* feat(ai-agent): support reasoning effort in AI agent workflow steps Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): round-trip native Anthropic thinking blocks and fix DeepSeek/Mistral reasoning Address review: native Anthropic now captures the signed thinking block during streaming and replays it before tool_use across iterations (prevents a 400 on multi-turn tool use). DeepSeek 'off' sends thinking:{type:disabled} instead of the rejected reasoning_effort:none, and Mistral drops temperature when reasoning is on. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(ai-agent): move reasoning effort into the provider/model selector Store reasoning_effort on ProviderConfig (next to the model) instead of a separate flow arg, and render the selector inside AIProviderPicker under the model dropdown. Add an explicit 'off' option on models that disable reasoning by omission (e.g. Claude), so reasoning can always be turned off from the UI. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(ai-agent): use DropdownV2 for reasoning effort, matching copilot chat Replace the Select combobox with the same DropdownV2 action-menu the copilot chat reasoning selector uses. Each option carries an action instead of a bound value, so click selection is unambiguous and there is no typeahead/sentinel-value mismatch on the off/default entries. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(ai-agent): regenerate system prompts for ProviderConfig.reasoning_effort Refresh system_prompts/auto-generated and cli skills.gen after adding reasoning_effort to the OpenFlow ProviderConfig schema (check-freshness). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): clear stale reasoning effort on model change; dedup bedrock reasoning folding Address cubic review: (P1) the reasoning picker now clears the stored effort when the newly selected model doesn't accept it (e.g. carrying 'xhigh' from Opus onto a model that tops out at 'high'), not only when the model can't reason at all. (P3) the proxy's accumulate_reasoning_delta now delegates to the shared bedrock_stream_event_to_reasoning_delta so worker and proxy folding can't drift. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(ai-agent): stream reasoning summary and show a thinking affordance in flow chat Add StreamingEvent::ReasoningTokenDelta, emitted from every worker reasoning path (Anthropic native thinking deltas, Bedrock, Gemini thought parts, OpenAI-compatible reasoning_content, OpenAI Responses reasoning_summary_text with summary:auto). The flow chat parses it and renders a collapsible 'Thinking' affordance on the assistant message (thinking tokens bill regardless of display, so surfacing the summary is billing-neutral). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): persist streamed reasoning onto the finished chat message Reasoning isn't stored server-side, so the completion re-poll (which swaps temp messages for the persisted ones) was dropping the streamed thinking summary. Carry it onto the final assistant message so the 'Thought process' affordance survives the run. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(ai-agent): match flow-chat thinking box to the copilot chat reasoning UI Replace the plain <details> thinking affordance with the same bordered, collapsible reasoning box the copilot chat uses (chevron + Brain/spinner + 'Thinking' header, markdown body, expand-while-streaming/collapse-on-answer). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): attribute streamed reasoning per turn by content; drop duplicated comment Address review: the completion-poll carry-over now matches each temp assistant turn's thinking summary to its persisted message by content, so a multi-turn response (reasoning -> tool call -> final answer) no longer misattributes an earlier turn's thinking to the final answer or drops intermediate turns. Also removes a leftover duplicated comment block above the AIReasoningEffortPicker effect. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): address review round 2 (carry-over edges, off-token validity, aria, test) cubic round 2: (1) reasoning carry-over now consumes temp turns in order verifying content, so identical/empty-content multi-turn responses attribute thinking correctly and reasoning-only turns aren't dropped; (2) the picker's stale-value check only accepts the off token when the model can actually disable reasoning; (3) add aria-expanded to the Thinking toggle; (4) add a test for the failed tool_result path. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): add bottom margin below the flow-chat thinking box Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): don't request OpenAI reasoning summary, matching the copilot chat OpenAI gates reasoning summaries behind org verification, so requesting summary: auto would 400 for unverified orgs. The copilot chat requests effort only and never asks for a summary; align the worker with it (reasoning: { effort }) and drop the now-unreachable summary-delta parsing. OpenAI reasoning no longer streams a summary in flow chat (consistent with the copilot); Anthropic/Bedrock/Gemini/DeepSeek reasoning display is unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): scope reasoning carry-over to newly persisted messages cubic round 3: matching by content over the full history could attach a new turn's reasoning to an older message with identical text. Restrict eligible targets to the messages just fetched for this response (via afterSeq), so historical turns are never touched. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): carry reasoning newest-first instead of gating on the final poll cubic round 4: gating the carry-over on the final poll's filteredResponse dropped reasoning for messages already fetched by an earlier streaming poll (their id is excluded by afterSeq). Walk persisted newest-first and consume the newest matching pending summary, stopping once summaries run out. This response's turns are always at the end, so they claim their own reasoning (P1) before older history is reached (P2), regardless of which poll persisted them. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(ai-agent): drop flow-chat reasoning display, keep backend + effort picker The chat-side thinking box relied on non-deterministically matching streamed (ephemeral) reasoning back onto persisted messages, which kept spawning edge cases. Remove the flow-chat display entirely (ChatMessage box, FlowChatManager carry-over/threading, parseStreamDeltas reasoning) and keep the sound backend: per-provider reasoning-effort requests, thinking-block round-trips for tool calls, and ReasoningTokenDelta streaming. A display can be built on top later, deterministically (e.g. once the stream carries the persisted message id). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(ai-agent): include reasoning_effort in default-config compare; document reasoning_token_delta Codex/Pi nits: isSameAsStoredConfig now compares reasoning_effort so the 'use as personal default' toggle reflects effort-only changes; openflow streaming-events doc lists the reasoning_token_delta event (regenerated auto prompts). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Windmill CLI
A simple CLI allowing interactions with windmill from the command line.

