Updates
ober
68c4be3bfe2e15db4300de0a451ad17002678ccb
--- a/README.md +++ b/README.md @@ -71,6 +71,7 @@ make binary # produce the standalone ./jcode | **[Providers & models](docs/providers.md)** | The 14 providers, model registry, per-model sampling, and hardware tiers. | | **[Tools](docs/tools.md)** | The agent's toolbox (file, bash, web, git, patch, task, MCP) and the safety model. | | **[Named agents & plans](docs/agents.md)** | Sub-agent roles with enforced write scopes, per-agent models, gated execution, and the plan-lifecycle skills. | +| **[Verify-gated runs](docs/verified.md)** | `jcode verified`, cookbook-guided local-model runs, MCP tools, write scopes, JSON status, and troubleshooting. | | **[TUI](docs/tui.md)** | Layout, keybindings, themes, and the rendering features. | | **[Forge & ATLAS reliability](docs/FORGE.md)** | Guardrails, workflows, verify-gate, best-of-k, the proxy, and the eval harness. | | **[Remote & Android](docs/remote.md)** | `serve` / `relay` / `connect` and the thin-client architecture. | --- a/docs/FORGE.md +++ b/docs/FORGE.md @@ -33,7 +33,7 @@ see [`FORGE_PORT_PLAN.md`](FORGE_PORT_PLAN.md). | `/forge verify` | Describe + self-test the verify-gate (ATLAS verify + repair). | | `/forge bestofk` · `/forge best-of-k` | Describe + self-test best-of-k diverse generation. | | `/forge breaker` · `/forge no-progress` | Describe + self-test the no-progress loop breaker. | -| `/forge run [opts] <task>` | Verify-gated coding on the **live** model (edit → verify → done). Options: `--verify`, `--bestof`, `--cwd`, `--write-scope`, `--guidance-file`, `--json`, `--status-file`. | +| `/forge run [opts] <task>` | Verify-gated coding on the **live** model (edit → verify → done). Options: `--verify`, `--bestof`, `--cwd`, `--write-scope`, `--guidance-file`, `--json`, `--status-file`, `--no-run-aliases`. See [verified.md](verified.md). | The `workflow` / `proxy` / `ablation` / `verify` / `bestofk` / `breaker` self-tests run real code against scripted inputs (no live model), so they double @@ -52,7 +52,7 @@ HTTP endpoint. See [The proxy](#the-openai-compatible-proxy) below. ### `jcode verified` (subcommand) ```bash -jcode verified "<task>" [--bestof K] [--verify CMD] [--cwd DIR] [--write-scope PATHS] [--json] [--status-file FILE] +jcode verified "<task>" [--bestof K] [--verify CMD] [--cwd DIR] [--write-scope PATHS] [--guidance-file FILE] [--json] [--status-file FILE] [--no-run-aliases] ``` Runs the [verify-gate](#verify-gate) on the live model — edit → run `CMD` → @@ -73,6 +73,9 @@ through the verified workflow's own edit tools, and success still requires the configured `verify` command to pass. `--no-mcp` keeps those external tools out by skipping MCP startup. +See [verified.md](verified.md) for the full operator guide, cookbook-guided +Jerboa workflow, JSON status shape, and troubleshooting notes. + --- ## The guardrails --- a/docs/README.md +++ b/docs/README.md @@ -21,6 +21,9 @@ elevator pitch. - **[Strict ladder howto](strict-ladder.md)** — practical workflow for using `/strict-ladder`, runtime `write_scope`, and scoped verified runs to make hard local-model tasks succeed one rung at a time. +- **[Verify-gated runs](verified.md)** — `jcode verified`, cookbook-guided + local-model workflows, MCP tools, write scopes, JSON status, and + troubleshooting. - **[TUI](tui.md)** — the terminal UI: layout, the full keybinding table, themes, and the markdown / syntax / diff renderers. --- a/docs/cli.md +++ b/docs/cli.md @@ -47,7 +47,7 @@ Parsed before any subcommand. | `relay …` | Run the reverse-tunnel rendezvous (VPS side). See [remote.md](remote.md). | | `connect HOST:PORT …` | Dial a relay as the controller. See [remote.md](remote.md). | | `proxy …` | OpenAI-compatible guardrail proxy. See [FORGE.md](FORGE.md#the-openai-compatible-proxy). | -| `verified <task> …` | Verify-gated coding on a live model. See [FORGE.md](FORGE.md#verify-gate). | +| `verified <task> …` | Verify-gated coding on a live model. See [verified.md](verified.md). | ### `keys` @@ -85,7 +85,7 @@ jcode connect HOST:PORT --host NAME [--token T] # controller side ### `verified` ``` -jcode verified "<task>" [--bestof K] [--verify CMD] [--cwd DIR] [--write-scope PATHS] [--guidance-file FILE] [--json] [--status-file FILE] +jcode verified "<task>" [--bestof K] [--verify CMD] [--cwd DIR] [--write-scope PATHS] [--guidance-file FILE] [--json] [--status-file FILE] [--no-run-aliases] ``` Runs an edit→verify→done loop on the live model: it edits, runs `--verify CMD` @@ -107,8 +107,8 @@ exits `0` only when verification passed, and exits `1` when the verified run stopped. Status fields include `ok`, `status`, `verify_passed`, `exit_code`, `exit_reason`, `error_type`, `error`, `summary`, `provider`, `model`, `verify_command`, `cwd`, and `write_scope`. -See -[FORGE.md](FORGE.md#verify-gate). +See [verified.md](verified.md) for the full workflow, MCP cookbook guidance, +JSON status shape, and troubleshooting notes. ## Slash commands (interactive) @@ -176,7 +176,7 @@ Useful built-in workflow skill: | `/forge verify` | Describe + self-test the verify-gate. | | `/forge bestofk` · `/forge best-of-k` | Describe + self-test best-of-k generation. | | `/forge breaker` · `/forge no-progress` | Describe + self-test the no-progress breaker. | -| `/forge run [opts] <task>` | Verify-gated coding on the live model. Supports `--verify`, `--bestof`, `--cwd`, `--write-scope`, `--guidance-file`, `--json`, and `--status-file`. | +| `/forge run [opts] <task>` | Verify-gated coding on the live model. Supports `--verify`, `--bestof`, `--cwd`, `--write-scope`, `--guidance-file`, `--json`, `--status-file`, and `--no-run-aliases`. | Each `/forge` self-test runs real code against scripted inputs (no live model), so it doubles as a smoke test. Full semantics in [FORGE.md](FORGE.md).