@sayknow-cli/coding-agent 0.7.24 → 0.7.25
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,13 @@
|
|
|
2
2
|
|
|
3
3
|
## [Unreleased]
|
|
4
4
|
|
|
5
|
+
## [0.7.25] - 2026-11-17
|
|
6
|
+
|
|
7
|
+
### Fixed
|
|
8
|
+
|
|
9
|
+
- Rendering a streamed multi-question `ask` call no longer throws `text.trim` errors before a question body arrives. Completed questions remain visible while later questions are still streaming; execution-time question validation is unchanged.
|
|
10
|
+
- Normal compaction checks no longer load the full transcript just to rule out an old overflow. Codex remote compaction switches to the existing summary path after a 60-second network deadline; user cancellation still stops compaction.
|
|
11
|
+
|
|
5
12
|
## [0.7.24] - 2026-11-13
|
|
6
13
|
|
|
7
14
|
### Changed
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"type": "module",
|
|
3
3
|
"name": "@sayknow-cli/coding-agent",
|
|
4
|
-
"version": "0.7.
|
|
4
|
+
"version": "0.7.25",
|
|
5
5
|
"description": "Sayknow-CLI CLI with read, bash, edit, write tools and session management",
|
|
6
6
|
"homepage": "https://sayknow-cli.com",
|
|
7
7
|
"author": "jaybeyond",
|
|
@@ -54,12 +54,12 @@
|
|
|
54
54
|
"@agentclientprotocol/sdk": "1.3.0",
|
|
55
55
|
"@babel/parser": "^7.29.3",
|
|
56
56
|
"@mozilla/readability": "^0.6.0",
|
|
57
|
-
"@sayknow-cli/stats": "0.7.
|
|
58
|
-
"@sayknow-cli/agent-core": "0.7.
|
|
59
|
-
"@sayknow-cli/ai": "0.7.
|
|
60
|
-
"@sayknow-cli/natives": "0.7.
|
|
61
|
-
"@sayknow-cli/tui": "0.7.
|
|
62
|
-
"@sayknow-cli/utils": "0.7.
|
|
57
|
+
"@sayknow-cli/stats": "0.7.25",
|
|
58
|
+
"@sayknow-cli/agent-core": "0.7.25",
|
|
59
|
+
"@sayknow-cli/ai": "0.7.25",
|
|
60
|
+
"@sayknow-cli/natives": "0.7.25",
|
|
61
|
+
"@sayknow-cli/tui": "0.7.25",
|
|
62
|
+
"@sayknow-cli/utils": "0.7.25",
|
|
63
63
|
"@puppeteer/browsers": "^2.13.0",
|
|
64
64
|
"@types/turndown": "5.0.6",
|
|
65
65
|
"@xterm/headless": "^6.0.0",
|
|
@@ -20,7 +20,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
|
|
|
20
20
|
"bridge.md": "# Bridge Protocol Reference (Experimental, Fail-Closed)\n\nBridge mode runs the coding agent as an experimental network control surface over\nHTTPS. The session-control surface is intentionally **fail-closed by default**\nwhile the bridge security model is hardened.\n\nDefault availability:\n\n- `GET /healthz` is available without auth and returns `{ \"status\": \"ok\" }`.\n- `GET /v1/help` is available without auth and reports the fail-closed endpoint\n matrix.\n- `POST /v1/handshake` remains authenticated, but the default response advertises\n no enabled session endpoints, no accepted capabilities, no accepted scopes, and\n no frame types.\n- `GET /v1/sessions/{session_id}/events` fails closed with\n `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/commands` fails closed with\n `403 endpoint_disabled` after bearer auth succeeds and before body parsing,\n command validation, scope checks, or dispatch.\n- `POST /v1/sessions/{session_id}/control:claim` and\n `POST /v1/sessions/{session_id}/control:disconnect` fail closed with\n `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/ui-responses/{correlation_id}` fails closed\n with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n or controller checks.\n- `POST /v1/sessions/{session_id}/host-tool-results/{correlation_id}` and\n `POST /v1/sessions/{session_id}/host-uri-results/{correlation_id}` fail closed\n with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n or host callback handling.\n\nThe implementation still contains the v1 protocol scaffolding and internal tests\nfor the previously enabled surface, but external clients must treat events,\ncommands, controller ownership, UI responses, host tool results, and host URI\nresults as unavailable unless a future release explicitly re-enables them.\n\nPrimary implementation:\n\n- `src/modes/bridge/bridge-mode.ts`\n- `src/modes/bridge/auth.ts`\n- `src/modes/bridge/event-stream.ts`\n- `src/modes/bridge/bridge-client-bridge.ts`\n- `src/modes/bridge/bridge-ui-context.ts`\n- `src/modes/shared/agent-wire/*` (protocol, scopes, handshake, command dispatch/validation, host bridges)\n- `packages/bridge-client/src/*`\n\n## Startup\n\n```bash\nskc --mode bridge [regular CLI options]\n```\n\nBehavior notes:\n\n- The bridge is served over **HTTPS only**. Startup refuses to bind without TLS\n configured (see Security and TLS). There is no unencrypted startup path.\n- `@file` CLI arguments are rejected in bridge mode (as in RPC mode).\n- Bridge mode reuses the RPC default-setting overrides and suppresses automatic\n session title generation.\n- One bridge process serves exactly **one live `AgentSession`**.\n- The default endpoint matrix disables session events, commands, controller\n ownership, UI responses, host tool results, and host URI results.\n\n### Configuration (environment variables)\n\nSee `docs/environment-variables.md` for the authoritative table. Summary:\n\n| Variable | Required | Default | Notes |\n| --- | --- | --- | --- |\n| `SKC_BRIDGE_TOKEN` | Yes | — | Bearer token for authenticated endpoints. **Secret — never commit.** |\n| `SKC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). |\n| `SKC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit.** |\n| `SKC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `SKC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `SKC_BRIDGE_SCOPES` | No | `prompt` | Parsed for internal compatibility, but default session endpoints are fail-closed. |\n\n## Security and TLS\n\nThe bridge is a network control surface, so it is **secure-by-default**:\n\n- **TLS is mandatory for every bind, including loopback.** Startup fails closed\n with a clear error if `SKC_BRIDGE_TLS_CERT` and `SKC_BRIDGE_TLS_KEY` are not\n both set. There is no plaintext fallback and no insecure/trust-bypass switch.\n- **Bearer token is mandatory** for every endpoint except `GET /healthz` and\n `GET /v1/help`.\n- The TypeScript SDK refuses bearer-token clients over non-`https` URLs by\n default. It allows plaintext only for `localhost`, `127.0.0.1`, or `[::1]`\n when the caller explicitly passes the localhost/test opt-in.\n- Session endpoints fail closed by default even when bearer auth and scopes are\n otherwise valid.\n\n## Handshake\n\n```\nPOST /v1/handshake (authenticated)\n```\n\nThe client sends its supported protocol version range, requested capabilities,\nand requested scopes. Version mismatch returns `status: \"rejected\"`,\n`reason: \"incompatible_version\"`. Malformed request bodies return\n`400 invalid_request`.\n\nIn the default fail-closed configuration, a successful authenticated\nhandshake returns:\n\n- `protocol_version` — the server protocol version (`BRIDGE_PROTOCOL_VERSION`, `2`).\n- `session_id` — the single session id this bridge serves.\n- `accepted_capabilities` — empty.\n- `accepted_scopes` — empty.\n- `unsupported` — every requested capability.\n- `endpoints` — all session endpoint descriptors present but empty strings.\n- `frame_types` — empty.\n\n## Fail-Closed Endpoint Matrix\n\nThe disabled endpoint matrix is:\n\n| Surface | Endpoint(s) | Default |\n| --- | --- | --- |\n| Events | `GET /v1/sessions/{session_id}/events?last_seq=<n>` | Disabled |\n| Commands | `POST /v1/sessions/{session_id}/commands` | Disabled |\n| Control | `POST /v1/sessions/{session_id}/control:claim`, `POST /v1/sessions/{session_id}/control:disconnect` | Disabled |\n| UI responses | `POST /v1/sessions/{session_id}/ui-responses/{correlation_id}` | Disabled |\n| Host tool results | `POST /v1/sessions/{session_id}/host-tool-results/{correlation_id}` | Disabled |\n| Host URI results | `POST /v1/sessions/{session_id}/host-uri-results/{correlation_id}` | Disabled |\n\nAuthenticated requests to disabled endpoints return:\n\n```json\n{ \"error\": \"endpoint_disabled\", \"endpoint\": \"commands\" }\n```\n\nThe `endpoint` value is one of `events`, `commands`, `control`, `uiResponses`,\n`hostToolResults`, or `hostUriResults`.