4 Commits
Author SHA1 Message Date
NB c5e66181b4 Start a workflow loop at its leftmost entry on the canvas (#12944)
* Start a workflow loop at its leftmost entry on the canvas

A workflow loop that one more connection also enters (for example the
task to a reviewer inside a search loop, #12199) got its loop edge from
a depth-first walk in the order in which the edges were added. When the
extra edge came first, the walk entered the loop at the reviewer and
marked search > reviewer as the loop edge, not enough > fork. Then
"Run from this step" on the reviewer counted the search as a later
step and ran it again, and a full run started the reviewer before the
search.

workflowLoopEdges now finds each group of steps that reach each other.
When edges from outside enter a group at more than one step, the loop
starts at the leftmost entry on the canvas; a tie, a single entry, or
no positions keep the step that the old walk reached first. The group
without its loop edges gets the same treatment for inner loops. On
30,000 random graphs without positions the result is the same as the
old walk, and no random graph keeps a loop after its loop edges are
removed.

The host run, the desktop and web canvas, and mobile all call this
shared function, so they keep the same loop edges. No wire protocol,
IPC or schema change: loop edges are computed from the graph, never
saved or sent. A joined server must be on the new version for its runs
to get the fix.

This ports the rule of #12240 to current main, without the doc
comments that AGENTS.md now forbids.

Fixes #12199

* Start a single-entry workflow loop at its entry and break an x tie by y

A loop with one entry from outside now starts at that entry, not at the
first loop node that the walk reaches. When two entries have the same x,
the topmost entry is the start. The architecture document gives the rule.
2026-11-19 18:58:07 +01:00
Aleksander DygońandClaude Opus 5.5 03c2ff34c2 Remove code comments and add the no-comments rule (#12604)
* Remove code comments and add the no-comments rule

Remove the comments from first-party code and configuration files:
TS/JS, JSX, CSS, SQL migrations, Swift, Kotlin, Gradle, shell,
Docker, systemd, Nix, YAML, TOML, JSONC and GritQL.

Keep only what a tool reads: license headers, shebangs, compiler
and lint directives, JSDoc types in plain .js files, generated file
headers, GritQL scope lines, the install-server.sh help text and the
openbot-boat-pre-stop marker. Vendored code, fixtures and released
schemas keep their comments.

Add the rule to AGENTS.md, and change the docs that asked for
comments. Add two i18n keys that only comments named to
RELEASED_SOURCE_KEYS.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep comments that are data in strings

The benchmark task files in opencode-free-models-bench.ts tell the
model what each function must do. The sample file and HTML page in
the two stories are display content. Put their comments back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep released migrations and mobile native inputs unchanged

check:migrations compares each released migration with v0.73.0 byte
for byte, so restore src/backend/migrations. A change to a native
build input of apps/mobile makes a new runtime version, so restore
those files and the extra fingerprint sources.

List these files and the comment markers that a tool reads in
AGENTS.md. Remove the last requests for comments in
src/renderer/AGENTS.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 12:19:28 +01:00
NBandClaude Opus 5.5 39b2a95052 Start workflows from GitHub events and change GitHub from workflows (#4288)
* Fix workflow node fades and ports in browsers without scroll timelines

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the GitHub workflow contract and the workflows-github-v1 capability

GitHub is a trigger type, an output target and a run source. The new
capability carries the GitHub catalog, repository options, event history
and a run with the last event. A client shows a workflow with a trigger
type or an output target that it does not know as read-only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add migration 49 for GitHub workflow runs, deliveries and actions

Migration 49 rebuilds workflow_runs to accept the github run source and
keeps every run id. It adds three tables:

- workflow_github_runs: the item of each run that a GitHub event started.
- workflow_github_deliveries: the event history of each GitHub trigger,
  and the per-item queue (a waiting row keeps its payload until it starts).
- workflow_github_actions: each change that a GitHub output made, so a
  retry does not repeat it and the loop guard can find its own events.

The latest schema takes the same run source line and tables. Tests cover
schemas 46 to 48, a late failure and retry, newer and missing histories,
constraint refusals and cascades.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Route GitHub App events through Signal to the hosts that watch them

Signal gets POST /v1/github/events. It checks the App signature, reads only
the installation and repository IDs, and sends the exact body to every host
whose GitHub route ticket names the repository. It keeps no body.

