mirror of
https://github.com/windmill-labs/windmill.git
synced 2026-08-18 08:01:26 +00:00
main
27 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 hugocasa
|
dae7c49f21 |
test(git-sync): cover fork-of-dev-workspace branch naming and routing (#10231)
* test(git-sync): cover fork-of-dev-workspace branch naming and routing A throwaway fork of a dev workspace pushes to `wm-fork/<tracked>/<id>` (the tracked branch, not the dev's label), and the root's `sync_forks` poller enumerates `wm-fork/<tracked>/*` and routes commits on that branch into the nested fork through the root. This was twice assumed to instead live on `wm-fork/<dev-label>/<id>` and therefore never be collected/reconciled; these tests pin the real behavior. - CLI unit: `computeGitSyncDeployBranch` for a fork whose parent is a dev workspace resolves to `wm-fork/main/<id>`, explicitly not `wm-fork/dev/<id>`. - git-sync E2E: fork a dev workspace, assert the created branch is `wm-fork/main/<id>` (not `wm-fork/dev/*`), then assert a commit on it deploys into the fork via the root's sync_forks poller while the root is untouched. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(git-sync): reconcile single-dev-per-root in fork-of-dev e2e The root workspace allows only one dev workspace, and a sibling test leaves one attached, so attach_dev_workspace failed with "already has a dev workspace". Detach any pre-existing dev before attaching, and detach ours via addCleanup so the test doesn't leak its own. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref to aaa6cb89b05b76139252c64f057e53b94d12ac60 This commit updates the EE repository reference after PR #680 was merged in windmill-ee-private. Previous ee-repo-ref: 4c08634af953db5c1125b1fb03f5af211fe21db3 New ee-repo-ref: aaa6cb89b05b76139252c64f057e53b94d12ac60 Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
hugocasa
|
51d8db6602 |
feat: automatic git-to-windmill sync (polling, webhooks, in-app PRs + checks) (#9552)
* docs: add design doc for automatic git-to-windmill pull sync
* docs: add migration plan and implementation phases to git-sync pull design
* feat(git-sync): add auto_pull settings schema and pull enqueue primitive
Adds AutoPullSettings/AutoPullMode/AutoPullStatus on GitRepositorySettings
(workspace_settings.git_sync JSONB), the GIT_SYNC_PULL_SCRIPT_PATH constant,
and should_pull/effective_poll_interval_s helpers with unit tests. Exports the
EE enqueue_git_pull_job primitive. Foundation for repo→Windmill auto-pull.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): poll repos and auto-pull new commits into the workspace
Phase 1 of automatic repo → Windmill sync. A monitor task (EE-licensed,
single-replica via advisory lock) git ls-remotes each auto-pull-enabled
repository ~every minute and enqueues a pull when the tracked branch moves,
reusing the {workspace_id}:git_sync concurrency key so pulls serialize with
in-flight push commits.
- windmill-store: background (no-authed) resolver get_git_repo_head_for_autopull
that resolves the repo resource (incl. $var: refs) and ls-remotes; GitHub-App
repos are skipped here and will sync via webhooks (phase 2).
- monitor.rs: poll/reconcile/persist with optimistic sha advance and failure
status; targeted jsonb update so concurrent settings edits aren't clobbered.
- edit_git_sync_repository: preserve server-owned auto_pull state on UI save.
- openapi: AutoPullSettings/AutoPullMode/AutoPullStatus + auto_pull field.
- frontend: per-repo "Automatically deploy changes from Git" toggle with last
sync status; demote the GitHub Actions link to an advanced CI option.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): wire webhook lifecycle + receiver; share reconcile logic
OSS side of phase 2 auto-pull webhooks:
- edit_git_sync_repository creates/removes the repo webhook on save (EE-gated,
best-effort → falls back to polling).
- monitor poller now delegates to the shared windmill_git_sync reconcile/persist
helpers (also used by the webhook receiver), removing duplicated logic.
