|
1 | | -# Repository-level Agent Guide |
2 | | - |
3 | | -Reply in the same language as the user. |
4 | | - |
5 | | -This is a TypeScript monorepo built for agent-assisted development. Keep the root `AGENTS.md` limited to hot-path rules: the project map, hard constraints, and workflow requirements — things every task needs to know. |
6 | | - |
7 | | -## Working Principles |
8 | | - |
9 | | -- Think from first principles. Start from real requirements, code facts, and verification results; if the goal is unclear, discuss it with the user first. |
10 | | -- Treat code, not documentation, as the source of truth. Unless the user explicitly says otherwise, do not read ordinary Markdown just to understand the implementation. |
11 | | -- Before making code changes, read the relevant code and the most recent constraints, and follow the nearest `AGENTS.md` in the directory tree. |
12 | | -- Keep changes focused. Do not slip in unrelated refactors along the way. |
13 | | -- When committing, do not add any co-author attribution, and do not reveal the identity of the agent in commit messages, PR descriptions, or any explanatory text. |
14 | | - |
15 | | -## Project Map |
16 | | - |
17 | | -- `apps/pythinker-code`: the CLI / TUI application. It consumes core capabilities through `@pymodel/pythinker-code-sdk` and must not depend directly on `@pymodel/agent-core`. When writing or modifying its terminal UI, use the `write-tui` skill (`.agents/skills/write-tui/SKILL.md`). |
18 | | -- the browser web UI: `apps/pythinker-web` (Vue 3 + Vite), the in-repo web client — REST + WS `/api/v1`, no `agent-core` dependency, see `apps/pythinker-web/AGENTS.md`. Its build output ships as the committed, prebuilt bundle `apps/pythinker-code/dist-web` (built with `pnpm --filter @pymodel/pythinker-web run build` and copied via `scripts/copy-web-assets.mjs`) — sync and commit the bundle in the same change whenever the web UI should ship differently. `apps/pythinker-code/scripts/check-web-assets.mjs` guards packaging against a missing bundle. To hack on the web UI against this repo's server, run `pnpm dev:server` here and point `pnpm dev:web` at it via `PYTHINKER_SERVER_URL`. |
19 | | -- `apps/vis`, `apps/vis/server`, `apps/vis/web`: visual debugging tools for sessions and replays. |
20 | | -- `apps/pythinker-inspect`: web inspector for the agent-gateway `/api/v1/debug` RPC surface — workspace/session browser, per-session transcript chat, per-scope Service panels, and the DI unit inspection view. See `apps/pythinker-inspect/AGENTS.md`. |
21 | | -- `packages/agent-core`: the unified agent engine, including Agent, Session, profile, skills, tools, plan, permission, background, records, the in-process DI service layer (`src/services/`), and other core capabilities. See `packages/agent-core/AGENTS.md`. |
22 | | -- `packages/agent-core-v2`: the DI × Scope agent engine behind agent-gateway. `LifecycleScope` has three tiers — `App` / `Session` / `Agent` (`app/scopes.ts`). Workspace resources use App-owned `WorkspaceInstance` / `Program` lifetimes, not a DI scope; callers resolve them through `IWorkspaceInstanceManager`. The engine also has the L3 unit layer (`Service`/`Fiber` units, collection contribution points, and the Feature seam in `src/features/`). See `packages/agent-core-v2/AGENTS.md` and use the `agent-core-dev` skill (`.agents/skills/agent-core-dev/SKILL.md`) when developing here. |
23 | | -- `packages/node-sdk`: the public TypeScript SDK and harness. |
24 | | -- `packages/kosong`: the LLM / provider abstraction layer. |
25 | | -- `packages/pyaos`: the execution environment and file/process abstractions. |
26 | | -- `packages/oauth`: Pythinker OAuth and managed auth utilities. |
27 | | -- `packages/telemetry`: shared client-side telemetry infrastructure. |
28 | | -- `packages/transcript`: the isomorphic transcript rendering data layer — L1 agent-granular store, L2 idempotent operations, L3 `off/turn/block/delta` subscription granularity, L4 framework-free view registry, plus turn-cursor pagination. Pure TypeScript (browser-safe, no engine imports); the sole owner of the transcript contract types (`src/contract/`) and the op-batch sequencing contract. See `packages/transcript/AGENTS.md`. |
29 | | -- `packages/agent-gateway`: the Pythinker Code server, backed by `@pymodel/agent-core-v2`; exposes sessions over REST + WebSocket (`/api/v1` + `/api/v1/ws`), plus the `/api/v1/debug/*` reflection RPC surface (`--debug-endpoints`, loopback bind + bearer auth). See `packages/agent-gateway/AGENTS.md`. |
