Mohamed BoudraandGitHub
ccb4e444ed
* docs(hub): name the Hub tools in workflow prompts
Every Hub workflow example now tells the agent which tool to call:
hub.reply for the user-facing response, hub.finish_execution to
complete the step and record structured output. Granting a capability
through allow_outputs makes the tool available; it does not make an
agent use it, and an agent that is not told answers in its own
transcript and leaves the step to its idle timeout. Explicit
instructions are what worked against real agents.
Classifier and other intermediate steps name hub.finish_execution
alone, so the docs do not imply every step must reply.
Drops the github.reply allow_outputs blocks from the GitHub examples.
The GitHub provider registers no output capabilities, so that
declaration never materializes a tool; those agents comment through
their scoped GH_TOKEN with gh, which the reference and trigger pages
already said. The read-only answer branch has no network authority for
that, so it only finishes.
Also quotes the "Request: ${{ paseo.prompt }}" prompt block in the
reference, which was invalid YAML as written.
* docs(hub): wrap triggering input in its own prompt block
Every Hub YAML example now ends its prompt with the raw triggering
message wrapped in <user-prompt> tags, as a separate block after the
workflow instructions. The agent can see where your instructions stop
and the request starts, which matters most on the steps that read
external Slack, Discord, and GitHub text.
The first workflow explains the convention in two sentences and points
at Hub security for the controls that actually limit an agent. Tags
label the input; they are not containment, and the docs do not claim
otherwise.
Replaces the earlier quoting fix in the prompt-blocks reference: the
message now lives in a block scalar, so the colon needs no quoting.
* docs: base worktree examples on origin/main
Every branch-off example now passes a remote-tracking ref. Paseo
fetches remote refs in the background, so origin/main is current while
the local main is whatever was last pulled, and base resolution tries
refs/heads first: an unqualified main silently branches off stale
history. The gotcha is explained once, next to the first branch-off
example in the worktrees guide; the other pages just use the ref, and
the Hub environment reference links there.
Also points the safety-gate classifier at the structured-output
section, which shows the output wrapper the finish call takes.
* docs(hub): configure Codex read-only through provider options
Hub examples described a read-only Codex step as mode: read-only. That
Paseo mode preset pairs the read-only sandbox with approval_policy
on-request, so an unattended Hub step stops to ask a question nobody is
there to answer. It is also not one of the modes the Codex provider
advertises.
Every read-only step now uses the provider-native passthrough proven by
the real-provider evidence in #3025: approval_policy never,
sandbox_mode read-only, web_search disabled. The security guide already
used this block; the workflow guide, examples, and reference now agree
with it, and the reference says plainly that a Paseo mode ID is a
separate surface from these options.
mode: full-access is unchanged. It maps to approval_policy never, so it
does not stall an unattended step.
* docs(hub): show a classifier choosing the repository and the model
Both routing jobs were only documented as caller-supplied inputs, so
there was no example of the thing people actually want: one read-only
classifier that reads the request, picks the repository it belongs to
and the model it needs, and hands both to a worker. Replaces the
caller-only model example, which the new one covers through its
override values.
The two axes are not symmetric and the example says so. A model is a
value, so values.selected_model goes straight into agent.model. An
environment cannot come from an expression at all: the compiler accepts
a literal name or paseo.inputs.<name> and nothing else, so each
repository needs its own environment and its own conditional step. One
classifier, exactly one worker.
Corrects the routing section, which listed environment among the fields
an agent output may select. It never could.
Also puts a blank line between adjacent steps and environments in the
deadline and repository-routing examples, and bases the daemon worktree
example on origin/main, which the earlier sweep missed.
* fix(website): keep development requests local
Canonical host redirects were applied to LAN-addressed development traffic, including inspector WebSockets. The redirected socket retained the Vite port and caused the development proxy to terminate when the public host timed out.
* docs(hub): order the workflow scenarios from simple to hard
The Hub pages were arranged by the shape of the configuration schema
rather than by what a reader is trying to do, which showed up three
ways: the overview opened on the storage hierarchy, workflow
configurations were split between workflows.md and a separate examples
page, and the examples that existed started with the hardest one.
workflows.md is now a ladder. One Slack trigger answering in a thread
stays inline as the first workflow, and nine further scenarios sit
under it as collapsible blocks, each a complete configuration adding
one idea to the one above: full access, repeated replies, a GitHub
trigger, two ordered steps, a typed input, two triggers, a classifier
choosing a model, a classifier choosing a repository, and last the
override composed with ??. configuration/examples.md is removed and its
configurations live there now.