- export the shared reconcile/persist/failure helpers; bump EE ref.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(git-sync): bump EE ref for phase 3 in-app PR creation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): show webhook vs polling status on the auto-pull toggle
When a repo has an active webhook (auto_pull.webhook_id set), the status line
reads "instant via webhook"; otherwise it reads the ~1-minute polling cadence.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): post PR diff check on dry-run completion (phase 4)
Worker completion hook in process_completed_job: when a DeploymentCallback job
carrying the __git_sync_pr_check marker finishes, parse the dry-run SyncResponse
and patch the GitHub check run with the diff summary (success/neutral/failure).
Export enqueue_git_pull_dry_run; bump EE ref.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(git-sync): bump EE ref (drop unused GHES webhook_secret)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* revert(git-sync): defer phase 4 PR diff checks (OSS side)
Remove the worker completion hook that posted the PR check run, drop the
enqueue_git_pull_dry_run re-export and the orphaned sqlx cache, bump EE ref.
Phases 1-3 (polling, webhooks, in-app PR creation) are unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Revert "revert(git-sync): defer phase 4 PR diff checks (OSS side)"
This reverts commit
|
||
 centdix
|
b0ddcf31e4 |
ci: add path-gated AI agent + ai_evals smoke workflows (#9640)
* ci: add path-gated AI agent integration tests workflow Runs integration_tests/ai_agent_tests against real LLM providers (Anthropic/OpenAI/Google) only when AI-agent backend code or the tests change, since runs make paid LLM calls. Adds a conftest fixture that skips provider-parametrized cases whose API keys are absent, so CI exercises only the providers it has secrets for. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: add path-gated ai_evals global-mode smoke workflow Runs the global AI chat eval (global-test1) across one cheap model per provider (Anthropic/OpenAI/Google/DeepSeek) only when the eval harness or copilot chat code change, since runs make paid LLM calls. Builds Windmill CE from source as the AI proxy; global tools/drafts run in the Vitest bridge. Gates on the deterministic draft pipeline (run succeeded + produced a draft + used write_script), not the variable LLM judge score. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: run AI smokes on PR ready-for-review instead of every push Switch the pull_request trigger from `synchronize` (every commit) to `ready_for_review`, with a job guard skipping draft PRs, so the paid LLM runs only fire when a PR is marked ready to merge (plus push-to-main and manual dispatch). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai_evals): lazily load cli mode so non-cli evals skip the cli toolchain The entrypoint eagerly imported modes/cli, which pulls the wmill CLI guidance modules and their JSR deps (@cliffy/*). Global/flow/script/app runs then crashed with "Cannot find module '@cliffy/ansi/colors'" when the cli workspace deps were not installed. Import createCliModeRunner dynamically inside runCliBenchmark instead. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(ai_agent): raise low max_completion_tokens to OpenAI's 16 minimum OpenAI's /v1/responses rejects max_output_tokens < 16 with a 400, failing test_low_max_tokens for openai. 16 still exercises a truncated response. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: run ai_evals workflow on Node 22 for the frontend undici 8.x dep The Vitest bridge loads frontend/node_modules/undici@8.x, which requires Node >=22.19; Node 20 failed with "webidl.util.markAsUncloneable is not a function" when loading vitest.config.ts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai_evals): run frontend evals autonomously + give global-test1 more turns Frontend evals (flow/script/app/global) ran the production chat prompt, which assumes an interactive human — so cheaper models burned their turn budget asking for confirmation, waiting for approval, or presenting a plan, sometimes hitting maxTurns without producing a draft. Append a shared autonomy note in baseEvalRunner (the path all frontend modes share, mirroring cli mode): act directly on clear requests; only ask on genuinely ambiguous ones (preserving the askUserQuestion cases). Also raise global-test1's maxTurns 8 -> 10 so a model that over-explores still converges. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci(ai_evals): watch draft/prompt deps outside copilot/ The global eval runs production frontend code in-process, so the smoke's behavior depends on files outside frontend/src/lib/components/copilot/**: the draft model (userDraft.svelte.ts, userDraftDbSyncer.svelte.ts), script inference (infer.ts), and the chat system prompts ($system_prompts -> system_prompts/auto-generated). Add them to both push and PR path filters so a change there actually triggers the smoke that gates on draft production. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: skip direct provider tests without credentials * feat: add ai evals skip judge flag * fix: simplify ai evals ci gate * fix: simplify ai evals smoke gate * fix: handle ai eval workflow triggers --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