The account service signs the 5-minute route ticket after it checks, with
the host's GitHub sign-in, which watched repositories that sign-in can see.
D1 keeps no GitHub route.

The host ingress socket holds a GitHub route through the new GitHubRelay,
answers github-delivery frames, and records the offline gaps.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Start workflow runs from GitHub events, one run per item

- Match GitHub events to triggers by repository, event and filters.
- Queue an event when a run of its item is open; start it when that run ends.
  Runs of other items start at the same time.
- Skip echoes of the workflow's own actions (self) and the fourth run in
  10 minutes that OpenBot's bot caused on one item (chain).
- Keep the newest 50 events per trigger and record offline gaps.
- Add the refused skip reason and caused_by_bot to the unreleased v49 table.
- Add scripts/github-workflow-e2e.ts (host level).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Make the changes of GitHub outputs as OpenBot's bot

A GitHub output makes one of the 10 changes through the GitHub REST API with
the App's installation token. "Agent chooses" asks a model once and keeps only
the repository's own labels and people. Each change writes a `sending` row
before the call and a `done` row after it, so a retry does not post twice and
the loop guard knows the change's events. A restart sends again only a change
that a second call does not repeat. "Run with last event" starts a run with
the newest matching item.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Show GitHub triggers and outputs on the workflow canvas

The trigger and output cards get GitHub rows: repository, event,
filters, action, labels and people, with "Agent chooses". The Events
row lists what GitHub sent. Access and event alerts open GitHub, and
Connect opens the connect dialog of the GitHub settings page.

The run bar lists the open runs and the waiting events, and the canvas
shows the steps of the open run that the user views.

The renderer reads the catalog, labels, people and event history from
the host through new IPC reads and Team API routes. GitHub shows only
for an owner or admin on a host with workflows-github-v1.

Stories replace the prototype stories.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Translate the GitHub workflow text into 12 languages

Name the GitHub event and action labels as literal catalog keys, and
remove two keys that no code uses.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Test the redaction of GitHub errors, and document GitHub workflows

Add a Vitest that checks that GitHub's error text and a failed request
put no token into a step's failure. Document the GitHub trigger path,
the delivery outcomes and the Team API routes, and add release notes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Remove unused GitHub exports, and fix an optional field in the e2e

Knip and the exactOptionalPropertyTypes ratchet failed the Check job.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Send not_planned to GitHub when an output closes an issue as not planned

The saved close reason is notPlanned. GitHub refused it with
"Please specify a valid state reason." The adapter now maps each saved
reason to the state_reason that GitHub accepts.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep trigger events off GitHub, and add repository search and loading rows

- A GitHub output removes the framed trigger event from its text. A comment
  that has only the event fails with a clear error and posts nothing.
- The repository menus have a search field.
- The Labels and Person menus show "Loading…" while the host reads them.
- The log says that the GitHub output failed, not that it made no change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Make each loop pass change GitHub, and keep Telegram when a ticket fails

- A GitHub output keys its change by run, node and pass. A loop pass
  makes its own change. A retry or a restart of the same pass does not
  make the change again.
- When the trigger event comes back in a loop, the output also removes
  the empty "Input N:" names of the event.
- A failed GitHub or webhook ticket does not stop Telegram or the other
  routes on the shared socket.
- The connector reads the App events from GITHUB_ROUTE_EVENTS.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Let Signal pass GitHub events of up to 512 KiB

An issue_comment or pull_request event can hold two texts of 65,536
characters each. Signal refused such an event with 413, and GitHub does
not send it again.

- GITHUB_DELIVERY_BODY_BYTES_LIMIT is 512 KiB.
- The pending budget for each host is 768 KiB, and the socket
  backpressure limit is 1 MiB, so the largest event fits.
- nginx gets a /v1/github/events location with the same body limit, no
  access log, and the 10-second wait of GitHub.
- The Signal e2e sends the largest event and one above the limit.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep an end marker in a comment inside its event, and stop loading after a failed options read

The event frame ends only at the marker on its own line. The JSON of the event keeps no line
break, so a commenter cannot end the frame early and get text posted as the bot.

A failed read of repository labels and people now stores empty options. The menus stop
showing "Loading". A change on GitHub reads them again.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 00:19:46 +01:00
NBandClaude Opus 5.5 4f076e6b8b Add workflows: connect agents and steps on a canvas (#3062)
* Add workflow IPC contracts

Types and guards for workflows: graph, summary, detail, runs, steps,
versions and their inputs. Add the input limits and the
workflows-changed agent event.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the workflow tables (migration 46)

Migration 45 only creates tables and indexes: workflows, nodes, edges,
versions, triggers, trigger webhooks, webhook receipts, runs, steps and
output deliveries. No row of an existing table changes. The same SQL is
the tail of the latest schema for new databases.

- workflow-migration.test.ts covers every schema from 8 to 44, rollback
  and retry, newer and incomplete histories, foreign keys and cascades.
- The older migration tests expect version 45 as the latest.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the workflow store and graph rules

The store saves graphs with a revision check, keeps up to 50 versions,
and keeps trigger rows. Deleting an agent removes it from workflow nodes
and keeps the step history.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the workflow IPC endpoints

The host answers list, get, create, rename, delete, save, versions and
restore. A joined server says that it does not support workflows yet.
The preview keeps workflows in memory.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add workflow runs

Run a workflow from the start, from a trigger, or from one node, and run
one node alone. Agent steps go through the routine sender, so an agent
answers in its own chat. Model and condition steps use a tool-less
generation; a condition answers yes or no. Approvals wait for a decision,
and a rejection stops the run. Notify outputs show a desktop notification.

A sweep at startup settles agent steps from their delivery and fails
model steps that a restart interrupted. Channel outputs fail with
outputPending until the messaging-place output lands.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the workflow run view and rail button

- WorkflowFeatures and the v1 set of node kinds, triggers and outputs.
- A pure run view: pages of runs, run and step changes, and the run
  state of each node.
- The Workflows rail button (Waypoints) and app.rail.workflows in all
  languages.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Move the workflow nodes into shared UI

- The board, camera, picker, tool art and one file per node kind move
  to packages/ui/src/features/workflows, with their styles. Their icons
  go through the shared icon exports.
- Nodes read agents, models, places, image models and files from
  WorkflowCatalogs on the board. No story data or simulated runs.
- The agent node writes agentId; a channel output writes connectionId
  and placeId, as the contract says.
- 199 English keys in the workflow module. Result times are ISO and
  formatted in the reader's locale.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Split the workflow canvas into shared UI

Move the canvas from the prototype into packages/ui as a controlled
component. The host gives the workflow, runs, versions and catalogs, and
gets each graph change. Remove the run simulation, presence and local ids.
Add the canvas keys in English, the Workflows stories over the preview
mock, and the Storybook icon link.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add the Workflows page to the desktop window

The Waypoints rail button opens a titled page with the workflow canvas of
the server. The page saves the graph 400 ms after the last edit, one save
at a time on its base revision, and loads it again after a change from
another device. A joined server without workflows shows a notice.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Add workflow triggers, place outputs and workflows-v1

- Schedule triggers: WorkflowTriggers is a routine due source. A missed
  time gives one run, and a time is skipped while a run is open.
- Webhook triggers: a third webhook route owner. The first secret makes
  the route. Receipts stop a second run for the same delivery.
- Place outputs: an output posts the result to a messaging place, once,
  and an interrupted post becomes uncertain at the next start.
- workflows-v1: the frozen Team API routes, codecs and event, the host
  route with its grant rules, the team client and the remote IPC branches.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Translate the workflow catalog

Add the 302 workflow keys in de, es, fr, it, ja, pl, pt, ru and tr.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Edit trigger schedules and webhook secrets on the canvas

A trigger node uses the routine schedule picker and saves the schedule
on the node. A webhook trigger without an address has a button that
makes the first secret, and so the address. The preview gives the next
run and the address.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Document workflows

PRIVACY.md says what a workflow keeps on this computer and what an
output and a webhook trigger send. The architecture notes describe the
run engine, the timer source, the webhook owner and workflows-v1.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fix the workflows page height and the canvas after a delete

The canvas is a direct child of the window page, so it gets the height
of the pane. The page reads its host once, without a tracked read.
When the host opens another workflow after a delete, the canvas shows
again; a switch while the Undo toast is open keeps the delete.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Name migration 46 in the workflow docs

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Scope workflow run and step keys to their workflow

A copy of a workflow keeps its node ids, so its schedule and webhook keys
were the same text as the first workflow's, and its runs were answered
with the other workflow's run. The keys are now unique per workflow.