Two claims in the old material were wrong and are corrected. Nothing
carries between steps except a declared output, so the planning
scenario passes its plan through output.schema instead of telling the
second agent to follow a plan it cannot see, and a worktree environment
creates a worktree per execution rather than sharing one. GH_TOKEN
authenticates the gh CLI but does not configure git, so the pages no
longer imply a step can push without a commit identity and credential
helper on the daemon host.
The overview drops the organization/connections/daemons/projects tree,
which concepts.md already owns, in favour of the smallest configuration
that does something. Hosting is now a link from the product pages
rather than a section in them.
* docs(hub): make GitHub access an explicit step grant
GitHub authority gets its own page. A step holds a token only when it
declares a github block — connection, repositories, permissions,
duration — and Hub supplies GH_TOKEN plus environment-only git
configuration, revoked when the step ends. No credential is ever
implied by the trigger source.
Rewrites the issue-to-pull-request scenario onto the block, repoints
the trigger, reference, FAQ, and concepts pages, and sweeps the Hub
pages for announcing sentences and compressed paragraphs.
* docs(hub): lighten dense reference prose
Restructure paragraph walls into short paragraphs, lists, and code
blocks: logout behavior in daemons, deploy paths and precedence in
configuration, install limits and dispatch fields in the API page,
required outputs and partial resolution in the reference, and the
policy translation and secrets guidance in security. Fixes two
remaining trigger-derived credential claims in triggers/index.
* fix(nix): update npm dependency hash
* docs(hub): document shared prompts and authority defaults
4.1 KiB
4.1 KiB
title, description, nav, order, category
| title | description | nav | order | category |
|---|---|---|---|---|
| Hub activity | Read what Hub did with an event, tell a filtered event from an unrouted one, and debug a trigger that did nothing. | Activity | 72 | Hub |
Hub activity
Every event Hub accepts is recorded, whether or not it ran anything. That record is how you debug a trigger.
Where to look
Project → Activity lists the events routed to that project: the event, its source, the result, and when it arrived.
The result column says what happened:
| Result | Meaning |
|---|---|
| A trigger name | The event matched that trigger and dispatched |
| A lifecycle state | The execution is in progress or finished |
no_matching_trigger |
The event reached the project, but no trigger's filters matched |
provider_unrouted |
No project route existed for the resource that produced the event |
Project → Executions lists the runs: which trigger, which configuration revision, which daemon, duration, and outcome.
Connections → Known unrouted events is the organization-level view. It holds events whose credential belongs to your organization but which no project's configuration claimed. A repository you connected but never named in a trigger lands here.
Those two are different problems. no_matching_trigger means your filters are wrong. An unrouted event means no configuration mentions that repository, workspace, or guild at all.
Nothing happened when I mentioned the bot
Work down this list.
- Is the event in the project's Activity? If not, check Connections → Known unrouted events. If it is there, no trigger names that resource. Add
filters.repo,filters.workspace, orfilters.guildand push. - Is the event anywhere at all? If not, the event never reached Hub. Check the provider's own delivery log: GitHub's App → Advanced → Recent Deliveries, or Slack's Event Subscriptions page. Then check that the app is subscribed to that event type.
- Is your user in
from_users? This is the most common cause. GitHub uses your login; Slack and Discord use the user ID, not the display name. - Did the mention match? On GitHub,
containsmust appear in the comment body. On Slack and Discord the bot must actually be mentioned, andpatternmatches only at the start of the text after the mention. - Is the configuration you think is active actually active? The Configuration tab shows the active revision and the last sync attempt. A failed push leaves the old revision serving.
- Is the daemon connected? An offline daemon fails dispatch with
daemon_not_connected. - Did it run and stop early? Check the execution. An agent that never reports back is ended by
idle_timeoutafter 5 minutes by default, ortimeoutafter an hour. - Did it run, but deliver nothing? Check the step's prompt. An agent that is not told to call
hub.replyandhub.finish_executioncan answer in its own transcript and never report back. See Tell the agent which tool to call.
Sync failures
The Configuration tab shows the latest sync state:
| State | What to do |
|---|---|
| Fetch failed | The file is missing at that commit, or the App can't read the repository |
| Invalid | Validation failed, or the config names something unreachable |
| Superseded push ignored | A newer commit already moved the branch head; nothing is wrong |
"Names something unreachable" is usually a repository the installation doesn't cover, a daemon that was renamed, or a connection slug that no longer exists. See How Hub works.
Nothing is retried
Hub does not queue events. A dispatch that fails because the daemon was offline stays failed, so trigger it again once the daemon is back.