centdix
|
77d9a53423 |
fix: strip additionalProperties from google schemas (#8964)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> |
||
|
hugocasa
|
a1a73309fd |
refactor: remove force_branch from git sync settings (#8934)
* [ee] refactor: remove force_branch from git sync settings Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: update ee-repo-ref to 680885a4e8c8de5185650cddeb56b926e722718f This commit updates the EE repository reference after PR #549 was merged in windmill-ee-private. Previous ee-repo-ref: 37fe2e1286a162119df885062e50461400631850 New ee-repo-ref: 680885a4e8c8de5185650cddeb56b926e722718f Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
centdix
|
b1778272fc |
fix: clean ai memory and cache bedrock prompts (#8847)
* fix: avoid persisting system prompts in ai memory Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: keep ai memory cleanup write-side only Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat: add bedrock prompt caching for claude Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test: add bedrock memory regression Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: gate bedrock prompt caching by model id Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs: link bedrock caching allowlist source Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> |
||
|
centdix
|
e44504c6e9 |
feat: add PDF input support to AI agent (#8525)
* feat: add PDF input support to AI agent with user_attachments field Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test: add integration tests for PDF input and backward compat Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add ContentPart::File variant for PDF support across all providers Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor: address review feedback on PDF support - Extract parse_data_url_bytes and mime_to_document_format helpers in Bedrock - Add is_document_mime helper in ai_types for centralized MIME routing - Extract s3_object_to_content_part helper to deduplicate image_handler/openai - Rename AnthropicImageSource to AnthropicBase64Source - Derive Bedrock DocumentFormat from MIME type instead of hardcoding Pdf Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: merge user message and attachments into single message for Bedrock Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
 Ruben Fiszel
|
68fd900076 |
fix: use bookworm-based php image to fix glibc 2.38 incompatibility (#8381)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> |
||
|
hugocasa
|
d2b9799ac4 |
test: git sync E2E tests + auto-manage git sync script version (#8253)
* test: add E2E git sync integration tests with Gitea Add 7 end-to-end tests that verify the full git sync pipeline: deploy objects in Windmill → DeploymentCallback job runs hub sync script → correct files appear in a Gitea git repository. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: auto-manage git sync script version locked to Windmill release - Add LATEST_GIT_SYNC_SCRIPT_PATH constant as single source of truth - Backend auto-fills empty script_path with latest on save - New repos use empty script_path (auto-managed by backend) - Existing repos with pinned versions show warning with opt-in button - cache_hub_scripts always caches the latest constant - Rename hubPaths.json gitSync entries to deprecated_ prefix Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update ee-repo-ref.txt for git-sync-tests branch Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update ee-repo-ref.txt Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: remove upgrade_git_sync_script_paths from save path Empty script_path is now resolved to latest at job dispatch time in EE, not on save. Users opt in via the UI button. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: use Option<String> for git sync script_path None means auto-managed (uses LATEST_GIT_SYNC_SCRIPT_PATH), Some(path) means pinned to a specific script. Resolution happens at job dispatch time via effective_script_path(). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: separate git sync tests into dedicated CI workflow - Remove git_sync_test from default integration test suite - Move gitea service to dedicated docker-compose.git-sync.yml - Add run_git_sync.sh script - New workflow triggers on changes to git sync crate, hub paths, ee-repo-ref, or the test files themselves Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: add Rust integration tests for git sync filtering logic Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: run git sync E2E tests via cargo run instead of docker image Build from source and run Windmill directly, start Gitea as a standalone container. Tests run against localhost — no pre-built Docker image needed, works on PRs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add relevance check before running git sync E2E tests Only run the expensive build+test when actually relevant: - Direct git sync file changes: always run - ee-repo-ref.txt changed: check if EE diff touches windmill-git-sync/ - Unrelated changes to workspaces.rs or other files: skip Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: remove broad path triggers from git sync workflow Remove workspaces.rs and wmill_integration_test_utils.py from path triggers - they change too often for unrelated reasons. Keep only git-sync-specific paths + ee-repo-ref.txt (filtered by check-relevance). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: rewrite git sync E2E tests with full coverage and fix test infra Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: remove accidentally committed gen files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: remove unit/integration tests for git sync filtering (covered by E2E) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: use correct build features and pass license key to test step in CI Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add workflow_dispatch trigger to git sync test workflow Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Update commit reference in ee-repo-ref.txt * fix: update stats_oss stubs to match EE telemetry signature changes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: disable -D warnings for git sync e2e build step Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: allow test connection button in auto-managed git sync mode The test connection button was disabled and runTestJob() bailed out when script_path was unset. The test job uses a separate hub script (gitSyncTest), not the sync script, so the guard was wrong. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update ee-repo-ref to include auto-managed script_path fix Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: use full SHA in ee-repo-ref.txt Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: address PR review feedback - Initialize current_count before loop in wait_for_sync_jobs - Clean up temp directories in clone helpers with addCleanup - Fail CI startup steps if Gitea/Windmill never become ready - Assert exact job count in exclude_path test - Remove docs/git-sync-tests-plan.md (stale planning doc) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: remove orphaned git_sync.sql fixture No longer referenced after Rust integration tests were removed. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: assert old file removal in rename test Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update ee-repo-ref to 612d96a66f9d0cfdae335ef3eb4881f3444ce7cd This commit updates the EE repository reference after PR #442 was merged in windmill-ee-private. Previous ee-repo-ref: a05004a7c82f3d1ee5f6863bb9f5a33827d30032 New ee-repo-ref: 612d96a66f9d0cfdae335ef3eb4881f3444ce7cd Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
Ruben Fiszel
|
759eb68a7f |
use polling loop in schedule integration tests to avoid CI flakes (#8196)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
3c89c28e71 |
chore: fix flaky agent token test by not splitting on underscore (#8048)
Base64url encoding uses '_' as a valid character, so splitting the JWT token on '_' would intermittently break the JWT parsing when the encoded payload or signature contained underscores. Strip the known prefix instead. Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
centdix
|
d95e4db8f3 |
feat(ai): add AWS bedrock session token support (#7908)
* Add AWS Bedrock session token support in API and worker * Add Bedrock auth mode integration tests for AI agents * Split Bedrock integration test env vars for IAM and session creds * cleaning * Add masked Bedrock bearer-token debug info logs * Revert "Add masked Bedrock bearer-token debug info logs" This reverts commit 6b2fc5e7c2d5b1c6db81f416a4439941a084108c. * cleaning |
||
|
Ruben Fiszel
|
8220a0bd8d | nits | ||
|
Ruben Fiszel
|
60240bb54f | fix e2e | ||
|
centdix
|
18d85f1412 |
fix: remove $schema field from Google AI output schema requests (#7765)
* fix: remove $schema field from Google AI output schema requests Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test: add $schema field to all output schema integration tests Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: remove $schema field from Google AI tool parameter schemas Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test: add workspace script tool test for AI agents Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> |
||
 Pyra
|
d30ef89a6c |
feat(python): restart installation OOM (#7507)
* use tini with unshare to preserve signals (e.g oom) * fix ci * ci as nsjail * simplify * fix flaky go integration test * feat(python): restart installation OOM Signed-off-by: pyranota <pyra@duck.com> * follow ups Signed-off-by: pyranota <pyra@duck.com> * fix oom_score_adj Signed-off-by: pyranota <pyra@duck.com> --------- Signed-off-by: pyranota <pyra@duck.com> Co-authored-by: Alexander Petric <alex@windmill.dev> Co-authored-by: Alexander Petric <alpetric@users.noreply.github.com> |
||
|
centdix
|
8125036e9b |
