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
12 KiB
title: hub.yml reference description: The authored Hub configuration: environments, triggers, typed inputs, workflow steps, routing, and prompt partials. nav: hub.yml reference order: 71 category: Hub
hub.yml reference
A configuration has environments and triggers. It may also include top-level project deployment metadata for paseo hub deploy. Execution fields belong to each trigger's steps.
project: my-project
environments:
- name: development
kind: daemon
daemon: my-macbook
cwd: /Users/you/code/project
triggers:
- name: request
on: manual.run
max_runtime: 2h
filters:
from_users: [automation]
steps:
- id: work
environment: development
max_runtime: 90m
idle_timeout: 10m
agent:
provider: codex
mode: full-access
prompt:
- text: Call hub.finish_execution when the step is complete.
- text: |
<user-prompt>
${{ paseo.prompt }}
</user-prompt>
project is an optional bare project slug. The deploy CLI uses it to choose the target project when -p, --project is absent. The flag takes precedence over this metadata without rewriting the YAML. project is not available to triggers, expressions, or agents.
Environments
| Field | Required | Notes |
|---|---|---|
name |
yes | Lowercase identifier referenced by a step. |
kind |
yes | daemon, fly, or docker in the authored schema; workflow steps must resolve to a daemon environment. |
daemon |
daemon only | Friendly daemon slug, resolved to its immutable ID when the revision activates. |
cwd |
daemon only | Absolute path on the daemon. |
image |
fly/docker | Image name. |
worktree |
no | branch-off, checkout-branch, or checkout-pr target. |
The worktree object is part of the environment. Its fields are exact authored names: newBranch and optional base for branch-off, branch for checkout-branch, and positive integer prNumber for checkout-pr. Give base a remote-tracking ref such as origin/main; see Git worktrees.
Triggers
| Field | Required | Notes |
|---|---|---|
name |
yes | Lowercase identifier, unique in the configuration. |
on |
yes | provider.event, such as slack.mention or manual.run. |
max_runtime |
yes | Positive duration for the complete trigger run, up to 24h. |
filters |
no in schema | Provider filters; externally sourced triggers still require a non-empty from_users allowlist. |
inputs |
no | Typed leading key=value invocation headers. |
values |
no | Derived expressions. |
steps |
yes | One or more ordered steps. |
Inputs
Each input has:
inputs:
repo:
type: string
required: false
choices: [project, paseo]
agent:
type: string
default: codex
choices: [codex, claude]
type is string, number, or boolean. required, default, and choices are optional. required and default cannot be combined. Defaults and choices must match the declared type; a default must be one of the choices.
Inputs may be referenced as ${{ paseo.inputs.name }}. A dynamic authority-bearing field such as a provider, model, mode, or environment requires finite choices at activation. A prompt cannot supply authority.
Values
Values bind expressions under their own namespace:
values:
selected_repo: ${{ paseo.inputs.repo ?? steps.classify.outputs.repo }}
The grammar supports paths, JSON literals, parentheses, !, ==, !=, &&, ||, and ??. It does not support function calls, JavaScript, arithmetic, mutation, or implicit string coercion. Referenced steps must exist and value dependencies cannot cycle.
Steps
| Field | Required | Notes |
|---|---|---|
id |
yes | Lowercase step identifier, unique within the trigger. |
environment |
yes | Environment name or a finite input expression resolving to one. |
max_runtime |
yes | Positive step hard limit, up to 24h. |
idle_timeout |
yes | Positive idle limit, no longer than the step hard limit. |
agent |
yes | provider, optional model, mode, thinkingOptionId, and provider-native options. |
prompt |
yes | Non-empty list of text and GitHub-only include blocks. |
if |
no | Expression deciding whether this ordered step runs. |
env |
no | Environment variables populated from connection values. See GitHub access. |
output |
no | { schema: <JSON Schema> } for the structured result the agent passes to hub.finish_execution. |
allow_outputs |
no | Registered output capabilities such as slack.reply or discord.reply, each with optional max and required. |
auto_archive |
no | Archives the step's agent when it ends. |
github |
no | Scoped GitHub token and git setup for this step. See GitHub access. |
Prompt blocks are objects, not a scalar prompt:
prompt:
- include: developer.md
- text: |
<user-prompt>
${{ paseo.prompt }}
</user-prompt>
Keep the triggering message in its own final block, wrapped in <user-prompt> tags, as the first workflow does.