\n\n## Protocol Catalog Kept for Internal Compatibility\n\nThe bridge protocol module still defines the v1 command and scope catalog so\nexisting internal tests can validate the dormant implementation and future\nre-enable work has a stable baseline.\n\nWhen internally enabled for compatibility tests, event replay still uses `last_seq` and the bounded replay reset marker `replay_window_exceeded`; command and UI response retries still use `Idempotency-Key`. These mechanisms are dormant for default external bridge clients because the endpoint matrix rejects the endpoints before they reach replay, body parsing, idempotency, scope, or dispatch logic.\n\nWorkflow-gate responses are part of the UI-response surface, not the dormant command surface: when internally enabled, an answerer responds to `workflow_gate` frame `wg_...` by posting `{ \"gate_id\": \"wg_...\", \"answer\": ... }` to `POST /v1/sessions/{session_id}/ui-responses/{gate_id}`. Gate answers are authorized by bearer auth, the `control` scope on this (default-disabled) endpoint, and the currently claimed controller owner token. `X-SKC-Bridge-Owner-Token` must match the claimed controller token; mismatches return `403 not_controller` and do not resolve the gate. `Idempotency-Key` is optional and is also forwarded as `idempotency_key` when supplied by SDK helpers.\n\n### Scopes\n\nThe configurable scope set (`BRIDGE_COMMAND_SCOPES`) is:\n\n- `prompt`\n- `control`\n- `bash`\n- `export`\n- `session`\n- `model`\n- `message:read`\n- `host_tools`\n- `host_uri`\n- `admin`\n\nThe mandatory compliance floor (`MANDATORY_FLOOR_COMMAND_SCOPES`) remains\n`prompt` for the dormant command surface. Because commands are disabled by the\nendpoint matrix, the default handshake advertises no accepted scopes.\n\n### Command catalog and scope mapping\n\n| Command | Scope |\n| --- | --- |\n| `prompt` | `prompt` |\n| `steer` | `prompt` |\n| `follow_up` | `prompt` |\n| `abort` | `prompt` |\n| `abort_and_prompt` | `prompt` |\n| `new_session` | `session` |\n| `get_state` | `message:read` |\n| `set_todos` | `control` |\n| `set_host_tools` | `host_tools` |\n| `set_host_uri_schemes` | `host_uri` |\n| `get_pending_workflow_gates` | `message:read` |\n| `set_capabilities` | `control` |\n| `set_model` | `model` |\n| `set_default_model_selection` | `model` |\n| `cycle_model` | `model` |\n| `get_available_models` | `model` |\n| `set_thinking_level` | `model` |\n| `cycle_thinking_level` | `model` |\n| `set_steering_mode` | `control` |\n| `set_follow_up_mode` | `control` |\n| `set_interrupt_mode` | `control` |\n| `compact` | `control` |\n| `set_auto_compaction` | `control` |\n| `set_auto_retry` | `control` |\n| `abort_retry` | `control` |\n| `bash` | `bash` |\n| `abort_bash` | `bash` |\n| `get_session_stats` | `message:read` |\n| `export_html` | `export` |\n| `switch_session` | `session` |\n| `branch` | `session` |\n| `get_branch_messages` | `session` |\n| `get_last_assistant_text` | `message:read` |\n| `set_session_name` | `session` |\n| `handoff` | `admin` |\n| `get_messages` | `message:read` |\n| `get_login_providers` | `admin` |\n| `login` | `admin` |\n| `negotiate_unattended` | `control` |\n| `workflow_gate_response` | `control` |\n\n### Dormant capabilities and frame types\n\nThese names remain in the protocol code for future compatibility and internal\nconformance tests, but they are not advertised by the default fail-closed\nhandshake:\n\nCapabilities: `events`, `prompt`, `permission`, `elicitation`, `ui.declarative`,\n`host_tools`, `host_uri`, `workflow_gate`.\n\nFrame types: `ready`, `event`, `response`, `ui_request`, `permission_request`,\n`host_tool_call`, `host_uri_request`, `reset`, `workflow_gate`, `error`.\n\n## UI Capability Parity\n\nBridge UI parity remains **semantic, not pixel-perfect** when the dormant UI\nsurface is explicitly enabled for internal validation. Local-only UI capabilities\ncontinue to report typed unsupported results instead of silent defaults:\n\n- `ui.terminal_input`\n- `ui.widget.component`\n- `ui.footer.component`\n- `ui.header.component`\n- `ui.custom.component`\n- `ui.editor.get_text`\n- `ui.editor.component`\n- `ui.tools_expanded`\n- Theme switching is unsupported (`setTheme` returns `{ success: false }`).\n\n## SDK Usage\n\n`@sayknow-cli/bridge-client` exposes `BridgeClient` with handshake, command\nhelpers mirroring the full RPC command catalog, an `events()` async generator,\ncontroller/UI/host-callback helpers, and an idempotency-key helper. The bridge\nsession-control surface remains fail-closed by default, so against an\nunconfigured bridge those helpers should be expected to fail because the server\nendpoint matrix disables the corresponding session endpoints until they are\nexplicitly enabled.\n\n`BridgeClient.respondGate(sessionId, gateId, ownerToken, answer, options)` posts to the fail-closed UI-response endpoint and returns the gate resolution envelope emitted by the bridge. It deliberately does not send `workflow_gate_response` through `/commands`. Gate answers are authorized by bearer auth, the `control` scope on the (by-default-disabled) `ui-responses` endpoint, and the current controller owner token; unauthorized owner-token attempts return `403 not_controller` without resolving the gate.\n\n> Response typing: in this experimental version, `command()` and the typed\n> command helpers return `Promise<unknown>`. Callers narrow the response\n> themselves. Importing `@sayknow-cli/coding-agent` internal `rpc-types` into the\n> SDK is intentionally avoided to preserve the package boundary; stable shared\n> protocol response types are tracked as follow-up work.\n\n## Limitations\n\n- **Single session per process.** A bridge process serves exactly one live\n `AgentSession`. The `session_id` is present in every frame and endpoint for\n ordering and future additive multiplexing, but multi-session multiplexing is\n **not** implemented in v1.\n- Session events, commands, controller ownership, UI responses, host tool\n results, and host URI results are disabled by default.\n- Coarse per-token scopes only (no fine-grained per-command policy yet).\n- UI parity is semantic, not pixel-perfect (see UI Capability Parity).\n\n## Hermes/Claw orchestration layering\n\nFor Hermes/Claw-style orchestration, treat `skc` as an external runner. The orchestration agent should choose or create the repository checkout first, preferably a dedicated Git worktree for branch-local work, then launch or attach a leader session with `skc --tmux` from that directory. SKC is not embedded runtime injection into Hermes, Claw Code, or another coding tool.\n\nPublic orchestration boundaries:\n\n1. Choose the repo/worktree and branch that will own changes, logs, and review evidence.\n2. Start or attach the SKC leader with `skc --tmux` from that directory. If you want SKC to create the sibling worktree, use `skc --tmux --worktree <branch-like-name>`; the argument is a worktree/branch name, not a filesystem path.\n3. Submit the workflow appropriate to the task: `/skill:deep-interview` for requirements discovery, `/skill:ralplan` for plan consensus, and `skc ultragoal ...` for durable goal tracking through execution and verification.\n4. Use `skc team ...` only when coordinated parallel tmux workers help with implementation or verification; single-lane work should stay in the leader session.\n5. Collect the handoff state: whether the session stopped cleanly, changed files, commands/checks run, failures, unresolved risks, and evidence summaries.\n\nBridge mode remains the public remote-control protocol for an already-running SKC session, but the session-control endpoints are fail-closed by default. Keep lifecycle, worktree selection, and evidence policy above the bridge frames, and avoid documenting private deployment, routing, or credential internals. Introducing another authenticated remote-control protocol for the same purpose should require ADR-level rationale.\n\nThe same external-runner workflow is summarized in the README section [Using SKC with other coding agents](../README.md#using-skc-with-other-coding-agents).\n",
