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
4.7 KiB
title, description, nav, order, category
| title | description | nav | order | category |
|---|---|---|---|---|
| Hub configuration | Where a project's configuration comes from, how GitHub sync works, and how revisions activate and roll back. | Configuration | 70 | Hub |
Hub configuration
A project is configured by one versioned document. The project's Configuration tab shows the active revision, its source, and the last synchronization attempt.
Sources
A configuration comes from exactly one source:
- GitHub source: one repository, the file
.paseo/hub.yml, on the repository's current default branch. - Manual source: edited in the dashboard and saved with Save and activate.
- CLI/API install: YAML sent explicitly with an organization API key.
Pick a GitHub source by choosing a repository and clicking Use for configuration. That syncs immediately and enables automatic deployment.
The path and the branch are fixed. There is no setting for either.
Deploy from the CLI
From a project checkout, add the target project slug as optional deployment metadata:
project: my-project
Then deploy:
paseo hub login https://hub.example.com
paseo hub deploy --dry-run
paseo hub deploy
Deploy reads exactly .paseo/hub.yml in the current directory; it does not search parent directories. Partials are read from .paseo/partials/ under the same directory.
paseo hub deploy path/to/config.ymldeploys another file. The bundle root stays the current directory.-p, --project <slug>overrides the file'sprojectvalue without changing the YAML sent to Hub.--dry-runsends the identical resolved YAML, project slug, and partial bundle to Hub's validator. Nothing is recorded or activated.
For each prompt include, the CLI sends one { path, content } entry whose path is relative to .paseo/partials/. Only files referenced by the main YAML are sent; include-looking text inside a partial is not scanned. Missing, unsafe, duplicate, unreadable, non-file, or oversized inputs fail locally, and a configuration with only inline prompt blocks sends no partials field.
Origin precedence:
--hubPASEO_HUB_URL- The active stored login
https://hub.paseo.sh
Credential precedence:
--api-keyPASEO_HUB_API_KEY- An exact-origin stored login
Keys passed by flag or environment are not stored, and a stored credential is never reused for a different Hub origin. Deploy and dry-run print the normalized destination before sending anything.
Sync
A push to the default branch of the configuration repository triggers a sync:
- Hub fetches
.paseo/hub.ymlat that exact commit. - It validates the document and resolves every repository, workspace, guild, and daemon it names.
- On success the revision becomes active.
Sync now does the same on demand.
Every attempt is recorded, including failures. The outcomes you will see:
| Outcome | What happened |
|---|---|
| Activated | Valid document, everything resolved, now serving events. |
| Invalid | The document failed validation or named something the organization can't reach. |
| Fetch failed | The file is missing, or GitHub could not be read. |
| Superseded push ignored | A newer commit already moved the branch head. |
A failed sync never replaces the active revision. A repository with a broken hub.yml keeps serving the last good one.
Revisions
Revisions are immutable and numbered per project. Rolling back selects an earlier revision and recompiles its routes. The next valid push activates again, so rollback holds only until the next push.
Switching source
Switching from GitHub to manual copies the active revision into the editor and stops syncing. Switching back means choosing a repository again.
While a project uses a GitHub source, the dashboard editor is read-only. The repository is the source of truth.
The configuration repository does not have to be the repository you watch
filters.repo can name any repository the organization has a connection for. Keeping hub.yml in a private repository while triggers watch several public ones is a common setup, because push access to the configuration repository grants access to the organization's connections.
Treat the configuration repository as part of the security boundary. Hub security covers what a changed configuration can authorize and how to limit the resulting agent process.
Next: Hub workflows, then the hub.yml reference.