mirror of
https://github.com/binaricat/Netcatty.git
synced 2026-11-16 20:11:08 +00:00
93 lines
5.5 KiB
Markdown
93 lines
5.5 KiB
Markdown
# Global Agent continuation: bounded QA recipe
|
|
|
|
This is a separate increment after the plugin platform foundation. The transport
|
|
review checkpoint is #4012 at `ea619555`; its isolated correction is `63f0572e0`.
|
|
The runtime continuation carries the correction through an ordinary feature-branch
|
|
merge. It is not merged to main or accepted for release.
|
|
|
|
## Reproduce the installable sample
|
|
|
|
From the exact runtime head reported in the handoff:
|
|
|
|
```sh
|
|
npm ci
|
|
npm run build:plugin-runtime-deps
|
|
node examples/plugins/global-agent/build.mjs
|
|
node packages/plugin-cli/dist/cli.js pack examples/plugins/global-agent/.package --out /tmp/netcatty-global-agent.ncpkg
|
|
sha256sum /tmp/netcatty-global-agent.ncpkg
|
|
```
|
|
|
|
The reproducible sample SHA-256 is
|
|
`f0edf43523845847d5dbb74b0c4d8cd3bfe8e0f89ca193f28140e6b47dc45ed0`.
|
|
Two independent package builds matched. Build scripts and tests are excluded
|
|
from the six-file installed package.
|
|
|
|
The sample reserves transcript space inside the actual 798-by-548-pixel plugin
|
|
viewport measured during native QA. In a scheduled native test environment, run
|
|
`npm run test:plugin-global-agent-layout` for the bounded render regression. It
|
|
loads the real sample HTML/CSS with synthetic history, including the fixture
|
|
notice, and checks transcript scrolling, reachable configuration, and visible
|
|
mouse Stop. It does not load the plugin script or start an Agent/provider. This
|
|
render check remains pending where the normal browser sandbox cannot start;
|
|
do not disable the sandbox to run it. Also verify the installed sample visually
|
|
at the 1188-by-848-pixel app window before accepting the viewport correction.
|
|
|
|
For the modal-history lifecycle regression, stop the synthetic stream, close
|
|
the modal with the host X, and reopen it without disabling/restarting the
|
|
plugin or waiting for five-minute lease expiry. Select the owned conversation,
|
|
confirm fresh empty targets, and Open. History must load without another model
|
|
request. Repeat with a new conversation. The sample command runtime retains
|
|
only its last host-issued chat handle and releases that exact lease on explicit
|
|
Open; it does not change core expiry, source ownership or duplicate-open guards.
|
|
|
|
## Native fixture acceptance (parent-scheduled GUI only)
|
|
|
|
1. Use an isolated synthetic profile, no real Notes, hosts, histories or keys.
|
|
Start `node scripts/plugin-global-agent-provider-fixture.mjs --port 9218`.
|
|
It performs no inference or outbound request and logs no bodies/headers.
|
|
2. Through normal host settings, configure an OpenAI-compatible Chat Completions
|
|
provider at `http://127.0.0.1:9218/v1`, model `global-agent-fixture`, with the
|
|
fixture-only literal `FIXTURE_ONLY_API_MARKER`. Do not use real credentials,
|
|
paid services, allowlist edits, debugger injection or the builtin AI sidebar.
|
|
3. Install the `.ncpkg` in Settings → Plugins and open its contributed Global
|
|
Agent Chat view. Verify light/dark/accent updates using existing theme tokens.
|
|
4. Choose Catty. Choose no targets, or only owned synthetic terminal fixtures,
|
|
then Open conversation. The fixture's default tool is `get_environment`; it
|
|
never requests a terminal command. Record Send → streamed result/usage and
|
|
`GET /fixture/status` counters. This proves a deterministic pipeline, not
|
|
real model inference.
|
|
5. Send `fixture:wait`, wait for output, press Stop. Verify aborted count rises
|
|
once and no late text appears. Capture screenshot/video with fixture labels.
|
|
6. Exercise Actions Ask using the existing in-app policy dialog: approve and
|
|
deny the scoped environment tool separately. Actions Deny permits model-only
|
|
chat with no tools. Agent-use Deny prevents dispatch. A policy change revokes
|
|
existing handles; reselect/reopen explicitly before another Send.
|
|
7. Close/reopen and disable/re-enable only this synthetic plugin. Reselect its
|
|
targets and reopen its owned conversation. History should survive, while the
|
|
private per-open actor ID is fresh. At five-minute expiry, the sample asks for
|
|
explicit reselection and keeps the draft, without resending or renewing scope.
|
|
8. Revoke/disable or lock while streaming and verify cleanup/no late events.
|
|
Disconnect/re-own a selected synthetic worker during selection and a turn;
|
|
stale selections must fail instead of binding a replacement connection.
|
|
|
|
Do not activate a configured real Claude backend in this fixture recipe. Claude
|
|
MCP's code/handler boundary is covered with synthetic tests; authenticated service
|
|
and genuine CLI acceptance remain unverified and require separately approved
|
|
access. Other backends are explicitly unsupported/unavailable. No background
|
|
service, blanket OS/Vault access, merge or release is implied.
|
|
|
|
## Evidence and limits
|
|
|
|
- Installed Catty path uses actual `AgentRuntime`, driver, main provider admission,
|
|
source policy and worker dispatcher, with JSDOM/in-process plugin transport and
|
|
synthetic workers. It proves selected B dispatch, stream, Stop, revocation and
|
|
history after runtime restart. This is not a native BrowserWindow sandbox test.
|
|
- Main/core tests cover source/session/resource substitution, scope expiry,
|
|
approval waits, worker lifecycle, cancellation, late completion, stable source
|
|
budgets, source-isolated history and no key serialization. Filesystem API reads
|
|
cannot access the core history root. Explicitly granted terminal commands still
|
|
have that terminal's native OS authority.
|
|
- No GUI ran in this executor. Native screenshots/video and independent runtime
|
|
review remain parent-owned gates. The exact-head CI result must be reported
|
|
separately from focused local evidence.
|