knew what was placed and whether it was healthy, never whether anyone wanted it — so on a fleet with more models than cards there was no way to answer the first question anyone asks, which is what can I stop. The router is the only thing that knows, so it now reports it: a timestamp written in Acquire, where a request already meets an endpoint under a lock already held, and collected once a tick as a map. That shape is the point. Per-request notification would be a firehose carrying one bit — the newest timestamp wins — and this costs the same on four replicas as on four hundred. It travels through an interface in the direction opposite EndpointSink, for the same reason that one exists: the control plane decides what should run, the router knows whether anyone wants it, and neither should need to be in the other's process to say so. Unknown is kept distinct from idle throughout. A router that has just restarted knows nothing, and a zero timestamp would be the oldest idle replica in every comparison — so one restart would nominate an entire fleet for eviction. Absent from the map, "-" in the table, negative in the JSON, and IdleFor returns a second value rather than a duration anything could act on by mistake. ctl status. A per-node listing is right for four nodes and wrong for two hundred: how full am I, what is broken, what is holding cards nobody is using are aggregates, and reading them off a long table is a chore, which means it gets skipped. Capacity per GPU class with usage bars, free whole nodes per fabric — the number that decides whether a multi-node replica can land, since free cards on the wrong fabric are not capacity for a model that spans nodes — replica and model counts, models that cannot be placed, and what has gone unasked-for. Derived from the same state the tables show, so it cannot disagree with them. Unhealthy GPUs count as neither used nor free, because counting them free is how a cluster looks like it has room it does not. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
c115681259 |
Meter a project nobody set limits on
Unlimited was the default. Creating a project without limits is the easy path and the common one — the "default" project on this cluster is one, and the person using it is metered by nothing at all. The first sign of that is the bill or the outage. auth.default_rpm and default_tpm now apply to a key no scope gives a limit to. Zero keeps the old behaviour, which is still a reasonable choice; the point is that it becomes a choice rather than an omission. Applied after the chain rather than folded in as its widest scope, because a default is a fallback and not a ceiling: a project deliberately given 600 rpm must keep it, and tightening would silently cap it at the default. An explicit limit wins in both directions. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
db448a9e87 |
Stop using a liveness timeout as a generation budget
response_header sounds like a check that the endpoint is alive, and for a streaming request it is: headers arrive before generation starts. For a non-streaming request the engine sends nothing until the completion is finished, so the same setting is the total generation budget wearing a liveness timeout's name. At 60s that was invisible on GPUs and a hard cap of roughly a hundred tokens on qwen2.5-coder-14b at 1.7 tokens a second. A request for 120 tokens failed at exactly one minute, and neither the setting's name nor the error said why. Two transports now: the short header timeout for streaming, where it still catches a sick endpoint, and a generation budget for non-streaming, defaulting to ten minutes. One number could not mean both things. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
082d52bc97 |
Stop shipping a placeholder that looks like a value, and say what is served
A user copied the curl from the profile page and sent it as it stood. Every other field in that snippet is filled in for them — the base URL, the key they had just been issued — so "model": "MODEL" reads as a value rather than a blank, and they got: no endpoint serves "MODEL" which is true and useless. It reads the same whether the name was a typo, a placeholder left in from the documentation, or a real outage, and it never says what would have worked. The message now lists what is being served, capped at ten with a count for the rest, and says plainly when nothing is. That list is what /v1/models already returns to the same caller, so it discloses nothing new. The profile page's example now names a model that is actually running, real ones before simulated — the point of an example someone can run is that it runs, and sending a first request to the sim engine would answer in Greek letters. The landing and claim pages keep a placeholder, because they are served without a key and deliberately say nothing about what is here; theirs is <model-name>, which cannot be mistaken for a value, with a line saying where to get the real one. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
a075ff4120 |
Add approximate prefix routing, and find out it did nothing
Tier 1 of plan §7.5: a radix tree of request prefixes that estimates which replica has already prefilled one. Bytes, not tokens — needing the engine's exact tokenizer is what makes tier 2 a separate project. It went in inert, and the decision metric is what caught it: 144 lookups, zero hits. The cause was a rule I had written and tested for. A node's label is the first request that created it, so the second request for the same system prompt diverges in its last few bytes — a new question after the same preamble, the single most common shape there is. Requiring the whole label to match threw away the 700 bytes they shared. What matters is the shared head, because that is what the engine cached, and a partial label match now counts. Two unit tests asserted the wrong rule and have been inverted. With that fixed, measured end to end against engines whose caches are too small for the working set: 22.5% cache hits without, 81.7% with, and the breakdown shows the misses are exactly the first round, when the tree is empty. The scenario matters as much as the number. With a handful of prompts and a large cache, scattering is free — every replica ends up holding everything — and prefix routing can only add constraint. The first version of the test measured that case and showed a loss, which was a true statement about a situation the feature is not for. Two things keep it from being the disaster prefix routing usually is. The imbalance guard, which needs both an absolute and a relative gap before it fires, because either alone misfires — absolute on an idle cluster, relative on a busy one. And it is a scorer rather than a filter: affinity is a vote the queue and inflight scorers can outvote, not a rule. The tree records the replica the picker actually chose, not the one the scorer proposed, and a node prefers the replica it has seen most rather than most recently — a count is stable under a randomizing picker, where recency just chases whatever the picker last did. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
e519dc587c |
Serve the cluster dashboard over the web, without serving pprof with it
Reaching it meant an SSH tunnel, because the page lived on the admin listener and that listener is bound to loopback. Opening the port was never the way to fix that: it also serves pprof, and pprof can dump the process heap, where every API key sits in plaintext. Exposing the port would have been exposing the key store. So the page moves rather than the port. The same dashboard is now mounted at /admin on the client-facing port, behind the session and CSRF machinery that already guards /profile, gated on a flag on the account. The admin listener keeps pprof and metrics and stays on loopback. One bit, not a role system: it grants looking. Everything that changes the cluster or issues a credential stays on the CLI, where it needs a shell rather than a session — which keeps the worst case of a stolen admin cookie to "saw the cluster" rather than "drained your fleet". Someone without the flag gets 404, not 403. A 403 confirms the page is there and that admin accounts exist here, which is free reconnaissance; 404 is what every other unknown path returns. The profile page does not show a link to a door the visitor cannot open. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
216fc9bb03 |
Let people sign up, be approved, and issue their own keys
Every key needed an operator with a shell. This adds the login system that made that necessary, which is the thing I argued against building until it was asked for — so it is built as if it will be attacked, because a public login form is. Signing up produces an account that can do nothing. Approval is what makes it work and stays on the CLI: having a shell on the control plane is what makes someone an administrator, and that is a smaller thing to get right than roles and an admin UI that mints credentials. The details that matter: Passwords are argon2id, where a slow hash is correct — the input is chosen by a human and has a dictionary, which is the opposite of an API key. Both kinds of authentication now live in this codebase and they are in separate packages so neither set of assumptions leaks into the other. Length is the only rule: composition rules push people towards Password1! and cost more entropy than they buy. Signup never says whether an address already has an account, and sign-in answers the same way for a wrong password and a missing account — verifying against a dummy hash when there is no user, so a stopwatch cannot enumerate accounts. Account state is checked after the password, not before, so guessing an address reveals nothing about it. Guessing is bounded per address rather than per IP: an attacker has many addresses to come from and one to guess against, and limiting by IP locks out an office behind one NAT. Sessions are server-side, so signing out and suspending take effect immediately rather than whenever a token expires; suspension is checked in the same query that resolves the session, because a second round trip is a check somebody eventually forgets. Every state-changing form carries a CSRF token verified against a hash in the session — a cookie authenticates the browser, not the page that asked. Key ownership is enforced in the UPDATE rather than by reading first, so a guessed key id from another account changes nothing. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
8d35faf6f8 |
Give the landing page somewhere to send people
The page explained the API, said keys come from an operator, and left the reader there. Someone who reaches the address without a key had no route to getting one, which is where onboarding stopped. `landing.contact` is that route, because the gateway cannot guess who to ask. An address becomes a mailto link, an http(s) URL stays a link, and anything else — a channel, a queue, a person — is shown as text. Other schemes are never linked: this string comes from configuration, configuration is not always written by whoever runs the gateway, and a javascript: href on a page served to every visitor is a short path to a stored XSS. Escaping the text does not make a scheme safe. Unconfigured, it now says something rather than nothing, and the page explains that a key arrives as a one-time link so the reader knows what to expect before it lands. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
0b93fb2883 |
Enforce budgets and rate limits, and write usage off the request path
The second half of phase 5. A key now has a cost, a quota and a bill. Rate limits use a sliding window rather than a fixed one. A fixed window lets a caller send its whole minute's allowance in the last second of one window and again in the first second of the next, so the observed rate is twice the configured limit exactly when the system is least able to take it. Checking and charging are one operation, or two concurrent requests both see room and both take it. Token limits are checked against an estimate, because the real count only exists once the request has run; the difference is charged afterwards, so a caller who consistently underestimates is still bounded, one window late. A request with no max_tokens gets a modest assumption rather than zero — assuming zero would let an unbounded request through every token limit. Limits are checked before admission, not after: a request over its quota should be refused rather than queued, where it would occupy a band's capacity to no purpose. All refusals are 429, but a spent budget carries no Retry-After because waiting does not help until the period rolls over, and saying otherwise turns one client into a retry loop. Usage goes to a buffered channel and is written in batches. Record never blocks: if the buffer fills — a database stalled long enough to lose eight thousand records — records are dropped and counted, because losing accounting is bad and turning a stalled database into an outage is worse. A clean shutdown drains what is queued; those are requests that were already served. Failures are logged at error, since silently losing billing data is the kind of thing discovered at the end of a month. Requests are accounted whatever their outcome. A request that used a GPU and then failed still used it, and a key that could spend nothing by failing would be a way around a budget. Budgets are counted in memory and restored from the store at startup, so a restart does not hand every key a fresh allowance. The budget period travels with the reservation rather than being re-derived, because a monthly budget credited to a daily counter is a budget that never binds. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
45c8cd23a3 |
Close the gateway: API keys, tenancy and model allowlists
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> |
||
|
|
501db3d3e8 |
Add the llama.cpp engine, and let a profile ask for no GPU
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> |
||
|
|
2373726efd |
Agent stream: connect the fleet to the control plane
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> |
||
|
|
c1b9ea1bc2 |
Phase 3 (3/3): wire the control plane to the router
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> |
||
|
|
dc38dd6096 |
Phase 1.5: admission control
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> |
||
|
|
a3f71aa5ee |
Phase 1: the router serves traffic
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> |