Use ${{ paseo.prompt }}, ${{ paseo.inputs.* }}, ${{ steps.*.outputs.* }}, and ${{ values.* }} in prompts, conditions, and agent selection fields. Provider event payloads are not part of this workflow expression namespace; provider adapters put the normalized request into the prompt and preserve the raw event as evidence.
agent.options carries JSON-safe options using the selected provider's native names and nesting. Paseo validates them with that provider's strict schema before starting the session. See Hub security for the trust boundary and copyable provider examples.
mode names a Paseo agent mode ID, which is a separate surface from these options. Some modes keep the provider's interactive approval flow, and that stalls an unattended step, so set the provider's own approval and sandbox settings in options instead.
Output capabilities
allow_outputs separates permission from obligation. max limits how many times a capability may be emitted and defaults to 1. Set required: true when the step must emit that capability at least once before it can finish successfully:
allow_outputs:
- type: discord.reply
max: 1
required: true
required: true means the step must actually emit the capability. Assistant text does not count.
- A required output must resolve to a registered, available capability for the execution, or dispatch rejects the step.
- A required output needs an effective
maxof at least1, or activation rejects the configuration. - Failed delivery is retryable. An agent that tries to finish first is told the concrete output tool to call, then
hub.finish_executionis retried.
Omitting required keeps the output optional. GitHub has no reply capability; a step acts through the gh CLI with the token its github block grants.
A declaration grants the tool. The step's prompt still has to tell the agent to call hub.reply, and to call hub.finish_execution when it is done. See Tell the agent which tool to call.
Prompt partials
include paths are relative to .paseo/partials/.
- GitHub configuration: Hub reads each file at the exact configuration commit and stores the resolved content and SHA-256 hash in the immutable revision.
paseo hub deploy: the CLI reads the referenced files from the local project root and sends them in the optionalpartialsbundle. The bundle path omits the.paseo/partials/prefix.- Missing files, unsafe paths, symlinks, submodules, directories, duplicate or unexpected bundle entries, and nested includes are rejected.
- Manual configurations cannot use repository partials.
Deadlines
The trigger's max_runtime is the hard limit for the complete workflow run. Each step also has max_runtime and idle_timeout:
max_runtime: 2h
steps:
- id: classify
max_runtime: 2m
idle_timeout: 30s
- id: implement
max_runtime: 90m
idle_timeout: 10m
The effective step hard and idle deadlines are capped by the remaining trigger deadline. Meaningful daemon activity refreshes idle time, but cannot extend a hard deadline. Hub persists absolute deadlines, so a restart or deployment does not reset them. A step timeout fails the run; a trigger timeout stops later steps and interrupts a live agent.
Provider invocation
The provider removes its mention or marker before Hub parses leading declared input tokens. Slack and Discord place the inputs immediately after the bot mention. GitHub places them after the configured marker. Manual runs send the same string as the API input:
@Paseo repo=project investigate the failed sync
The first token that is not a declared input begins the prompt. The clean prompt is available as ${{ paseo.prompt }}. The raw provider message remains separate Activity evidence. See provider triggers for provider-specific marker and filter behavior.
Removed fields
Do not put execution fields directly on a trigger. environment, agent, prompt, timeout, idle_timeout, auto_archive, and allow_outputs are step fields now. The duration field is max_runtime; timeout is not an alias.
Next: Hub workflows for routing patterns and copyable configurations.