|
|
21
21
|
"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `sayknow-cli` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nSayknow-CLI (`skc`) is centered on `packages/coding-agent/`. The public workflow surface is intentionally fixed at four source-bundled skills and four public role subagents. Runtime state, specs, plans, goals, team state, and local overrides live under `.skc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/skc/skills/<name>/SKILL.md\n```\n\nPublic role subagent prompts are embedded from:\n\n```text\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\nThe runtime can still discover project/user overrides, but the bundled defaults are loaded from source so a missing project `.skc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `skc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `skc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, and ACP modes; external machine clients use the SDK WebSocket interface.\n- `packages/coding-agent/src/sdk/session.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@sayknow-cli/agent-core` agent.\n- `packages/coding-agent/src/tools/index.ts` is the built-in tool registry for file/code/runtime tools such as read, bash, edit, AST tools, eval, find/search, LSP, browser, task/subagent, recipe, IRC, todo, web search, and write. Memory backends are private integrations, not public coding-harness tools.\n- `packages/coding-agent/src/defaults/skc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n- `packages/coding-agent/src/coordinator/contract.ts` defines the transport-neutral third-party coordinator contract used by `skc mcp-serve coordinator`, `skc coordinator`, and `skc setup hermes`.\n- `packages/coding-agent/src/coordinator-mcp/server.ts` implements the outward MCP adapter for bot/coordinator integrations, including session start/register, turn state, question answering, status reports, and artifact reads.\n- `docs/external-control-readiness.md` classifies the public external-control surfaces: SDK WebSocket for live session control, Coordinator MCP for multi-session control planes, and ACP for editor/ACP clients. `docs/bot-integration.md` is the end-to-end guide for external controller authors.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@sayknow-cli/ai`.\n\n- `packages/agent/src/index.ts` exports the `Agent`, loop APIs, append-only context, compaction, telemetry, proxy utilities, thinking helpers, and shared types.\n- `packages/agent/src/agent-loop.ts` owns the turn loop: transform context, call the model stream, execute tool calls, append tool results, and emit lifecycle events.\n- `packages/agent/src/agent.ts` wraps the loop with mutable state, subscriptions, prompt/continue/abort APIs, queues, provider session state, telemetry, and state mutation helpers.\n- `packages/agent/src/types.ts` defines `AgentMessage`, `AgentTool`, loop config, event, and runtime state contracts.\n\n### `packages/tui/`\n\nTerminal UI framework used by the CLI.\n\n- `packages/tui/src/index.ts` exports components, keybindings, autocomplete, terminal abstractions, image support, TUI core, and utilities.\n- `packages/tui/src/tui.ts` manages component rendering, focus, overlays, terminal dimensions, diff state, and synchronized output.\n- `packages/tui/src/terminal.ts` abstracts terminal lifecycle, dimensions, cursor controls, title/progress, Kitty protocol state, and appearance notifications.\n- `packages/tui/README.md` documents the component model and built-in components such as text, input, editor, markdown, loaders, select/settings lists, spacer, image, box, and container.\n\n### `packages/natives/` and Rust crates\n\nNative helper layer exposed through N-API.\n\n- `packages/natives/package.json` exports `native/index.js` and generated TypeScript definitions.\n- `packages/natives/native/loader-state.js` resolves platform/CPU-specific native binaries and validates package/native version alignment.\n- `crates/pi-natives/src/lib.rs` is the N-API root for appearance, AST search/editing, clipboard, filesystem scan/cache, grep/glob, syntax highlighting, HTML-to-Markdown, keyboard parsing, process/PTY/shell support, SIXEL, code summarization, token counting, text measurement/wrapping/truncation, workspace scanning, power assertions, and isolation helpers.\n- `crates/pi-shell/src/lib.rs` exposes brush-based shell execution primitives used by the native shell adapter.\n- `crates/pi-shell/src/shell.rs` implements persistent and one-shot shell execution, streaming, environment handling, cancellation, and output minimizer telemetry.\n- `crates/pi-shell/src/fixup.rs` performs conservative AST-based bash command fixups.\n- `crates/pi-natives/src/pty.rs` implements interactive PTY sessions.\n\n### `packages/utils/`\n\nShared TypeScript utilities.\n\n- `packages/utils/src/index.ts` exports abortable/async helpers, color/env/dir utilities, fetch retry, formatting, frontmatter, glob helpers, JSON helpers, logging, MIME detection, prompt rendering, process-tree helpers, sanitization, streams, temp files, tab spacing, type guards, and executable lookup.\n- `packages/utils/src/ptree.ts` and `packages/utils/src/procmgr.ts` wrap native process helpers for ergonomic TypeScript use.\n\n### `packages/stats/`\n\nLocal observability dashboard for session and model usage.\n\n- `packages/stats/src/index.ts` exposes the `skc-stats` CLI entrypoint and exports aggregation/server APIs.\n- `packages/stats/src/aggregator.ts` parses session-derived request metrics and writes aggregated data through SQLite.\n- `packages/stats/src/server.ts` serves local dashboard API routes and static SPA assets.\n- `packages/stats/src/types.ts` and `packages/stats/src/shared-types.ts` define dashboard and aggregate metric shapes.\n\n### `packages/typescript-edit-benchmark/`\n\nPrivate benchmark package for TypeScript edit tasks.\n\n- `packages/typescript-edit-benchmark/package.json` exposes `typescript-edit-benchmark` and depends on the coding-agent, agent-core, ai, tui, utils, diff, prettier, and Babel tooling.\n- `packages/typescript-edit-benchmark/src/index.ts` is the benchmark CLI: it resolves fixtures, loads tasks, runs edit attempts, records progress, and writes reports/conversation dumps under `runs/`.\n\n## Python packages\n\n### External machine interfaces\n\nExternal machine clients use the SDK WebSocket interface documented in `docs/sdk.md`. Coordinator MCP supplies multi-session orchestration, while ACP remains the stdio editor protocol. The former Python RPC client and bot integration paths were removed with the RPC ingress mode.\n\n## Runtime flow\n\nA normal CLI session starts in `packages/coding-agent/src/cli.ts`, routes through command handling, then reaches `packages/coding-agent/src/main.ts`. `main.ts` converts CLI/runtime settings into `CreateAgentSessionOptions` and calls `createAgentSession()` in `packages/coding-agent/src/sdk/session.ts`.\n\nThe SDK builds the session context, loads the default skills, creates built-in tools, resolves model/auth state through `@sayknow-cli/ai`, constructs the system prompt, and instantiates `@sayknow-cli/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected interactive TUI, print, or ACP mode while exposing external control through the SDK WebSocket interface.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-skc-definitions.test.ts\n```\n\nFor broader TypeScript verification, use the root script:\n\n```sh\nbun run check:ts\n```\n\nDo not use `tsc` or `npx tsc` directly in this repository.\n",
