* feat: add token usage tracking to AI agent output
Add TokenUsage struct to track input/output/cache tokens from AI providers.
Currently implemented for Bedrock provider, with infrastructure in place
for other providers. Usage is included in the AI agent result alongside
output and messages when available.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add token usage extraction for Anthropic provider
Extract usage from message_delta SSE event and convert to TokenUsage.
Includes input_tokens, output_tokens, cache_read_input_tokens, and
cache_creation_input_tokens (mapped to cache_write_input_tokens).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add token usage extraction for Google AI/Gemini provider
Extract usage from usageMetadata in Gemini SSE events and convert to TokenUsage.
Maps promptTokenCount -> input_tokens, candidatesTokenCount -> output_tokens,
totalTokenCount -> total_tokens.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add token usage extraction for OpenAI Responses API provider
Extract usage from response.completed SSE event and convert to TokenUsage.
Maps input_tokens, output_tokens, and total_tokens directly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add token usage extraction for Azure OpenAI / Chat Completions API
Add stream_options.include_usage to request and parse usage from final
SSE chunk for providers using the standard OpenAI Chat Completions API
(Azure OpenAI, Mistral, DeepSeek, Groq, TogetherAI, CustomAI).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: cleanup token usage tracking - remove unused Image usage field and accumulate across iterations
- Remove unused `usage` field from ParsedResponse::Image variant
- Add TokenUsage::accumulate() method to sum usage across agent iterations
- Accumulate input/output/total/cache tokens instead of replacing with last iteration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: remove verbose debug logging from AI providers
Remove tracing::info!("[debug] ...") statements that were too verbose
for production. These logged raw events on every streaming event.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add retry mechanism for OpenAI-compatible providers without stream_options support
Some OpenAI-compatible providers don't support the stream_options parameter
for usage tracking. This adds a retry mechanism that:
- First attempts the request with stream_options.include_usage
- If it fails with 400 and error mentions stream_options/include_usage,
automatically retries without the parameter
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: remove unnecessary text parsing overhead in image response handlers
Revert debugging changes that read response as text before parsing JSON.
Using response.json() directly is more efficient.
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: centralize TokenUsage conversion with constructor methods
Add new(), from_input_output(), and with_cache() constructors to TokenUsage
to eliminate duplicate conversion logic across providers. Also fixes potential
truncation in Bedrock cache token conversion by using i32::try_from with
fallback to i32::MAX.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: simplify Anthropic usage extraction and add Default derive
- Use idiomatic `if let` pattern instead of `is_some()` check for usage extraction
- Add Default derive to OpenAIChatUsage for consistency with other usage structs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: use saturating_add to prevent overflow in token accumulation
In long-running agents with many iterations, token counts could
potentially overflow. Using saturating_add ensures values cap at
i32::MAX instead of wrapping around.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* better claude
* nit
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: forward teams error to client
* chore: update ee-repo-ref to 9a3d71f2c6a41ed4d17111a8c05d8e1d4933898d
This commit updates the EE repository reference after PR #400 was merged in windmill-ee-private.
Previous ee-repo-ref: 25d35a8de1cd70e281dc876e51cd30402580b5c0
New ee-repo-ref: 9a3d71f2c6a41ed4d17111a8c05d8e1d4933898d
Automated by sync-ee-ref workflow.
* fix
* fix
* fix
* al
* sqlx
* sqlx
* all
* all
---------
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
- Add AgentConfig struct to validate required env vars on startup
- Change build_agent_http_client to require explicit token and URL
- Remove DEFAULT_BASE_INTERNAL_URL fallback (no more silent localhost:8000)
- Exit immediately if agent cannot connect to server on initial load
- Update integration tests to use dynamic port for BASE_INTERNAL_URL
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: Raw apps deployment UI (and merge UI)
* Add folders and resource tpyes to merge UI
* claude first pass on adding the new arg for h_deploy_metadata
* Add missing argument to handle_deployment_metadata in all its calls
* Add support for folders and resource types in merge UI
* Update eereporef for CI
* Update ee repo
* Add migration to reset cached diff with potential artifacts
* fix type in frontend
* Preapare sqlx
* Remove unused import and logs
* update ee-repo
* Update eerepo
* chore: update ee-repo-ref to aca38475afd2cafaf63f4bbffc65be9437d57d86
This commit updates the EE repository reference after PR #397 was merged in windmill-ee-private.
Previous ee-repo-ref: 19c64cf8c61d83f45047b37660054b29658cd403
New ee-repo-ref: aca38475afd2cafaf63f4bbffc65be9437d57d86
Automated by sync-ee-ref workflow.
* Make integration test for workspace comparisons
* Update SQLx metadata
---------
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* better claude
* refactor: remove seed parameter from AI chat completions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
The uuid-ossp extension was created in the first migration but never
actually used - the codebase uses gen_random_uuid() which is built-in
to PostgreSQL 13+. This allows Windmill to run on AWS RDS where
application users may not have CREATE SCHEMA privileges.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: workspace dedicated workers
* ref
* chore: update ee-repo-ref to a18ac31062ac092cb9a5fc87629e217d97f4911d
This commit updates the EE repository reference after PR #398 was merged in windmill-ee-private.
Previous ee-repo-ref: 98cfe3fef764d9d815d326d5056c734a03689d33
New ee-repo-ref: a18ac31062ac092cb9a5fc87629e217d97f4911d
Automated by sync-ee-ref workflow.
* fix(frontend): workspace script in flow steps
---------
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* fix(cli): revert findCodebase relative_path check that broke ../shared codebases
The previous change added a check to ensure script paths start with the
codebase's relative_path. However, this broke cases where relative_path
uses parent directory references (e.g., "../shared") because:
1. path.join normalizes paths, so "/project/../shared/f/script.ts" becomes
"/shared/f/script.ts"
2. FSFSElement strips the cwd prefix, resulting in "f/script.ts"
3. The check "f/script.ts".startsWith("../shared/") failed
The original behavior was correct - relative_path indicates where to find
codebase files, while includes/excludes patterns match against the normalized
paths that get passed during sync.
Fixes regression reported in #7729 comments.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test(cli): add preview test for codebase with imports
Tests that codebase bundling correctly includes imported modules,
which is the key functionality needed for ../shared codebases.
The test creates a helper module and a main script that imports
from it, then verifies the bundled script executes correctly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add "Mutex Selection in Async Code" section explaining when to use
std::sync::Mutex vs tokio::sync::Mutex based on official Tokio docs.
std::sync::Mutex is preferred for data protection as it's faster;
tokio::sync::Mutex only needed when holding locks across .await points.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: do not quit indexer when receiving handoff during pull
* update
* Add correct return type
* update ee-repo-ref [CI only]
* chore: update ee-repo-ref to c05572e93739e2697ab310d87efe2744cd0e1aaf
This commit updates the EE repository reference after PR #394 was merged in windmill-ee-private.
Previous ee-repo-ref: 4358aa9c5b3b38ba74d7ea52cafd49899d338a07
New ee-repo-ref: c05572e93739e2697ab310d87efe2744cd0e1aaf
Automated by sync-ee-ref workflow.
---------
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* fix: handle empty strings in AI resource fields via serde deserializer
Add `empty_string_as_none` deserializer that converts empty strings to None
during deserialization. Applied to base_url, api_key, region, and AWS
credential fields in AIStandardResource and ProviderResource.
This fixes the "relative URL without a base" error when creating Anthropic
resources with empty base_url fields.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* nit
* nit
* nit
* cleaning
* cleaning
* cleaning
* cleaning
* fix: apply empty_string_as_none deserializer to api_key field
Consistent with other fields in ProviderResource, empty strings are now
deserialized as None for the api_key field.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Enable running the dev command from any directory by specifying the
target .raw_app folder as an argument. Workspace resolution and
authentication still happen from the original cwd to find wmill.yaml.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
QuickJS was missing an explicit memory limit, unlike deno_core which has
a 128MB heap limit. This adds a 32MB limit appropriate for lightweight
flow expression evaluation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, accessing a non-existent step via results.nonexistent would
throw an error. This fix makes both Deno Core and QuickJS return null
instead, enabling patterns like:
- results.nonexistent ?? 'default'
- results.nonexistent?.value ?? 'default'
The fix was applied to:
- js_eval.rs: handle_full_regex fast-path now uses .ok().flatten()
- js_eval_quickjs.rs: fallback path now uses .ok().unwrap_or(null)
Added flow engine test to verify the behavior.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add QuickJS as alternative JS engine for flow expression evaluation
Add rquickjs as an optional alternative to deno_core for evaluating
JavaScript expressions in flow transformations. QuickJS offers ~8-16x
faster startup times for simple expressions, making it ideal for
evaluating many small expressions in flows.