30 | | -- `packages/klient`: the client SDK — a contract-driven facade over agent-core-v2 (`global.*` / `session(id).*` / `agent(id).*`, zod-validated); transport via subpath entry (`@pymodel/klient/ipc|memory`, both return the same `Klient`); also hosts the e2e suites. See `packages/klient/AGENTS.md`. |
31 | | -- `packages/tree-sitter-bash`: a pure-TypeScript bash parser (no runtime deps, no wasm); `parse(source, { timeoutMs, maxNodes })` runs under a deterministic budget and returns a discriminated `ParseResult` — callers must treat aborted/hasError trees as "cannot analyze" and degrade. Parser only, no safety judgments; see the package README's "Known differences" section. |
32 | | -- `packages/minidb`: the embedded JSON document store (`MiniDb`) behind agent-gateway's search index — snapshot + WAL persistence with an exclusive write lock, a larger-than-RAM full-text layer, and persistent index generations. See `packages/minidb/AGENTS.md`. |
33 | | -- `packages/protocol`: shared REST + WS protocol schemas (envelope, error codes, pagination, ws-control types). |
34 | | -- `packages/pi-tui`: vendored TUI library (upstream fork with local divergences; tests run with `node --test`, not vitest). See `packages/pi-tui/AGENTS.md`. |
35 | | -- `packages/acp-adapter` / `packages/acp-server`: Agent Client Protocol bridges — v1 engine (`@agentclientprotocol/sdk` pinned `^0.23.0`) and v2 engine via a `klient` memory-transport facade. |
36 | | -- `packages/server` and `packages/server-e2e` are empty leftover directories, excluded from the workspace — not packages. |
37 | | - |
38 | | -## Environment Requirements |
39 | | - |
40 | | -- **Node.js**: `>=24.15.0` (from the root `package.json` `engines`; `.nvmrc` is `24.15.0`, used by nvm / fnm / mise to pick the minimum recommended version). |
41 | | -- **pnpm**: `10.34.3` (from the root `package.json` `packageManager`). |
42 | | -- `pnpm install` will fail when the Node version is not satisfied, because `.npmrc` sets `engine-strict=true`. |
43 | | - |
44 | | -## Monorepo Workspace Maintenance |
45 | | - |
46 | | -- `pnpm-workspace.yaml` is the source of truth for workspace membership, but `flake.nix` also contains **hardcoded** `workspacePaths` and `workspaceNames` lists. |
47 | | -- **Whenever you add or remove a workspace package, you MUST update both `pnpm-workspace.yaml` and `flake.nix` — for every package, including leaf / test / e2e packages that nothing depends on.** |
48 | | - - `pnpm-workspace.yaml` uses globs (`packages/*`, `apps/*`), so most packages land there automatically; `flake.nix` is fully manual and is where omissions happen. |
49 | | - - Missing a path in `flake.nix`'s `workspacePaths` will silently drop files from the Nix build's `src` fileset. |
50 | | - - Missing a name in `flake.nix`'s `workspaceNames` will break `pnpmConfigHook` because dependencies for that workspace will not be fetched. |
51 | | -- The automated "Check flake.nix workspace sync" (`scripts/check-nix-workspace.mjs`) only validates the transitive dependency **closure of `@pymodel/pythinker-code`**. A leaf package outside that closure (e.g. an e2e package nobody imports) slips through even when it is missing from `flake.nix`. A green check is therefore NOT proof that `flake.nix` is fully in sync — keep it updated by hand on every add/remove, do not rely on the check to catch omissions. |
52 | | - |
53 | | -## General Coding Rules |
54 | | - |
55 | | -- `packages/agent-core-v2`, `packages/agent-gateway`, and `packages/transcript` are comment-free zones: no line/block comments; no JSDoc either, not even on exported symbols; the only exception is a load-bearing lint-suppression directive (`oxlint-disable` / `eslint-disable`), while other tooling directives (`@ts-expect-error`, …) stay banned. Enforced by `scripts/check-no-comments.mjs`, which runs as part of `pnpm lint`. |
56 | | -- For optional object properties, pass `undefined` directly instead of using conditional spread. |
57 | | - - YES: `{ user }` |
58 | | - - NO: `{ ...(user ? { user } : undefined) }` |
59 | | -- Optional object properties do not need to additionally allow `undefined` in the type. |
60 | | - - YES: `interface Options { user?: User }` |
61 | | - - NO: `interface Options { user?: User | undefined }` |
62 | | -- Internal methods with only a single parameter should not be turned into options objects just for stylistic uniformity. |