You can find more information in Windmill Docs
Installation
Install the wmill CLI tool using npm install -g windmill-cli.
Update to the latest version using wmill upgrade.
Workspaces
To get started run wmill workspace add or use the instructions from the
workspace settings.
Running Flows & Scripts
Run a script or flow using wmill flow/script run u/username/path/to/script and
pass any inputs using --data + Inputs specified as a JSON string or a file
using @ <filename> or stdin using @-.
Curl-style syntax using -d @- for stdin or -d @<filename> is also supported.
Flow Steps and Logs will be streamed during execution automatically.
Pushing Resources, Scripts & More
The CLI can push specifications to a windmill instance. See the examples/ folder for formats.
Switch to a different workspace
wmill workspace switch <workspace_name>
Sync a workspace
Pull
wmill sync pull
Push
wmill sync push
We recommend using the --yaml option to use yaml instead of json as the encoding format. Yaml will be made the default soon.
Pushing individual files
You can push individual resources using
wmill <type> push <file_name> \<remote_name\>. This does not require a special
folder layout or file name, as this is given at runtime.
Listing
All commands support listing by just not providing a subcommand, ie
wmill script will result in a list of scripts. Some allow additional options,
learn about this by specifying --help.
User Management
You can add & remove users via wmill user add/remove, and list them using
wmill user
Pulling
You can pull the entire workspace using wmill pull
Completion
The CLI comes with completions out of the box via wmill completions <shell>.
(Via cliffy)
Bash
To enable bash completions add the following line to your ~/.bashrc:
source <(wmill completions bash)
Fish
To enable fish completions add the following line to your
~/.config/fish/config.fish:
source (wmill completions fish | psub)
Zsh
To enable zsh completions add the following line to your ~/.zshrc:
source <(wmill completions zsh)
Development
AI Guidance Variants
wmill init can now materialize alternate AI guidance bundles without changing
the generated defaults in the repo, but this is exposed as internal env-var
overrides rather than public CLI flags.
Examples:
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills wmill init --use-default
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills WMILL_INIT_AI_AGENTS_SOURCE=/path/to/AGENTS.md wmill init --use-default
WMILL_INIT_AI_SKILLS_SOURCE=/path/to/custom/skills WMILL_INIT_AI_CLAUDE_SOURCE=/path/to/CLAUDE.md wmill init --use-default
This is the same guidance-writing path used by the benchmark CLI under
ai_evals/, so the benchmark harness and wmill init now generate the same
project guidance shape:
AGENTS.mdCLAUDE.md.agents/skills/*.claude/skills/*
Testing with a local windmill-yaml-validator
To test local changes to the validator before publishing, use npm link:
# In windmill-yaml-validator/
npm run build
npm link
# In cli/
npm link windmill-yaml-validator
Running Tests
Prerequisites:
- PostgreSQL running locally (default:
postgres://postgres:changeme@localhost:5432) - Rust toolchain installed
Run tests locally (full features):
bun test test/
Run tests in CI mode (minimal features, skips EE tests):
CI_MINIMAL_FEATURES=true bun test test/
| Variable | Description |
|---|---|
CI_MINIMAL_FEATURES |
Set to true to skip EE-dependent tests |
DATABASE_URL |
PostgreSQL connection string |
EE_LICENSE_KEY |
Enterprise license key for EE features |