Key changes:
- Add new `quickjs` feature flag for windmill-worker
- Implement js_eval_quickjs.rs with true async Rust callbacks for
variable(), resource(), and results.xxx access (no pre-fetching)
- Share expression transformation logic (replace_with_await,
replace_with_await_result) between both implementations
- Add USE_QUICKJS_FOR_FLOW_EVAL env var to switch engines at runtime
- When only quickjs feature is enabled (no deno_core), QuickJS is
automatically used
- Add comprehensive parity tests comparing QuickJS and deno_core output
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* all
* quickjs
* quickjs
* all
* all
* all
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Fix standalone bundle path lookup in worker to not add redundant file
extension (the path already contains .tar/.esm suffixes from the API)
- Fix CLI preview tar bundle handling to preserve binary data correctly
(was using btoa(blob.text()) which corrupted binary tar data)
- Add integration tests for script/flow preview commands covering:
- Regular scripts (non-codebase)
- Codebase scripts (CJS and ESM formats)
- Codebase scripts with assets (tar bundles)
- Flow preview
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add `wmill script preview <path> [--data <json>]` command to test scripts against remote workspace without deploying
- Add `wmill flow preview <path> [--data <json>]` command to test flows against remote workspace without deploying
- Support codebase scripts with automatic bundling via esbuild
- Add `--silent` flag to suppress logs and only output final result
- Fix `findCodebase` to properly check if path is within codebase relative_path before pattern matching
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Previously, getCurrentGitBranch() was called inside loops for every
file processed during sync pull/push operations. For workspaces with
1900+ files, this spawned thousands of git subprocesses, causing a ~2x
performance regression.
This fix caches the git branch at the start of:
- elementsToMap() for pull operations
- push() for push operations
Expected improvement: ~3.2s -> ~1.6s for large workspaces.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The dnt polyfill's import-meta-ponyfill doesn't resolve symlinks when
comparing process.argv[1] with import.meta.url. When npm creates a
symlink for the `wmill` bin (e.g., /usr/bin/wmill -> .../main.js),
the paths don't match and isMain() incorrectly returns false, causing
the CLI to silently exit without running.
This fix resolves symlinks using fs.realpathSync() before comparison,
ensuring the CLI works correctly when invoked via npm-installed symlinks.
Tested with Node.js 20 and 25.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove service re-exports from client.ts
- Build default export explicitly in index.ts
- Use unbundled ESM output
- Add sideEffects: false
Results: ~900 bytes vs 91KB for simple imports
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
tsdown's bundled .d.ts output uses namespace declarations that reference
forward-declared types, which breaks Monaco/ATA type acquisition.
Switch to:
- tsdown for JS bundles (ESM + CJS) with --no-dts
- tsc with emitDeclarationOnly for clean individual .d.ts files
This restores the type structure from 1.617.0 which worked correctly
with Monaco editor's automatic type acquisition.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
tsdown generates "export { X as default }" which doesn't work properly
with Monaco's TypeScript type acquisition. This post-processes the .d.ts
files to use "export default X" instead.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enables `import wmill from "windmill-client"` syntax which was previously
broken due to missing default export in the generated ESM bundle.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When creating an Anthropic resource with "standard platform", the resource
JSON may contain `"base_url": ""` rather than omitting the field. Serde
deserializes this as `Some("")`, which bypassed the fallback logic and
caused "relative URL without a base" errors.
Similarly, AWS Bedrock with an empty region string would produce an
invalid URL like `https://bedrock-runtime..amazonaws.com`.
Filter out empty strings when checking for custom base_url and region
values, allowing the default URLs to be used correctly.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: typescript client esm build
* fix: add --dts flag and restore tsconfig options for typescript client ESM build
- Add --dts flag to tsdown commands to generate declaration files
- Restore outDir in tsconfig.json for compatibility
- Restore forceConsistentCasingInFileNames for case-sensitive systems
- Update README_DEV.md to reflect new tsdown build process
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Ruben Fiszel
centdix
Alexander Petric
wendrul
hugocasa
Pyra
Diego Imbert
Mark Lai
Guilhem