Files
agentic-mobile-control/openspec/specs/cloud-planner-proxy/spec.md
T
2026-07-15 09:43:14 +08:00

113 lines
7.0 KiB
Markdown

# cloud-planner-proxy Specification
## Purpose
Define the Cloud Control Plane's planner-decision proxy endpoint, which
allows a Host Agent to delegate AI Planner LLM calls to the cloud using
cloud-held provider credentials, removing the need for Host Agent-held
provider API keys.
## Requirements
### Requirement: Cloud Control Plane exposes an authenticated planner-decision endpoint
The Cloud Control Plane SHALL expose an internal endpoint that accepts an AI Planner tool-calling decision request from an authenticated Host Agent, and SHALL require the same host-scoped bearer credential already used for heartbeat, claim, lease renewal, and result reporting -- no separate credential or enrollment step.
#### Scenario: Authenticated host requests a planner decision
- **WHEN** a Host Agent presents its existing valid host-scoped credentials
with a planner-decision request
- **THEN** the Cloud Control Plane accepts and processes the request for
that host
#### Scenario: Unauthenticated or foreign-host request is rejected
- **WHEN** a request omits valid host-scoped credentials, or presents
credentials bound to a different host than the one referenced in the
request
- **THEN** the Cloud Control Plane rejects the request without invoking any
LLM provider
### Requirement: Endpoint resolves exactly one tool-call decision using cloud-held provider configuration
The Cloud Control Plane SHALL use its own configured LLM provider, model, and credentials -- not any value supplied by the requesting Host Agent -- to resolve a planner-decision request to exactly one tool name and one arguments object, within the active database-managed Provider profile's timeout. The endpoint SHALL resolve the active Provider profile for every request and use its provider, model, timeout, configured base URL, and encrypted cloud-held credential. It SHALL NOT read Cloud API planner Provider/model/timeout/API-key environment variables.
#### Scenario: Provider returns a usable decision
- **WHEN** the configured provider responds to a planner-decision request
with a tool call
- **THEN** the Cloud Control Plane returns exactly one resolved tool name
and arguments object to the requesting Host Agent
#### Scenario: Configured provider is unreachable or misconfigured
- **WHEN** the Cloud Control Plane's configured provider call fails (for
example, invalid credentials, provider error, or timeout)
- **THEN** the endpoint returns a structured failure response rather than a
fabricated decision, and does not crash the Cloud Control Plane process
#### Scenario: Database profile is the only planner configuration source
- **WHEN** the Cloud API process has legacy planner environment variables
- **THEN** subsequent planner-decision requests use only the active database
profile and do not read a legacy Provider credential for that decision
#### Scenario: Host supplies a different timeout
- **WHEN** a Host Agent's planner-decision request carries a timeout that differs
from the active Provider profile
- **THEN** the Cloud Control Plane uses the active Provider profile's timeout
for the provider call
### Requirement: Cloud-proxy transport removes the need for Host Agent-held provider credentials
A Host Agent using the cloud-proxy transport for its AI Planner SHALL be able to execute AI-planned tasks without any locally configured LLM provider API key.
#### Scenario: Host configured for cloud-proxy transport has no local provider key
- **WHEN** a Host Agent is configured to use the cloud-proxy transport and
has no `ANTHROPIC_API_KEY`/`OPENAI_API_KEY` set in its own environment
- **THEN** it can still obtain AI Planner decisions by calling the Cloud
Control Plane's planner-decision endpoint
### Requirement: Cloud Control Plane persists each resolved planner decision for later retrieval
The Cloud Control Plane SHALL, for each planner-decision request it successfully resolves to a tool-call decision, persist the request's system prompt, user prompt, resolved tool name and arguments, and an assigned step index scoped to the request's `task_id` and `attempt`, in addition to returning the decision to the requesting Host Agent. The Cloud Control Plane SHALL NOT persist screenshot bytes from these requests.
#### Scenario: A planner-decision request resolves successfully
- **WHEN** the Cloud Control Plane resolves a planner-decision request with task
context to a tool-call decision
- **THEN** it persists the request's system prompt, user prompt, resolved tool
name and arguments, and a step index for that task and attempt before
returning the decision to the Host Agent
#### Scenario: A planner-decision request fails
- **WHEN** the configured provider call fails and the endpoint returns a
structured failure response
- **THEN** no planner-decision row is persisted for that request
#### Scenario: A screenshot was included in the request
- **WHEN** a planner-decision request includes a screenshot
- **THEN** the screenshot bytes are used only to call the LLM provider and are
not written to the persisted decision log
### Requirement: Persisted planner decisions are retained within a bounded window
The Cloud Control Plane SHALL prune persisted planner decisions once their owning task has been in a terminal state for longer than a configurable retention window, so that indefinite operation does not cause unbounded growth of the decision log.
#### Scenario: A task's retention window has elapsed since reaching a terminal state
- **WHEN** a task reached a terminal state more than the configured retention
window ago
- **THEN** the Cloud Control Plane removes that task's persisted planner
decisions
#### Scenario: A task is still active or within its retention window
- **WHEN** a task is still active, or reached a terminal state less than the
configured retention window ago
- **THEN** its persisted planner decisions remain available for query
### Requirement: Cloud-side planner decision history is scoped to cloud-proxy transport
The Cloud Control Plane's persisted planner-decision log SHALL contain entries only for Hosts whose planner calls were routed through cloud-proxy transport; it SHALL NOT contain entries, synthesized or otherwise, for Hosts using direct-to-provider transport.
#### Scenario: A Host uses direct-to-provider transport
- **WHEN** a Host Agent configured for direct-to-provider transport executes an
assignment
- **THEN** no planner-decision entries for that assignment appear in the Cloud
Control Plane's persisted decision log
### Requirement: Planner-proxy failures do not silently substitute a default action
The Cloud Control Plane SHALL report a failure to the requesting Host Agent when it cannot resolve a planner-decision request to a valid tool call, rather than returning a default, guessed, or previously cached decision.
#### Scenario: Endpoint cannot resolve a decision
- **WHEN** the configured provider does not return a usable tool call for a
planner-decision request
- **THEN** the Cloud Control Plane's response indicates failure, and the
requesting Host Agent treats the planner call for that turn as failed