|
|
22
22
|
"codegraph-custom-tool.md": "# CodeGraph as a custom tool\n\n[CodeGraph](https://github.com/colbymchenry/codegraph) is a local, language-agnostic\ncode knowledge graph for AI agents. It pre-indexes symbols, call edges, and\ndependencies in a project so an agent can answer structural questions (\"how does X\nwork\", \"who calls X\", \"what breaks if I change X\") in a few graph queries instead\nof crawling files with `search`/`read`.\n\nThis guide shows how to wire CodeGraph into SKC through the **custom-tool extension\npath** — no core changes, no built-in provider. SKC intentionally keeps third-party\nCLI integrations like this in the user/project extension layer rather than bundling\nthem, so you own the integration and its lifecycle.\n\n> CodeGraph integrates with other agents over MCP, but this guide wires it as a SKC\n> custom tool around CodeGraph's local **CLI** — it does not add an MCP server or a\n> built-in provider. For how SKC treats MCP servers in standalone sessions, see\n> [`standalone-mcp.md`](standalone-mcp.md).\n\n## 1. Install and index\n\n```bash\n# Install the CodeGraph CLI (or use the install script from CodeGraph's README).\nnpm i -g @colbymchenry/codegraph\n\n# Build the local index for a project.\ncd your-project\ncodegraph init\n```\n\n`codegraph init` creates a local `.codegraph/` directory. No data leaves your\nmachine — it is a local SQLite index.\n\n## 2. Add the custom tool\n\nSKC discovers custom tools from a `tools/` directory in its config dirs:\n\n- **Project-scoped**: `<project>/.skc/tools/`\n- **User-scoped (all projects)**: `~/.skc/agent/tools/`\n\nA `*.ts` tool file's default export is a factory `(pi) => CustomTool`. The factory\nreceives an API (`pi`) with members such as `exec`, `cwd`, `zod`, and `logger` — so\nthe tool needs no imports from SKC internals.\n\nSave the following as `.skc/tools/codegraph.ts` (project) or\n`~/.skc/agent/tools/codegraph.ts` (user):\n\n```typescript\n/**\n * CodeGraph custom tool for sayknow-cli (SKC).\n *\n * Wraps the local CodeGraph CLI (https://github.com/colbymchenry/codegraph) so the\n * agent can query a project's code knowledge graph instead of crawling files.\n *\n * It only runs CodeGraph's query-style (read-only) subcommands and never edits your\n * source files. It does not run indexing or sync commands. (CodeGraph maintains its\n * own local `.codegraph/` index via its own CLI; this tool only reads from it.)\n *\n * Prereqs: `npm i -g @colbymchenry/codegraph` and `codegraph init` in the project.\n */\nimport type { CustomToolFactory } from \"@sayknow-cli/coding-agent\"; // optional: editor types only\n\nconst CODEGRAPH_CLI = \"codegraph\";\nconst TIMEOUT_MS = 60_000;\nconst SEARCH_LIMIT_DEFAULT = 10;\nconst MAX = 100;\n\nconst codegraph: CustomToolFactory = (pi) => {\n\tconst z = pi.zod;\n\n\tconst parameters = z\n\t\t.object({\n\t\t\top: z\n\t\t\t\t.enum([\"explore\", \"search\", \"callers\", \"callees\", \"impact\", \"status\"])\n\t\t\t\t.describe(\n\t\t\t\t\t\"explore: context (relevant source + call paths) for a natural-language query — prefer for 'how does X work'; search: full-text symbol search (target=query); callers: who calls target; callees: what target calls; impact: blast radius of changing target; status: index health (no target).\",\n\t\t\t\t),\n\t\t\ttarget: z\n\t\t\t\t.string()\n\t\t\t\t.optional()\n\t\t\t\t.describe(\n\t\t\t\t\t\"For explore: a natural-language query or symbol(s). For callers/callees/impact: a symbol name. For search: the query. Omit for status.\",\n\t\t\t\t),\n\t\t\tlimit: z.number().int().min(1).max(MAX).optional().describe(`Max search results (default ${SEARCH_LIMIT_DEFAULT}).`),\n\t\t\tmaxFiles: z.number().int().min(1).max(MAX).optional().describe(\"For explore: cap files whose source is included.\"),\n\t\t})\n\t\t.strict();\n\n\ttype Params = import(\"zod/v4\").infer<typeof parameters>;\n\n\tfunction buildArgs(params: Params): string[] {\n\t\tif (params.op === \"status\") return [\"status\", pi.cwd, \"--json\"];\n\t\tconst target = params.target?.trim();\n\t\tif (!target) throw new Error(`codegraph ${params.op} requires a non-empty \"target\".`);\n\t\tif (params.op === \"search\") {\n\t\t\tconst limit = Math.min(params.limit ?? SEARCH_LIMIT_DEFAULT, MAX);\n\t\t\treturn [\"query\", target, \"--json\", \"--limit\", String(limit), \"--path\", pi.cwd];\n\t\t}\n\t\tif (params.op === \"explore\") {\n\t\t\tconst args = [\"explore\", target, \"--path\", pi.cwd];\n\t\t\tif (params.maxFiles !== undefined) args.push(\"--max-files\", String(params.maxFiles));\n\t\t\treturn args;\n\t\t}\n\t\treturn [params.op, target, \"--json\", \"--path\", pi.cwd];\n\t}\n\n\tfunction ref(r: { name: string; kind: string; filePath: string; startLine: number }): string {\n\t\treturn ` - ${r.name} (${r.kind}) — ${r.filePath}:${r.startLine}`;\n\t}\n\n\tfunction render(params: Params, stdout: string): string {\n\t\tif (params.op === \"explore\") return stdout.trim() || `No exploration results for \"${params.target?.trim() ?? \"\"}\".`;\n\t\tlet data: any;\n\t\ttry {\n\t\t\tdata = JSON.parse(stdout);\n\t\t} catch {\n\t\t\tthrow new Error(`codegraph ${params.op} returned unparseable output.`);\n\t\t}\n\t\tif (params.op === \"search\") {\n\t\t\tconst hits = data as Array<{ node: any }>;\n\t\t\tif (hits.length === 0) return `No symbols matched \"${params.target?.trim() ?? \"\"}\".`;\n\t\t\treturn [\n\t\t\t\t`${hits.length} symbol(s) matching \"${params.target?.trim() ?? \"\"}\":`,\n\t\t\t\t...hits.map(({ node }) => {\n\t\t\t\t\tconst exp = node.isExported ? \" [exported]\" : \"\";\n\t\t\t\t\tconst sig = node.signature ? ` ${node.signature}` : \"\";\n\t\t\t\t\treturn ` - ${node.name} (${node.kind})${sig}${exp} — ${node.filePath}:${node.startLine}`;\n\t\t\t\t}),\n\t\t\t].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"callers\") {\n\t\t\tconst list = data.callers ?? [];\n\t\t\treturn list.length === 0\n\t\t\t\t? `No callers found for \"${data.symbol}\".`\n\t\t\t\t: [`${list.length} caller(s) of \"${data.symbol}\":`, ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"callees\") {\n\t\t\tconst list = data.callees ?? [];\n\t\t\treturn list.length === 0\n\t\t\t\t? `\"${data.symbol}\" has no recorded callees.`\n\t\t\t\t: [`${list.length} callee(s) of \"${data.symbol}\":`, ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"impact\") {\n\t\t\tconst header = `Impact of changing \"${data.symbol}\" (depth ${data.depth}): ${data.nodeCount} node(s), ${data.edgeCount} edge(s) affected.`;\n\t\t\tconst list = data.affected ?? [];\n\t\t\treturn list.length === 0 ? header : [header, \"Affected:\", ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\t// status\n\t\tif (!data.initialized) return `CodeGraph is not initialized for ${data.projectPath}. Run \\`codegraph init\\`.