63 | | -- Except for a package's `index.ts`, other `index.ts` files should prefer `export * from './module';`. |
64 | | -- Do not add too many new test files. Prefer adding tests to the existing test file of the corresponding component or module. |
65 | | -- When a test fails because of a user modification, default to fixing the test first; do not change the implementation to satisfy an old test unless the implementation truly has a bug. |
66 | | -- Do not sacrifice code quality for external compatibility unless the user explicitly asks for it. Breaking changes go through changesets and a `major` bump, gated by the rule below. |
67 | | - |
68 | | -## Experimental Features |
69 | | - |
70 | | -- Gate a not-yet-public feature behind an experimental flag. Flags are env-driven and default off: `PYTHINKER_CODE_EXPERIMENTAL_<NAME>` toggles one, `PYTHINKER_CODE_EXPERIMENTAL_FLAG` enables all. Release by flipping the entry's `default` to `true`. |
71 | | - - `packages/agent-core` (v1): add the flag to the central registry at `packages/agent-core/src/flags/registry.ts`, then check it with `flags.enabled('my-feature')`. |
72 | | - - `packages/agent-core-v2` and agent-gateway modules: there is no central catalog — declare the flag in the owning domain via `registerFlagDefinition` at import time (see `packages/agent-core-v2/docs/flag.md`), then check it with `IFlagService.enabled(id)`. Current search-index-separation flags: `persistence_minidb_readmodel` (session read model, default on) and `search_worker` (global search worker host, default on). |
73 | | - |
74 | | -## Where to Update Instructions |
75 | | - |
76 | | -- Hard rules that affect almost every task: update the root `AGENTS.md`. |
77 | | -- Rules that only affect a specific directory: update the nearest sub-directory `AGENTS.md`. |
78 | | -- Project-map entries stay at 1–2 sentences; deep package docs live in the package's own `AGENTS.md`. |
79 | | -- Keep instruction updates focused and supported by code facts. |
80 | | - |
81 | | -## Workflow Requirements |
82 | | - |
83 | | -- Prefer `rg` / `rg --files` when reading code. |
84 | | -- When designing changes, follow existing boundaries and local patterns first. |
85 | | -- In public text and test data, replace real internal identifiers with neutral placeholders such as `example.com`, `example.test`, and `YOUR_API_KEY`. Before opening a PR, ask a read-only agent to audit the diff for context-specific internal identifiers. |
86 | | -- When creating a PR, the PR title must follow Conventional Commit style, e.g. `chore: remove legacy format commands`. |
87 | | -- When an AI agent opens or updates a PR, fill in `.github/pull_request_template.md` — link the related issue or explain the problem, then describe what changed. Do not leave placeholder text or submit a generic summary of the diff. |
88 | | -- Do not submit vague AI-generated PR text. The human author must understand the change well enough to explain the code, edge cases, and why the approach fits this repository. |
89 | | -- After finishing a task and before submitting a PR, you must run the `gen-changesets` skill (see `.agents/skills/gen-changesets/SKILL.md`) and generate a changeset under `.changeset/` according to its rules. |
90 | | -- Changesets must strictly follow the rules in `.agents/skills/gen-changesets/SKILL.md`: write one short user-facing sentence that states only what changed, and skip any change users cannot perceive. |
91 | | -- When generating a changeset, **never** decide on a `major` bump on your own — stop, explain, and get explicit user confirmation first; default to `minor`, fall back to `patch`. See `.agents/skills/gen-changesets/SKILL.md`. |
92 | | -- Prefer importing via `import ... from '#/...'`, which serves the same purpose as `import ... from '@/...'`. |
93 | | -- Do not commit throwaway scratch or exploratory files. Never stage: |
94 | | - - Agent working notes or handoff/summary documents (e.g. `HANDOVER-*.md`, `HANDOFF-*.md`, `handoff.md`). |
95 | | - - Throwaway UI/UX prototypes or design mockups (e.g. `*-designs.html`, `*-mockup.html`, `*-demo(s).html`) at the repo root or under a `design/` folder. The only tracked `.html` files should be Vite `index.html` entrypoints. |
96 | | - Before committing or opening a PR, run `git status` and `git diff --staged --stat` and remove anything matching these patterns. Put scratch work under `.tmp/` (gitignored) instead of the repo root or the source tree. |
| 1 | +@AGENTS.md |
0 commit comments