fix(aiagent): fix memory with openai (#7506)
* add memory test * fix memory with openai |
||
|
hugocasa
|
f7085770c7 | fix(ci): increase integration test http client timeout for go test (#7498) | ||
|
centdix
|
eeb4feb13c |
chore(aiagent): better handling of schemas (#7488)
* better handling of schemas * add tests * better * add tests * handle allof |
||
|
centdix
|
f0361a027f | fix param for openai (#7483) | ||
 claude[bot]
|
6be060bea8 |
feat(ai): add websearch tool for AI agents (#7399)
* refactor(ai): use responses API for OpenAI/Azure, create 'other' provider for completion endpoint - Created new 'other.rs' provider using the OpenAI-compatible completion endpoint - Refactored 'openai.rs' to use the Responses API for both text and image output - Updated query_builder to route OpenAI/AzureOpenAI to OpenAIQueryBuilder - All other providers (Mistral, DeepSeek, Groq, etc.) now use OtherQueryBuilder - Updated OpenRouter to delegate to OtherQueryBuilder instead of OpenAIQueryBuilder This prepares the codebase for adding websearch tool support using the Responses API. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(ai): add websearch as AI agent tool type - Added WebsearchToolValue to ToolValue enum in flows.rs - Updated all pattern matches to handle websearch tool type - Added has_websearch parameter to run_agent function - Websearch tools don't require additional configuration This prepares the backend for provider-specific websearch implementations. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(frontend): add websearch as tool option in AI agent UI - Added WebsearchTool type and utility functions to agentToolUtils.ts - Added "Web Search" option in tool insertion menu (InsertModuleInner) - Updated NewAIToolNode to handle pickWebsearchTool event - Updated AIToolNode to render websearch tools properly - Updated FlowModuleSchemaMap to create websearch tools Users can now add websearch tools to AI agents through the UI. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(ai): implement websearch for OpenAI provider - Added has_websearch parameter to BuildRequestArgs - OpenAI provider now adds web_search tool to requests when enabled - Uses OpenAI Responses API web_search tool type - Websearch tool is added before other custom tools in the request Implements websearch functionality for OpenAI and Azure OpenAI providers. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(ai): implement websearch for Anthropic provider - Created anthropic.rs provider with native Anthropic API format - Added web_search tool to Anthropic requests when enabled - Anthropic uses /messages endpoint with x-api-key authentication - Updated query_builder to route Anthropic to new provider Implements websearch functionality for Anthropic Claude models. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(ai): implement websearch for Gemini/GoogleAI provider - GoogleAI now uses completion endpoint (other.rs) for text instead of responses API - Added Google Search grounding when websearch is enabled - Uses google_search_retrieval tool in request when has_websearch is true - Updated parse methods to use OtherQueryBuilder for completion endpoint Implements websearch functionality for Google Gemini models. Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * fix frontend * fix anthropic and openai * better for gemini * structured output * cleaning * fix validate tool * fixes * cleaning * cleaning * fix for openai * no responses api for azure * fixes * fix * add tests for ai agent * avoid panic * better tests * test user images * fix tool choice * always use streaming backend side * big cleaning * show annotations plus agent action for open ai websearch use * show annotations plus agent action for anthropic websearch use * show annotations plus agent action for google websearch use * nit forntend * rm * fix * add test for image ouptut * fix for azure * add in openflow * fix * fix * nit tests * fixes --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> Co-authored-by: centdix <farhadg110@gmail.com> |
||
 Alexander Petric
|
8ad730b290 |
extra logging for agent_token flake (#5693)
* extra logging for agent_token flake * extra logging for agent_token flake |
||
|
Alexander Petric
|
dda92b5491 |
agent integration tests (#5684)
* agent integration tests * agent integration tests * Update integration_tests/requirements.txt Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> --------- Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> |
||
 Ruben Fiszel
|
938b8d81dd | fix lock-write for deno | ||
|
Ruben Fiszel
|
0dc9466dc1 |
fix: integration_tests/requirements.txt to reduce vulnerabilities (#4038)
The following vulnerabilities are fixed by pinning transitive dependencies: - https://snyk.io/vuln/SNYK-PYTHON-CERTIFI-7430173 Co-authored-by: snyk-bot <snyk-bot@snyk.io> |
||
|
Ruben Fiszel
|
50254eced2 | fix integration tests | ||
|
Ruben Fiszel
|
19246bcf3e |
chore: eetest (#2937)
* chore: Windmill integration tests * Revert github workflow temp changes * fix ee --------- Co-authored-by: gbouv <guillaume@windmill.dev> |