`;\n\t\tconst lines = [\n\t\t\t`CodeGraph index for ${data.projectPath}:`,\n\t\t\t` files: ${data.fileCount}, nodes: ${data.nodeCount}, edges: ${data.edgeCount}`,\n\t\t];\n\t\tif (data.languages?.length) lines.push(` languages: ${data.languages.join(\", \")}`);\n\t\tconst p = data.pendingChanges;\n\t\tif (p && (p.added || p.modified || p.removed)) lines.push(` pending sync: +${p.added} ~${p.modified} -${p.removed}`);\n\t\treturn lines.join(\"\\n\");\n\t}\n\n\treturn {\n\t\tname: \"codegraph\",\n\t\tlabel: \"CodeGraph\",\n\t\tdescription:\n\t\t\t\"Query the project's CodeGraph code knowledge graph (symbols, callers, callees, impact, and an 'explore' context query) via the local codegraph CLI. Read-only with respect to your source. Prefer over search/read for structural questions. Requires `codegraph init` to have been run in the project.\",\n\t\tparameters,\n\t\tstrict: true,\n\t\tasync execute(_id: string, params: Params, _onUpdate: unknown, _ctx: unknown, signal?: AbortSignal) {\n\t\t\tlet result: { stdout: string; stderr: string; code: number };\n\t\t\ttry {\n\t\t\t\tresult = await pi.exec(CODEGRAPH_CLI, buildArgs(params), { cwd: pi.cwd, signal, timeout: TIMEOUT_MS });\n\t\t\t} catch (e) {\n\t\t\t\tconst msg = e instanceof Error ? e.message : String(e);\n\t\t\t\tif (/not found|enoent/i.test(msg)) {\n\t\t\t\t\tthrow new Error(\"The `codegraph` CLI is not installed. Install it: npm i -g @colbymchenry/codegraph\");\n\t\t\t\t}\n\t\t\t\tthrow e;\n\t\t\t}\n\t\t\tif (result.code !== 0) {\n\t\t\t\tconst err = result.stderr.toLowerCase();\n\t\t\t\tif (err.includes(\"not initialized\") || err.includes(\".codegraph\") || err.includes(\"no index\")) {\n\t\t\t\t\tthrow new Error(\"CodeGraph is not initialized for this project. Run `codegraph init` in the project root.\");\n\t\t\t\t}\n\t\t\t\tthrow new Error(result.stderr.trim() || \"codegraph failed with no diagnostic output.\");\n\t\t\t}\n\t\t\treturn { content: [{ type: \"text\", text: render(params, result.stdout) }] };\n\t\t},\n\t};\n};\n\nexport default codegraph;\n```\n\nThe `import type` line is optional — it only provides editor types when SKC is\nresolvable from your tool file. It is erased at runtime, so the tool loads fine\nwithout it.\n\n## 3. Use it\n\nStart SKC in the project. The `codegraph` tool is now available to the model. Ask\na structural question and it will call the tool, for example:\n\n- `codegraph` with `{ \"op\": \"explore\", \"target\": \"how requests are routed\" }` can\n return relevant source plus graph context in one call.\n- `{ \"op\": \"callers\", \"target\": \"MyClass.handle\" }` lists callers.\n- `{ \"op\": \"impact\", \"target\": \"parseConfig\" }` shows what a change would affect.\n- `{ \"op\": \"status\" }` reports index health.\n\n## Operations\n\n| `op` | `target` | Description |\n| --- | --- | --- |\n| `explore` | natural-language query | Context query: relevant symbols' source plus graph context (CodeGraph's `explore`). `maxFiles` caps included source. |\n| `search` | query | Full-text symbol search (`limit`, default 10). |\n| `callers` | symbol | Functions/methods that call the symbol, including dynamic dispatch. |\n| `callees` | symbol | Functions/methods the symbol calls. |\n| `impact` | symbol | Blast radius of changing the symbol. |\n| `status` | — | Index health: file/node/edge counts, languages, pending sync. |\n\n## Notes\n\n- **Read-only with respect to your code.** The tool only runs CodeGraph's\n query-style subcommands; it never edits your files and does not run indexing or\n sync commands. CodeGraph maintains its own local `.codegraph/` index via its CLI.\n If results look stale or `status` reports pending changes, refresh the index with\n CodeGraph's CLI (e.g. `codegraph sync`) outside SKC.\n- **Safe argument handling.** The example spawns CodeGraph with argv arrays via\n `pi.exec` (no shell), `op` is constrained to a fixed enum, and numeric inputs are\n capped — there is no shell interpolation of model-provided values.\n- **Scope.** Use a project-scoped file to limit the tool to one repo, or a\n user-scoped file to make it available everywhere `codegraph init` has been run.\n- **Naming.** The tool registers as `codegraph`; rename it in the file if it\n collides with another tool in your setup.\n- **Fallback.** If the graph reports a symbol is missing, a file is flagged as\n pending sync, or you need a non-structural text search, refresh the CodeGraph\n index outside SKC or fall back to `read`/`search`.\n- For background on how SKC treats external tools and MCP servers in standalone\n sessions, see [`standalone-mcp.md`](standalone-mcp.md).\n",
|
|
23
|
-
"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n - `type: \"compaction\"`\n - `summary`, optional `shortSummary`\n - `firstKeptEntryId` (compaction boundary)\n - `tokensBefore`\n - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n - `type: \"branch_summary\"`\n - `fromId`, `summary`\n - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in four ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n entry: 0 1 2 3 4 5 6 7 8 9\n ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n └────────┬───────┘ └──────────────┬──────────────┘\n messagesToSummarize kept messages\n ↑\n firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n entry: 0 1 2 3 4 5 6 7 8 9 10\n ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n └──────────┬──────┘ └──────────────────────┬───────────────────┘\n not sent to LLM sent to LLM\n ↑\n starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n ↑ ↑ └─────────────────┬────────────────┘\n prompt from cmp messages from firstKeptEntryId\n```\n\n### Overflow-retry vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n - The failing assistant error message is removed from active agent state before retry.\n - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow.\n - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold maintenance**\n - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n - Tool-output pruning runs instead of compaction only when it leaves enough headroom under the threshold (see [Pre-compaction pruning](#pre-compaction-pruning)).\n - Context promotion is tried before compaction.\n - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n - With `compaction.strategy: \"handoff\"`, threshold maintenance starts a new handoff session instead of writing a compaction entry; if handoff returns no document without aborting, it falls back to context-full compaction.\n - On success, if `compaction.autoContinue !== false` and the triggering answer was unfinished (it called tools or stopped for a reason other than `stop`), schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`. A finished answer is compacted without a continuation turn.\n\n- **Mid-run maintenance** (inside a tool loop)\n - Trigger: between tool-loop steps, against `resolveMidRunThresholdTokens(...)`. When the model's usable window (`contextWindow - reserve`) exceeds the default ceiling (300K), a lower configured threshold is deferred to the ceiling, so a 150K threshold on a 1M-token model compacts at answer boundaries instead of mid-task. Smaller windows use the configured threshold as-is.\n - The run ends with `stopReason: \"maintenance\"` and the session resumes it with `agent.continue()` on the rewritten context.\n - After a compaction, if an SKC workflow skill (`deep-interview`, `ralplan`, `ultragoal`, `team`) invoked on the current branch is active and its instructions are no longer in context, they are re-attached as a hidden `workflow-skill-context` message. The same restore runs before the next prompt after an answer-boundary compaction.\n\n- **Idle maintenance**\n - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\nPruning rewrites history the provider has already cached, so the next request re-writes almost the whole prompt cache. At the compaction threshold a prune therefore runs only when it brings the context down to at most `100 - compaction.pruneMinHeadroomPercent` percent of the threshold (`shouldPruneAtThreshold`; default `20`, so 240K under the 300K ceiling). A smaller prune would reach the threshold again within a few requests and pay the rewrite each time, so the session compacts instead. `compaction.pruneMinHeadroomPercent: 0` accepts any prune that gets back under the threshold.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI code provider models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n ┌─ B ─ C ─ D (old leaf, being abandoned)\n A ───┤\n └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n ┌─ B ─ C ─ D ─ [summary of B,C,D]\n A ───┤\n └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n - overflow path emits `Context overflow recovery failed: ...`\n - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `true`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
|
|
23
|
+
"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n - `type: \"compaction\"`\n - `summary`, optional `shortSummary`\n - `firstKeptEntryId` (compaction boundary)\n - `tokensBefore`\n - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n - `type: \"branch_summary\"`\n - `fromId`, `summary`\n - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in four ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n entry: 0 1 2 3 4 5 6 7 8 9\n ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n └────────┬───────┘ └──────────────┬──────────────┘\n messagesToSummarize kept messages\n ↑\n firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n entry: 0 1 2 3 4 5 6 7 8 9 10\n ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n └──────────┬──────┘ └──────────────────────┬───────────────────┘\n not sent to LLM sent to LLM\n ↑\n starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n ↑ ↑ └─────────────────┬────────────────┘\n prompt from cmp messages from firstKeptEntryId\n```\n\n### Overflow-retry vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n - The failing assistant error message is removed from active agent state before retry.\n - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow.\n - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold maintenance**\n - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n - Tool-output pruning runs instead of compaction only when it leaves enough headroom under the threshold (see [Pre-compaction pruning](#pre-compaction-pruning)).\n - Context promotion is tried before compaction.\n - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n - With `compaction.strategy: \"handoff\"`, threshold maintenance starts a new handoff session instead of writing a compaction entry; if handoff returns no document without aborting, it falls back to context-full compaction.\n - On success, if `compaction.autoContinue !== false` and the triggering answer was unfinished (it called tools or stopped for a reason other than `stop`), schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`. A finished answer is compacted without a continuation turn.\n\n- **Mid-run maintenance** (inside a tool loop)\n - Trigger: between tool-loop steps, against `resolveMidRunThresholdTokens(...)`. When the model's usable window (`contextWindow - reserve`) exceeds the default ceiling (300K), a lower configured threshold is deferred to the ceiling, so a 150K threshold on a 1M-token model compacts at answer boundaries instead of mid-task. Smaller windows use the configured threshold as-is.\n - The run ends with `stopReason: \"maintenance\"` and the session resumes it with `agent.continue()` on the rewritten context.\n - After a compaction, if an SKC workflow skill (`deep-interview`, `ralplan`, `ultragoal`, `team`) invoked on the current branch is active and its instructions are no longer in context, they are re-attached as a hidden `workflow-skill-context` message. The same restore runs before the next prompt after an answer-boundary compaction.\n\n- **Idle maintenance**\n - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\nPruning rewrites history the provider has already cached, so the next request re-writes almost the whole prompt cache. At the compaction threshold a prune therefore runs only when it brings the context down to at most `100 - compaction.pruneMinHeadroomPercent` percent of the threshold (`shouldPruneAtThreshold`; default `20`, so 240K under the 300K ceiling). A smaller prune would reach the threshold again within a few requests and pay the rewrite each time, so the session compacts instead. `compaction.pruneMinHeadroomPercent: 0` accepts any prune that gets back under the threshold.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI code provider models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n- Codex's provider-native request has a 60-second network deadline, including response-body reads. If it expires, compaction proceeds to the existing summary path. Cancelling compaction still stops it without starting a fallback summary.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n ┌─ B ─ C ─ D (old leaf, being abandoned)\n A ───┤\n └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n ┌─ B ─ C ─ D ─ [summary of B,C,D]\n A ───┤\n └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n - overflow path emits `Context overflow recovery failed: ...`\n - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `true`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
|
|
24
24
|
"composer-codex-parity.md": "# Composer 2.5 Fast parity repro\n\nThis document records the one-command repros for the Composer 2.5 Fast stability work. Scope is SKC-local only: no OpenClaw reference, no Cursor live e2e, no upstream xAI/server change, and no Codex refactor. Codex is the baseline/report model only.\n\n## Focused discipline regression\n\n```sh\nbun test packages/ai/test/composer-discipline.test.ts\n```\n\nExpected contract:\n\n- `grok-build/grok-composer-2.5-fast` and other composer ids receive `COMPOSER_EDIT_DISCIPLINE_PROMPT` ahead of host/default system prompts on the `openai-completions`, `openai-responses`, and Cursor RPC prompt paths.\n- Non-composer models keep their system prompt payload unchanged.\n- The prompt explicitly covers adversarial shell file discovery, shell file reads, out-of-band shell writes, fabricated/stale anchors, malformed tool arguments, and contaminated bash command strings.\n\n## V3 mock P1 gate\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --mock --seed 42 -n 5 --model grok-build/grok-composer-2.5-fast --baseline-model openai-codex/gpt-5.5:low\n```\n\nEquivalent package script:\n\n```sh\nbun run bench:composer-stability-v3\n```\n\nP1 passes when `candidateFailureCount <= baselineFailureCount` over the same deterministic scenario matrix. Mock mode is a smoke gate, not live parity proof.\n\n## V3 trace-backed gate\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --trace --trace-file packages/agent/test/fixtures/composer-stability-v3/traces/parity.json\n```\n\nEquivalent package script:\n\n```sh\nbun run bench:composer-stability-v3:trace\n```\n\nTrace files can be JSON, JSON arrays, JSON `{ \"records\": [...] }`, or JSONL. Each record declares `scenarioId`, `modelRole` (`candidate` or `baseline`), `model`, `trial`, optional `expected`, and `events`. The classifier maps recorded tool behavior to failure classes:\n\n- `shell-read`\n- `shell-file-discovery`\n- `shell-write`\n- `contaminated-command`\n- `bad-anchor-unrecovered`\n- `malformed-tool-args-unrecovered`\n- `sanitize-replay-regression`\n- `wrong-file-edit`\n- `missing-tool-turn`\n- `timeout`\n\nTrace P1 is applicable only when both candidate and baseline records exist, and it can pass only with at least three comparable candidate/baseline scenario ids so a one-scenario smoke cannot fake parity. It reports `candidateFailureCount`, `baselineFailureCount`, `parityDelta`, per-scenario counts, and the trace artifact paths that were scored.\n\n## Optional live smoke\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --live -n 3 --model grok-build/grok-composer-2.5-fast --baseline-model openai-codex/gpt-5.5:low\n```\n\nLive smoke is informational. Without `GROK_CLI_OAUTH_TOKEN` and Codex/OpenAI credentials, or without trace artifacts from a real capture, `--live` exits successfully with an explicit skip record and `p1.applicable=false`; it does not fake a P1 pass. Pass `--live --trace-dir <captured-traces>` to score real captured runs through the same trace classifier. Cursor live e2e is intentionally out of scope.\n\n## Broader local verification\n\n```sh\nbun test packages/agent/test/composer-stability-v3.test.ts packages/coding-agent/test/grok-cli-sanitize.test.ts packages/coding-agent/test/grok-build-stream.test.ts\nbun test packages/agent packages/ai\nbun scripts/verify-g002-gates.ts\n```\n\nUse `mise x bun@1.3.14 -- <command>` when `bun` is not on `PATH`.\n",