Migration 46 is not released, so its tables change in place: steps check
their kind, and the unused waiting status, trigger enabled and
last_scheduled_for columns, delivery retry columns and the inactive
receipt reason are gone. A refused delivery gets its own reason.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fix workflow run starts, the sweep and schedule waits

- A run, its version, its reused steps and its webhook receipt are one write.
- A webhook request that the graph refuses gets an ignored receipt and 202.
- A trigger of a workflow with an open run waits for the run to end.
- One failing schedule trigger does not stop the others.
- The sweep ends steps that a restart or an agent delete left open, and
  ends a stop that a restart cut off.
- A run version is kept only when the graph changed.
- Store errors carry a code; the Team API maps missing to 404 and a bad
  schedule to 400. The list reads every graph in one query.
- The runs cursor names the run, so runs of the same millisecond stay.
- The routine timer plans again only when a trigger changes or a run ends.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Share the workflow helpers with routines

Use one placeholders, receipt cutoff, result text, node agent, node
timezone, CHECK column and coalesced sweep helper. Build the edge maps
in place.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fix workflow canvas bugs in keys, drags, uploads and approvals

- Agent and LLM pickers set model, provider and effort as one change.
- Undo and redo stop a drag and cancel queued layout frames.
- Keys, clipboard and Delete act only in the canvas, its portals or the
  page body. Menus and lists keep their letter keys. Delete and cut do
  nothing on a frozen or deleted workflow.
- Drag and pointer listeners are removed on cancel, restore and unmount.
- Slots and ports stop the resize observer when they go.
- Asset uploads belong to the board. Their blob URLs are freed at
  unmount, a file is found by id, and the upload button follows
  features.uploads.
- The canvas label names the workflow. The minimap is hidden from screen
  readers. The live region tells only the step status changes.
- Ports set aria-pressed only while a line is drawn.
- A new note saves the name of its author in its fields.
- Picker tiles get the colour of their kind.
- A new node does not cover a node at the centre of the view.
- Search reads the text fields of the board, not the DOM.
- An approval answer is for one step, and shows again when sending fails.
- Each trigger gets its own new schedule object.
- The search fields show a grey focus ring.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Make the workflow canvas do less work for each change

- Selected, removed and locked nodes are projections. A node runs
  again only when its own state changes.
- The list of nodes on the canvas and the trigger lookup are memos.
- Fit to view and the minimap use the sizes from the resize observer.
  Fit reads the element only for a node that has no size yet.
- A line that the user draws adds points in place. A move does not copy
  the line or put it in a store.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Open the workflows-v1 names and add the version graph read

- The wire carries node kinds, edge types, statuses, sources, trigger
  types and version kinds as short names. A client maps a name it does
  not know: a node becomes a locked note, its edges go, and the
  workflow is read-only.
- New workflows.versionGraph read (IPC and Team API). The host hides a
  version that names an agent the member cannot see.
- The IPC parse keeps only known graph keys and refuses a graph over
  1 MiB with its own sentence.
- Align wire limits: runs limit 1-50, run number and attempt >= 1,
  runs cursor up to 64 characters.
- Move the workflow decoders to remote-workflow-decoding.ts. Delete the
  unused team-client and web-runtime workflow requests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Ask for the manage level to change a shared workflow

- A member needs manage on each agent of the graph, before and after,
  to save, rename, delete or restore a workflow or to make a new
  webhook secret. A run, a stop and a decision still need chat.
- Retry, stop and decide also check the agents of the run's own graph:
  a retry ran an agent that the current graph no longer names.
- An owner or admin sees a workflow whose agent was deleted.
- A save conflict answers as missing when the newer graph names an
  agent that the member cannot see.
- Run answers empty the oldest step texts to fit one frame, as the run
  page does. A single step of a hidden agent answers 404, not 500.
- Reuse runEventsEffect from route-events.ts.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Share one workflows controller between the page and stories

- Move the save queue, resets, restore, preview and delete into
  workflows-controller.ts. The page and the stories use it.
- A version preview reads its graph from the host.
- A conflict or a restore keeps the canvas edits on undo, and a toast
  tells the user.
- A failed save keeps the edit for the next save. A restore or a
  delete saves the waiting edit first. A failed delete shows the
  workflow again.
- A member without "Can manage" on each agent gets a read-only canvas.
  Only an admin can rotate a webhook secret. The channel output hides
  when there are no places.
- Add the Korean workflow catalogs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Document workflow permissions and test agent steps

