chore(release): v0.8.0

[GrowthX-Team]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and publish to npm yourself or setup this action to publish automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@outputai/llm@0.8.0

Minor Changes

• ae5bab4: Add per-message provider options to .prompt files via messageOptions.

  • Define named messageOptions sets in front matter and attach them to message blocks with options="<name>" (e.g. <system options="cached">); each set is a provider-namespaced providerOptions object merged onto that message.
  • Enables Anthropic prompt caching ({ anthropic: { cacheControl: { type: ephemeral } } }) and any other per-message provider option, on any provider.
  • Cost tracking now reports cached input tokens (input_cached) even for models whose pricing record lacks a cache_read rate, so cache savings are visible in usage aggregations instead of silently disappearing.

Patch Changes

• Updated dependencies [306c136]
  • @outputai/core@0.8.0

@outputai/cli@0.8.0

Patch Changes

• d67ad85: Faster CLI startup: ship oclif.manifest.json in the published package so only the invoked command module is loaded (instead of importing every command on every invocation), move the update check off the critical path (the init hook now only reads the local cache and refreshes it via a detached background process with a 5s registry timeout, instead of awaiting an unbounded npm view subprocess), and load undici only when a proxy env var is configured.

• bd6bd49: workflow cost now calculates costs from the trace events themselves (the as-charged "Original" cost) and applies costs.yml as an override layer (the "Adjusted" cost), displaying both per model and per host. This fixes models with no costs.yml entry (e.g. gpt-5.5) and HTTP hosts (e.g. api.exa.ai, api.firecrawl.dev) previously reporting $0, and surfaces where the configured costs.yml rate diverges from what was actually charged. The bottom line shows the adjusted total with the as-charged total alongside.

  Costs come exclusively from trace cost attributes: LLM nodes with an llm:usage event and HTTP calls with an http:request:cost event are counted as-charged (even on error responses — the event proves a charge); calls without events are not priced. Traces from SDK versions that predate cost attributes (< 0.5) report no costs. Only exact (computed) recomputes override an event cost — estimates and failed recomputes never do, and a configured $0 price is now honored. Body-dependent costs.yml service rules require traces recorded with OUTPUT_TRACE_HTTP_VERBOSE=true (the dev default).

  --format json field changes (the report shape changed; update any scripts parsing it): llmTotalCost → llmOriginalCost/llmAdjustedCost; services[]/serviceTotalCost → httpCosts[] (grouped by host) with httpOriginalCost/httpAdjustedCost; unknownModels removed; per-call cost/warning → originalCost/adjustedCost; new originalTotalCost; totalCost is now the adjusted total.

• Updated dependencies [ae5bab4]

  • @outputai/llm@0.8.0
  • @outputai/credentials@0.8.0
  • @outputai/evals@0.8.0

@outputai/core@0.8.0

Patch Changes

• 306c136: Fixed missing eventDate fields on hook types.

@outputai/credentials@0.8.0

Patch Changes

• Updated dependencies [306c136]
  • @outputai/core@0.8.0

@outputai/evals@0.8.0

Patch Changes

• Updated dependencies [306c136]
• Updated dependencies [ae5bab4]
  • @outputai/core@0.8.0
  • @outputai/llm@0.8.0

@outputai/output@0.8.0

Patch Changes

• Updated dependencies [d67ad85]
• Updated dependencies [bd6bd49]
• Updated dependencies [306c136]
• Updated dependencies [ae5bab4]
  • @outputai/cli@0.8.0
  • @outputai/core@0.8.0
  • @outputai/llm@0.8.0
  • @outputai/credentials@0.8.0
  • @outputai/evals@0.8.0
  • @outputai/http@0.8.0

@outputai/http@0.8.0

Patch Changes

• Updated dependencies [306c136]
  • @outputai/core@0.8.0

output-api@0.8.0

Patch Changes

• d67ad85: getWorkflowResult now fetches only the first history event (WorkflowExecutionStarted) to extract the workflow input, instead of paging through the full event history. Makes input extraction on the result endpoints (/workflow/:id/result and /workflow/:id/runs/:rid/result) O(1) regardless of history size.
• 2a4105c: Expose structured workflow failure details (failure object with message, type, retryable, and a sanitized cause chain) in /workflow/run and /workflow/:id/result responses, alongside the existing error string. Also log Temporal/gRPC client errors with full nested context (cause chain, gRPC code/details, redacted metadata keys, workflowId/runId/taskQueue/query) while keeping client-facing HTTP responses sanitized.