The global variable requestCounter is not thread-safe. In a concurrent environment like a web server, this will lead to race conditions when multiple requests are processed simultaneously. Consider using sync/atomic to increment the counter safely.

The increment operation on requestCounter is not atomic. Use atomic.AddUint64(&requestCounter, 1) to ensure thread safety.

The read operation on requestCounter is not atomic. Use atomic.LoadUint64(&requestCounter) to ensure thread safety.

Preserve scalar system prompts during Claude injection

This rewrite path is entered whenever a top-level system key exists, but injectIntoClaudeSystem only preserves existing entries by iterating system.ForEach and never normalizes scalar system values. The repo still supports string system prompts elsewhere (e.g. Claude executor handles system strings), so payloads like {"system":"...","messages":[...]} can have their original system instruction dropped or reshaped when temporal injection runs, changing model behavior.

Useful? React with 👍 / 👎.

Avoid prepending temporal message before Imagen prompt parse

Prepending the temporal message at messages[0] breaks the Imagen compatibility path that derives prompt text from the first non-empty messages.#.content entry (internal/runtime/executor/gemini_vertex_executor.go loop at lines 125-130). After this change, messages-format Imagen requests can use the injected temporal block as the prompt instead of the user’s prompt, producing incorrect image generations.

Useful? React with 👍 / 👎.

Inject temporal tags for Gemini-style payloads

InjectIntoPayload only handles top-level system and messages, then returns the payload unchanged for other schemas. Native Gemini/Vertex requests use contents payloads, so this path skips temporal injection entirely and anti-drift is not applied on those provider routes, despite this change advertising provider-wide request injection.

Useful? React with 👍 / 👎.

Report health from all registered models

GetModelsHealth starts from GetAvailableModels("openai"), which excludes models whose clients are fully suspended/unavailable. That causes /models/health to omit exactly the models operators need to debug during outages, contradicting the handler’s stated goal of reporting all registered models.

Useful? React with 👍 / 👎.

Resolve model alias before deciding temporal injection

This injects temporal text based on req.Model before alias/model-pool resolution, so the image-model safeguard can be bypassed when users call an aliased route model (for example, img) that later resolves to an Imagen upstream model. In that case InjectIntoPayload sees a non-image alias and prepends a system message, then executeMixedOnce rewrites to the Imagen model (execReq.Model = upstreamModel), and Imagen prompt extraction can consume the injected block instead of the user prompt. Fresh evidence: alias remapping happens only after this line, so the prior Imagen fix does not apply to aliased image routes.

Useful? React with 👍 / 👎.

Define newly referenced OpenRouter registry functions

This change introduces calls to registry.BuildModelSources, registry.GetOpenRouterLastRefresh, registry.TriggerOpenRouterRefresh, and registry.StartOpenRouterEnrichment, but no corresponding definitions are added in the internal/registry package. That leaves these references unresolved at build time, so server/management packages cannot compile until the symbols are implemented (or the calls are removed).

Useful? React with 👍 / 👎.

Inject temporal tags for OpenAI Responses payloads

InjectIntoPayload only injects when a top-level system or messages field is present, and otherwise returns the body unchanged. Requests sent through /v1/responses use the Responses schema (input/instructions) and are forwarded as-is, so temporal anti-drift is skipped for that endpoint family despite this feature being applied in the central conductor path.

Useful? React with 👍 / 👎.

Update registry entries instead of cloned model info

enrichModelsFromOpenRouter calls GetModelInfo and assigns info.ContextLength, but GetModelInfo returns a cloned ModelInfo, so this write is discarded and never updates r.models. That makes enrichment effectively a no-op even though enrichedCount is incremented and logs say models were enriched, leaving downstream model metadata unchanged.

Useful? React with 👍 / 👎.

Return true enriched count in refresh response

RefreshModels publishes enriched_count from TriggerOpenRouterRefresh, but that function returns the size of the OpenRouter cache (len(contextLength)), not how many registered models were enriched in this refresh. This can report misleadingly large counts (or wrong error semantics when cache is empty due fetch failure), so operators cannot trust the endpoint output.

Useful? React with 👍 / 👎.

Fall back to temporal defaults when config omits section

temporalConfig() returns cfg.Temporal whenever a runtime config is loaded, but Config.Temporal.Enabled defaults to false when the temporal block is absent in YAML. Because SetConfig always stores a non-nil config, ShouldInject sees Enabled=false and skips injection for all normal deployments unless users explicitly add temporal.enabled: true, which silently disables the feature this commit introduces.

Useful? React with 👍 / 👎.

Apply temporal injection in CountTokens path

Temporal rewriting is added for Execute/ExecuteStream here, but executeCountMixedOnce still sends the original payload to CountTokens. Endpoints that preflight with token-count APIs (for example Claude/Gemini count routes via ExecuteCountWithAuthManager) will undercount because the injected temporal system block is missing there, so a request can pass counting and then fail real execution with token/context limits.

Useful? React with 👍 / 👎.

Merge temporal defaults when config block is partially set

temporalConfig() returns *cfg.Temporal as-is whenever the block exists, so omitted YAML fields keep Go zero-values. A config like temporal: { inject_interval: 5 } leaves Enabled=false, causing ShouldInject to skip all requests even though defaults are documented as enabled-by-default; this silently disables the feature for partial configs instead of applying defaults plus overrides.

Useful? React with 👍 / 👎.

Cache OpenRouter source using local model IDs

The enrichment cache stores keys from the OpenRouter response (openRouterContextLengths), but source lookup later is done with local registry IDs via GetOpenRouterContextLengthSource(modelID) in BuildModelSources. For non-exact matches (the same function explicitly supports cases like local gemini-3.1-pro matched from provider-prefixed IDs), source attribution will miss and /models/health reports provider/static even when context length came from OpenRouter.

Useful? React with 👍 / 👎.

Include unavailable models in enrichment pass

The enrichment loop uses GetAvailableModels("openai"), which excludes models whose clients are currently suspended/unavailable, but this function is intended to enrich registered models lacking context_length. During outages or quota suspension, those models are skipped entirely and remain unenriched until they become available again, undermining the management health metadata this change introduces.

Useful? React with 👍 / 👎.

Avoid double-counting temporal interval in Antigravity paths

The Antigravity executor calls ShouldInject again after signature validation even though the conductor already evaluated it for the same outbound attempt, and req.Payload is reset to originalPayload before this second check. That means interval mode increments the global counter twice per Antigravity request; for example, with inject_interval: 2, the second check is always true so Antigravity requests are injected every time instead of every second request, and other interval values are similarly phase-shifted.

Useful? React with 👍 / 👎.