|
|
25
25
|
"computer-use/README.md": "# Native computer-use tool\n\nStatus: **in progress (draft)** — coordinate contract + native `screenshot`\ncapture landed and verified; input primitives, kill-switch, and napi/TS surface\nto follow.\n\nA new, model-agnostic `computer` tool that lets any model drive the user's real\nmacOS desktop via the OpenAI computer-use action set. Built fresh (the\nopen-source `openai/codex` repo has no GUI computer-use source to copy; only the\npublic action *schema* is mirrored).\n\nThis feature was scoped through SKC's deep-interview (requirements) and ralplan\n(Planner/Architect/Critic consensus) workflows. The full deep-interview spec and\nthe consensus plan + ADR are the authoritative source of truth; this document is\nthe committed summary and roadmap.\n\n## Locked decisions (ADR summary)\n\n- **Target:** the user's real macOS desktop, OS-native control. v1 is macOS-only\n (Linux/Windows deferred behind the same tool schema).\n- **Driver:** any model via a generic structured tool-call interface — no\n provider-specific computer-use API.\n- **Action set:** the exact OpenAI computer-use primitives — `screenshot`,\n `click`, `double_click`, `move`, `drag`, `scroll`, `type`, `keypress`, `wait`.\n- **Implementation:** built fresh in the Rust `pi-natives` crate (napi),\n exposed through `packages/natives` to a new\n `packages/coding-agent/src/tools/computer.ts`, kept deliberately lower-level\n than the existing `browser` tool (coordinate/input primitives only, no web\n semantics).\n- **Coordinate contract:** a single normalized virtual display. The returned\n screenshot's pixel dimensions *are* the action coordinate space; Rust owns the\n transform to macOS logical points (Retina/HiDPI-safe) and display selection.\n- **Permissions:** macOS TCC (Accessibility + Screen Recording) auto-preflighted;\n on a missing grant, open the relevant Settings pane and return a clear\n \"grant then retry/relaunch\" error.\n- **Gating:** off by default; opt-in config flag (per session) plus a persistent\n always-on option.\n- **Safety:** no per-action approval (autonomous), **but** a daemon-enforced\n global kill-switch outside model control (global hotkey OR TUI stop key) that\n aborts queued actions, releases held keys/buttons, suspends further input, and\n snapshots the last screen. Reset is user-only, never via the model-facing tool.\n- **Architecture:** every primitive delegates to one central Rust\n `execute_action` state machine (preflight, validation, cancellation, audit,\n screenshot policy, release-all) so per-primitive methods cannot drift past the\n safety contract. The in-process supervisor sits behind a `SupervisorClient`\n boundary so an out-of-process daemon can replace it later without changing the\n napi surface.\n\n## Capture + coordinate contract (shipped)\n\n`crates/pi-natives/src/computer/coords.rs` implements the pure, framework-free\ncore: `NormalizedDisplay` maps a screenshot-space pixel `(x, y)` to a macOS\nlogical point via per-axis scale and the display's logical origin, rejecting\nout-of-bounds and non-finite inputs. It is unit-tested (scale 1.0/2.0,\nfractional and anisotropic scale, non-zero origins, edges, out-of-bounds,\ninvalid scale) and requires no display or granted permissions.\n\n`crates/pi-natives/src/computer/capture.rs` (macOS) implements the read-only\n`screenshot` primitive: it captures the primary display via CoreGraphics into a\nPNG and derives the `NormalizedDisplay` scale from captured physical pixels vs\nlogical bounds, surfacing a missing Screen Recording grant as\n`CaptureError::CaptureFailed` (never a silent black frame). Verified live: a\nreal, non-uniform primary-display capture decodes as a PNG with matching\ndimensions (`cargo test -p pi-natives --ignored captures_non_uniform_primary_display`).\n\n## Delivery roadmap\n\nDelivery ships a `screenshot`+`click`+`type` vertical slice first; the remaining\nsix primitives fast-follow; v1 acceptance = all nine primitives drive a real\nmacOS app end-to-end plus a kill-switch drill (per-primitive napi unit tests +\nmanual macOS E2E).\n\n| Slice | Scope | Status |\n|-------|-------|--------|\n| Coordinate contract + planning docs | `coords` module + unit tests + this doc | **done (this PR)** |\n| Native screen capture (`screenshot`) | `capture` module, primary display, PNG + scale | **done (this PR, verified live)** |\n| TCC preflight (`permissions`) | Accessibility + Screen Recording checks, Settings openers, fail-closed guards | **done (this PR, verified live)** |\n| napi screenshot binding (`computerScreenshot`) | napi → `packages/natives` → TS, verified live | **done (this PR)** |\n| Native input orchestration (`input`) | `InputController` click/double_click/move/drag/scroll/type/keypress + release_all over an `EventSink` | **done (this PR)** — logic unit-tested; **live cursor-move injection verified** (Accessibility granted) |\n| Central `execute_action` state machine | preflight + supervisor + cancellation + audit + release-all | planned |\n| Kill-switch supervisor + global-hotkey event-tap | `supervisor` (fail-closed `input_allowed`, user-only reset) + `hotkey` CGEventTap on a CFRunLoop thread | **done (this PR)** — supervisor unit-tested; **synthetic-hotkey latch verified live** |\n| Supervisor-gated `execute_action` + napi/TS `computer` tool | wire input through `input_allowed` + cancellation; `ComputerController` napi; `computer.ts` schema/gating/prompt/renderer | next |\n| Manual macOS E2E acceptance | TextEdit all-nine + kill-switch drill | planned (requires macOS hardware + granted TCC + human operator) |\n\nThe remaining input backend, kill-switch, napi/TS surface, and manual\nend-to-end acceptance still require injecting events into a live desktop and a\nhuman-operated drill, so they are tracked as follow-up work rather than landed\nin this draft.\n",
|
|
26
26
|
"discord-onboarding.md": "# Discord notification onboarding\n\nThis is the managed Discord notification adapter. It is an SDK client: every\nlocal SKC session retains its own loopback SDK endpoint, while the daemon maps\nthat session to one Discord thread under a configured parent channel.\n\n## Prerequisites\n\nCreate a Discord application and bot through Discord's developer portal, install\nthe bot in the target guild, and create or select the parent channel that will\ncontain SKC session threads. Configure the bot with only the permissions it\nneeds in that channel:\n\n- View Channel\n- Send Messages\n- Create Public Threads\n- Send Messages in Threads\n- Manage Threads (needed to archive, unarchive, and lock session threads)\n- Read Message History\n\nEnable the Gateway intents required to receive the configured thread messages\nand interactions. Do not grant Administrator merely to make setup work. Keep\nthe bot and parent channel private to people permitted to see local session\nmetadata.\n\n## Configure the adapter\n\n`skc notify setup discord` is non-interactive. It requires these flags:\n\n- `--discord-bot-token`\n- `--discord-application-id`\n- `--discord-guild-id`\n- `--discord-parent-channel-id`\n\nIt also accepts `--redact`. Supply secret flag values from an approved local\nsecret mechanism rather than placing them in shell history, files committed to\nthe repository, chat transcripts, or screenshots. The setup command writes:\n\n- `notifications.enabled = true`\n- `notifications.discord.botToken`\n- `notifications.discord.applicationId`\n- `notifications.discord.guildId`\n- `notifications.discord.parentChannelId`\n- `notifications.redact = true` when requested\n\n`skc notify status` shows configured Discord identifiers and masks token values.\nIt must not be used as a way to recover a token.\n\n## Threads, resume, and replies\n\nA session gets one Discord thread. For a generic text-channel parent, the daemon\nfirst posts a nonce-bearing starter message and then uses Discord's **Start\nThread from Message** endpoint. It never sends the protocol-invalid nested\n`message` field to the **Start Thread without Message** endpoint. A notification\ncreates a durable local mapping before remote work begins; a retry first finds\nthe nonce-bearing starter message and attached thread, reconciling an uncertain\ncreate instead of intentionally creating a second thread. The nonce is only an\nopaque correlation marker and never contains credentials.\n\nWhen a session is archived, the daemon archives its thread. On resume it first\ntries to unarchive that thread. If Discord refuses unarchive, the daemon creates\na replacement thread and marks the old mapping superseded. Inbound events from a\nsuperseded thread, stale endpoint generation, unknown route, bot author, or\nmissing local endpoint fail closed and are not routed to a session.\n\nReply controls carry the session endpoint generation. Discord interaction IDs\nand event IDs are deduplicated locally. A reply is sent to the loopback SDK only;\nthe daemon never stores endpoint tokens or message bodies in its conversation\nstate.\n\n## Operational safety\n\nDiscord API permission failures, rate limits, disconnects, and uncertain creates\nmust be retried through the managed daemon's reconciliation path. Do not use a\nsecond bot process against the same managed state directory, manually edit\nconversation files, scrape a session terminal, expose the loopback endpoint, or\nturn Discord into a general remote shell.\n\nThe supported surface is notification delivery and replies to the SDK protocol.\nProvider registration, provider secrets in session state, and arbitrary remote\ncontrol are out of scope.\n\n## Verification boundary\n\nThe shipped acceptance coverage uses an injectable fake Discord provider. It\ncovers uncertain create reconciliation, durable restart behavior, archive/\nunarchive-or-replacement resume, stale/superseded inbound rejection, permission\nand rate-limit failure paths, and disconnect handling. It deliberately does not\nrequire live Discord credentials, a live guild, or live-provider end-to-end\ntests.\n",
|
|
@@ -12187,6 +12187,12 @@ export class AgentSession {
|
|
|
12187
12187
|
);
|
|
12188
12188
|
}
|
|
12189
12189
|
|
|
12190
|
+
#isBeforeLatestCompaction(timestamp: number): boolean {
|
|
12191
|
+
// An overflow error retained after compaction must not trigger it again.
|
|
12192
|
+
const entry = getLatestCompactionEntry(this.sessionManager.getBranch());
|
|
12193
|
+
return entry !== null && timestamp < new Date(entry.timestamp).getTime();
|
|
12194
|
+
}
|
|
12195
|
+
|
|
12190
12196
|
/**
|
|
12191
12197
|
* Check if context maintenance or promotion is needed and run it.
|
|
12192
12198
|
* Called after agent_end and before prompt submission.
|
|
@@ -12222,18 +12228,11 @@ export class AgentSession {
|
|
|
12222
12228
|
// shouldn't trigger compaction for the new model.
|
|
12223
12229
|
const sameModel =
|
|
12224
12230
|
this.model && assistantMessage.provider === this.model.provider && assistantMessage.model === this.model.id;
|
|
12225
|
-
|
|
12226
|
-
// The error shouldn't trigger another compaction since we already compacted.
|
|
12227
|
-
// Example: opus fails -> switch to OpenAI code backend -> compact -> switch back to opus -> opus error
|
|
12228
|
-
// is still in context but shouldn't trigger compaction again.
|
|
12229
|
-
const compactionEntry = getLatestCompactionEntry(this.sessionManager.getBranch());
|
|
12230
|
-
const errorIsFromBeforeCompaction =
|
|
12231
|
-
compactionEntry !== null && assistantMessage.timestamp < new Date(compactionEntry.timestamp).getTime();
|
|
12232
|
-
if (
|
|
12231
|
+
const isNewOverflow =
|
|
12233
12232
|
sameModel &&
|
|
12234
|
-
|
|
12235
|
-
|
|
12236
|
-
) {
|
|
12233
|
+
classifyContextOverflow(assistantMessage, assistantMessage.transportFailure, contextWindow) &&
|
|
12234
|
+
!this.#isBeforeLatestCompaction(assistantMessage.timestamp);
|
|
12235
|
+
if (isNewOverflow) {
|
|
12237
12236
|
this.#overflowMaintenanceAttempts += 1;
|
|
12238
12237
|
if (this.#overflowMaintenanceAttempts > 1) return false;
|
|
12239
12238
|
// Remove the error message from agent state (it IS saved to session for history,
|
package/src/tools/ask.ts
CHANGED
|
@@ -1347,8 +1347,8 @@ interface AskRenderArgs {
|
|
|
1347
1347
|
multi?: boolean;
|
|
1348
1348
|
questions?: Array<{
|
|
1349
1349
|
id: string;
|
|
1350
|
-
question
|
|
1351
|
-
options
|
|
1350
|
+
question?: string;
|
|
1351
|
+
options?: Array<{ label: string }>;
|
|
1352
1352
|
multi?: boolean;
|
|
1353
1353
|
}>;
|
|
1354
1354
|
}
|
|
@@ -1410,6 +1410,7 @@ export const askToolRenderer = {
|
|
|
1410
1410
|
|
|
1411
1411
|
for (let i = 0; i < args.questions.length; i++) {
|
|
1412
1412
|
const q = args.questions[i];
|
|
1413
|
+
const question = q.question ?? "";
|
|
1413
1414
|
const isLastQ = i === args.questions.length - 1;
|
|
1414
1415
|
const qBranch = isLastQ ? uiTheme.tree.last : uiTheme.tree.branch;
|
|
1415
1416
|
const continuation = isLastQ ? " " : uiTheme.tree.vertical;
|
|
@@ -1422,15 +1423,15 @@ export const askToolRenderer = {
|
|
|
1422
1423
|
container.addChild(
|
|
1423
1424
|
new Text(` ${uiTheme.fg("dim", qBranch)} ${uiTheme.fg("dim", `[${q.id}]`)}${metaStr}`, 0, 0),
|
|
1424
1425
|
);
|
|
1425
|
-
const deepInterviewQuestion = renderDeepInterviewAskQuestion(
|
|
1426
|
-
container.addChild(deepInterviewQuestion ?? new Markdown(
|
|
1426
|
+
const deepInterviewQuestion = renderDeepInterviewAskQuestion(question, uiTheme);
|
|
1427
|
+
container.addChild(deepInterviewQuestion ?? new Markdown(question, 3, 0, mdTheme, accentStyle));
|
|
1427
1428
|
|
|
1428
1429
|
const qOptions = q.options;
|
|
1429
1430
|
if (qOptions?.length) {
|
|
1430
1431
|
const entries = qOptions.map((opt, j) => {
|
|
1431
1432
|
const isLastOpt = j === qOptions.length - 1;
|
|
1432
1433
|
const optBranch = isLastOpt ? uiTheme.tree.last : uiTheme.tree.branch;
|
|
1433
|
-
const shouldNumberOption = deepInterviewQuestion !== null || isDeepInterviewAskQuestion(
|
|
1434
|
+
const shouldNumberOption = deepInterviewQuestion !== null || isDeepInterviewAskQuestion(question);
|
|
1434
1435
|
const displayLabel = shouldNumberOption ? formatNumberedOptionLabel(opt.label, j) : opt.label;
|
|
1435
1436
|
const optLabel = renderInlineMarkdown(displayLabel, mdTheme, t => uiTheme.fg("muted", t));
|
|
1436
1437
|
return {
|