Docs and the release note give the manage rule, the version-graph route
and the sweep rules. A new e2e checks that an agent delete fails the open
step, and that a restart ends a stopping run. The webhook e2e checks that
a graph this version cannot run gives a refused receipt.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fix workflow canvas halt on restore and new node placement

A restore that removed a node wrote the slot size store in a list cleanup,
which halts Solid. The reset now drops the sizes of the removed nodes. A new
node now moves past each card that it would cover, not only an exact corner.
The controller reads the server role untracked.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Read the first agent fields of an agent step untracked

The catalog agent is a store, so a read of its model and provider in the
component body warned that the value does not update.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Remove unused workflow exports and fix optional props for the type ratchet

Knip found 13 exports that only their own file uses. The optional props
that take an undefined value now say so, as exactOptionalPropertyTypes
requires.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Document that workflows with no agent need no agent level

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep the workflow canvas and its toolbars on whole pixels

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fade workflow canvas parts in out of a blur instead of a move

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Remove the entry animations of the workflow canvas

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Match the workflow title to the other page titles and remove its icon

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Balance the paddings of the workflow title and HUD buttons

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Give the workflow top row the button size of the other pages' top rows

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Make the workflow canvas icons and node toolbars sharp

On a screen with one device pixel for each CSS pixel, the canvas icons get a line of 2, so a line fills
whole pixels. The node toolbar icons are 16px, as in the tool bar. After the camera, a node or the
selection moves, the node toolbars and result strips move onto whole device pixels.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fill the icon of a pressed workflow canvas tool

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Snap the workflow node toolbars to whole pixels and enlarge their icons

The earlier sharpness commit added the snap offsets in the canvas but not the CSS that reads
them. The node toolbar and the result strip now add the offsets to their position, and the
toolbar icons show at 16px.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fill the pressed Select arrow fully

The part-fill rule matched the svg element too, so it had more specificity than the arrow
rule, and the arrow stayed at 35%.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Give workflow sticky notes the corner radius of the other cards

A note had a 6px corner that shrank with the zoom while its selection ring and resize arc
kept their screen gap, so the corners did not look alike. Notes and their drop preview now
use the card radius.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Allow loops in workflows

A connection back to an earlier step is a loop. The run takes it as the
next pass: the earlier step runs again with the loop's answer as one more
input, and the steps after it follow. A loop has no pass limit; a
condition, a failed or rejected step, or a stop ends it.

The canvas draws a loop under its steps with a "Loop" badge, and with an
"Endless loop" warning when no condition is in the loop. While the user
connects, the draft line says that the connection makes a loop.

A retry now runs every step after the retried step again, not only the
skipped ones.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Do not select a workflow step on a press of its port

A press on a port, a portal or the edge actions selected the step under it,
so a new connection also moved the selection.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Show why a workflow Output or Condition step failed

These cards have no result field, so a failed step showed only its status.
They now show the error of the step.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Retry a workflow step with the node's current settings

A retry used the settings that the run copied, so a fix made after the
failure, such as a new output place, did not apply. A retry now uses the
current node, and the run's copy only when the node is gone or is now
another kind. The Team API already checks the agents of both graphs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Reuse a warm provider for workflow model steps and count their usage

A model or condition step started a new provider process each time and
recorded no tokens. Now one process without tools per provider stays for
5 idle minutes; each step still starts a new ephemeral thread and closes
it after the turn. The process stops when the main client stops or
changes, after a failed step, and at shutdown.

The tokens of these steps go to one reserved usage row,
WORKFLOWS_USAGE_ID, which the host report, the Team API filter and the
usage panel accept. Agent steps still count under their agent.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Report workflow runs and actions to product analytics

The host sends system_workflow_run when a run ends (outcome, source, duration, step counts by
kind) and workflow_count in the daily inventory. The window sends workflow_action for each user
action on a workflow. No name, text, graph or ID is sent. Host generation 11, desktop 12.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Translate the workflow text to Simplified Chinese

main added zh as a 12th language. Add the workflow and workflow error catalogs, and the Workflows
rail, usage and notification keys, so zh has every key.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Fix workflow review findings before merge

- Reuse steps in graph order, so a reused step does not make a node behind it due.
- Build the input of a retried agent step again from the current task.
- Show the Workflows usage row only to a peer with workflows-v1.
- Keep the warm client state correct when a generation is interrupted, and wait for idle stops at shutdown.
- Send the duration of a workflow run up to 30 days.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 14:26:17 +01:00