Skip to content

feat(context): scoped project context, convention imports and learning - #68

Draft
BIackFIame wants to merge 6 commits into
howdeploy:mainfrom
BIackFIame:stack/6-context
Draft

BIackFIame wants to merge 6 commits into
howdeploy:mainfrom
BIackFIame:stack/6-context

Conversation

@BIackFIame

@BIackFIame BIackFIame commented Sep 23, 2026 •

Copy link
Copy Markdown
Contributor

Goal

Give agents the project's own rules and preferences at launch, learn from explicit corrections, and show container routes across computers.

Behavior

  • Scoped project preferences are stored and delivered to agents through fixed launch routes, with a route preview.
  • Live convention imports from AGENTS.md, CLAUDE.md and Cursor rules (bounded frontmatter parsing), plus design token editing.
  • Learning from explicit corrections and accepted changes. Reviewed changes are checked against project conventions, and capsule patches can get an explicit read-only agent review.
  • Containers across computers: on-demand inventory, launch previews, and complete eligible routes launched through the shared policy gates.
  • Keyboard focus and control visibility fixes, and explicit delegation settings. The Browser card is unchanged from main, per the maintainer's browser freeze.

Documentation

docs/context.md, docs/container-overview.md, linked from both READMEs.

Verification

  • npm run typecheck passed. Full suite: 1397/1397; Even G2 companion tests (npm run test:even): 47/47.

Series

Each part is one commit on top of the previous one. Please merge them in order. Until #67 is merged, GitHub also shows the earlier parts here; review only the top commit ea26b70 (Commits tab → last commit).

Part PR Scope Lines
1 #63 Providers: Cursor, MiniMax Code, Devin, Antigravity +579/−90
2 #64 API keys, API profiles, agent delegation (MCP) +4275/−63
3 #65 Remote servers, placement, privacy tiers, accounts +6620/−40
4 #66 Isolation: capsules, worktrees, containers +5508/−839
5 #67 ACP, connection settings, remote containers +6827/−563
6 #68 Project context and learning +6148/−370
7 #69 Routing, reasoning effort, server preparation, sign-in +3122/−467
8 #70 Open issues and safe fixes from open PRs +306/−58

Compatibility with open upstream PRs

integration/stack-with-open-prs is this whole stack with #54–#62 merged on top and every conflict resolved. On that branch both TypeScript checks, 1492/1492 tests, npm run test:even (47/47) and electron-vite build pass.

I will rebase this stack onto whichever of these lands first.

🤖 Generated with Claude Code

BIackFIame and others added 6 commits September 23, 2026 17:16
Provider CLI resolution is driven by declarative command definitions
instead of assuming the executable matches the provider id. MiniMax
Code (`mcode`), Antigravity (`agy`) and Cursor resolve through the same
registry, known install directories, recheck and install links that howdeploy#52
introduced. Cursor prefers `cursor-agent`; a generic `agent` is accepted
only when its real path is verified as Cursor, because Grok also
installs an `agent` executable.

Each new agent gets normal and resume launches where the CLI documents
them, its YOLO flag only where one exists, launcher entries with a
settings migration, its provider mark and session restore. MiniMax Code
has no permission-bypass flag, so its YOLO profile launches the stock
CLI and says so. Antigravity restores as a fresh session because it has
no resumable id that CanvasTTY can persist.

Provider ids, labels and launcher order live in a dependency-free
`providerCatalog.ts` that `contracts.ts` re-exports, so the Even G2
companion bundle stays free of URLs outside its network whitelist; its
phone launcher lists the new agents too.

Lifecycle hooks are prepared only for providers that have a hook adapter, so
the new agents never write Grok's shared hook configuration.

ADR: docs/adr/ADR-20260921-provider-cli-command-definitions.md

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…tion

- Provider API keys are stored in the main process, encrypted with
  Electron safeStorage; the renderer only sees which keys exist.
- API profiles name a model backend (protocol, HTTPS base URL, key
  reference, default model) with built-in presets.
- Sessions carry role and parent metadata; restore drops orphaned
  subagents instead of resurrecting them.
- Per-provider capability descriptors state what CanvasTTY can really do
  with each agent, and agent control (spawn, send, observe, result,
  cancel, children) works over ordinary terminal sessions.
- An orchestration MCP surface rides the existing agent-bridge design:
  authenticated user-local socket, one-use bootstrap capabilities, scoping
  to the caller's own session subtree, and MCP injection for Claude,
  Codex, OpenCode, Kimi and Hermes. Only orchestrator sessions receive it;
  ordinary launches are unchanged.

ADR: docs/adr/ADR-20260921-orchestration-mcp-rides-agent-bridge.md

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…accounts

- Saved remote hosts use the system OpenSSH client (BatchMode, no stored
  passwords) for connectivity checks, remote terminals, CLI discovery,
  light load/memory metrics and per-host workspace mapping.
- Automatic placement applies hard filters (reachability, provider rules,
  workspace mapping, capacity) before ranking by load and free memory,
  and probes whether each provider's API answers from that host.
- spawn_agent can request a host, so subagents may run remotely.
- Data-handling tiers D0-D3 are enforced at spawn time, with host
  confidentiality ceilings and repository path policies.
- Several accounts per provider with subscription tiers; each account is
  bound to its own computer.
- Security fixes: lease supersession, an authentication hang and SSH
  option injection through host fields.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Bounded task capsules and workspace sandbox plans; protected mounts
  are rejected and hidden edits are retained.
- One live launch policy for create, restart and restore, enforcing
  account host affinity, budgets and privacy before every spawn.
- Bounded host probes that honour account placement.
- Accounts launch their bound model with isolated API credentials;
  Kimi homes and OpenCode API protocols are aligned.
- Durable isolated git worktrees that preserve agent output.
- Configured Docker/Podman containers run with durable owned
  workspaces, a fixed Python bootstrap that verifies limits, capabilities
  and mounts before exec, and cleanup fenced against pending creation.
- A responsive API profile editor and launcher controls for workspaces
  and containers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Local ACP conversations and lifecycle for Kimi, Cursor and MiniMax,
  with model selection confirmed before prompts are admitted.
- Settings gain account connections, host controls, explicit account
  launch routing and responsive navigation.
- Remote API agents run in containers with host-local credentials;
  retained remote output can be reviewed and exported.
- Capsules retain output, launch only verified selected files in owned
  containers, apply reviewed snapshots and run saved checks in isolated
  snapshots; orchestration is scoped to live parent authority.
- Initial tasks are delivered through literal startup arguments instead
  of typed PTY input.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Stored project preferences with scopes, delivered to agents through
  fixed launch routes with a route preview.
- Live imports of project conventions (AGENTS.md, CLAUDE.md, Cursor
  rules with bounded frontmatter parsing) and design token editing.
- Learning from explicit corrections and accepted changes, checks of
  reviewed changes against project conventions, and explicit read-only
  agent review of capsule patches.
- Container inventory and launch previews across computers, with
  complete eligible routes launched through the shared policy gates.
- Keyboard focus and control visibility fixes; explicit delegation. The
  Browser card is unchanged, per the maintainer's browser freeze.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant