@nanobpm/nano-coder 0.1.0 → 0.2.1

package/README.md

@@ -20,11 +20,12 @@ cargo install nano-coder             # or build from source
 - **Sessions**: Append-only JSONL session logs with resume and input-ID deduplication
 - **Lifecycle Hooks**: 6 hook events for observing/intercepting agent behavior
 - **Configuration**: TOML-based config file at `~/.config/nano-coder/config.toml`
-- **Commands**: `/help`, `/compact`, `/context`, `/verbosity`, `/settings`, `/tools`, `/exit`
+- **Commands**: `/help`, `/compact`, `/context`, `/verbosity`, `/settings`, `/tools`, `/skills`, `/exit`
 - **Streaming output**: answers stream in, thinking shows collapsed (Ctrl-O expands it), tool calls show inline
 - **Status line** pinned to the bottom of the terminal, plus manual and automatic context compaction
 - **Task plans**: `plan_*` tools keep a plan with notes outside the conversation, so long tasks survive compaction, resume and a change of worker
 - **Project instructions**: `AGENTS.md` (or `CLAUDE.md`, `.github/copilot-instructions.md`) from the repository is added to the system prompt
+- **Skills**: `SKILL.md` folders from the repository, `~/.agents/skills`, and an spm `ai.lock`, loaded on demand with `load_skill`
 
 ## Two Execution Modes
 
@@ -83,6 +84,8 @@ events c8ctl-nano's transcript producer records into the engine's AgentInstance
 **Project instructions.** `session/new` and `session/load` results include
 `_meta.projectInstructions`: the absolute paths of the instruction files that were added to
 the system prompt for the session's `cwd` (see [Project Instructions](#project-instructions)).
+`_meta.skills` lists the skills found for it, and `_meta.skillWarnings` (when present) explains
+any that could not be loaded (see [Skills](#skills)).
 
 **Plans.** Each plan change sends a `plan` update: ACP `entries` (`content`, `priority`,
 `status`) plus `_meta.plan`, the full plan with ids, notes and dependencies. To continue a job
@@ -133,6 +136,8 @@ src/
 ├── instructions.rs # AGENTS.md / CLAUDE.md discovery for the system prompt
 ├── plan.rs      # Task plan and the plan_add / plan_update / plan_show tools
 ├── goal.rs      # report_outcome tool (completed / blocked)
+├── commands.rs  # Slash-command table for /help and the as-you-type menu
+├── skills.rs    # SKILL.md discovery, ai.lock sources and the load_skill tool
 ├── reminders.rs # <system-reminder> notes appended to tool results
 ├── settings.rs  # /settings menu and config-file writer
 └── config.rs    # Configuration file loading and management
@@ -171,6 +176,8 @@ The harness exposes 6 lifecycle hook events:
 - `plan_add`, `plan_update`, `plan_show` - The agent's task plan (see [Task Plans](#task-plans)).
 - `report_outcome` - Report the task `completed` or `blocked`, with a `summary`; ends the turn
   (see [Outcomes](#outcomes)).
+- `load_skill` - Return a skill's instructions and list its other files; `name`. Offered only
+  when skills were found (see [Skills](#skills)).
 
 Any other tool's result longer than 40,000 characters is cut the same way as bash output,
 with the whole result saved under the temp directory (`nano-coder-<pid>/tool-<id>-<name>.txt`)
@@ -182,6 +189,10 @@ workspace.
 
 ## Commands
 
+Typing `/` at the prompt lists the commands under it, and each further character narrows the
+list. Tab completes the command, or the part all matches share. Esc hides the list. The
+list is built from the same table as `/help` (`src/commands.rs`).
+
 - `/help` - Show available commands
 - `/compact [focus]` - Summarize older messages with the current model, keeping the latest
   message. Optional text tells the summary what to focus on. Esc Esc or Ctrl-C cancels
@@ -199,6 +210,7 @@ workspace.
     (`--config` or `~/.config/nano-coder/config.toml`), keeping comments and
     other settings. Leaving with unsaved changes asks whether to save
 - `/tools` - List registered tools
+- `/skills` - List the skills the agent can load, where each lives, and any loading warnings
 - `/plan` - Show the agent's task plan with all notes
 - `/model [provider/model]` - Show or switch the model (conversation is kept)
 - `/providers` - List providers, endpoints and whether their API key is available
@@ -242,11 +254,20 @@ auto_compact = true                     # summarize automatically when the conte
 auto_compact_threshold = 0.8            # fraction of the context window
 # context_window = 128000               # override the window (providers can set it too)
 verbosity = "normal"                    # quiet | normal | verbose | debug (or --verbosity)
+timestamps = true                       # prefix CLI messages with the local time (HH:MM:SS)
 project_instructions = true             # load AGENTS.md etc. (see Project Instructions)
 project_instruction_files = ["AGENTS.md", "CLAUDE.md", ".github/copilot-instructions.md"]
 plan_tools = true                       # offer the plan_* tools (see Task Plans)
 outcome_tool = true                     # offer report_outcome (see Outcomes)
 reminders = true                        # append <system-reminder> notes to tool results
+
+[skills]                                # see Skills
+enabled = true
+dirs = [".agents/skills", ".github/skills", ".claude/skills"]   # relative to the git root
+user_dirs = ["~/.agents/skills"]
+ai_lock = true                          # load skills pinned in ai.lock
+fetch = true                            # fetch ai.lock commits missing from the spm store
+allowed_hosts = ["github.com"]          # hosts ai.lock entries may be fetched from ("*" = any)
 ```
 
 The default model is `gpt-4o-mini` on the `mock` provider, so the harness still works offline.
@@ -268,8 +289,10 @@ Built-in presets:
 | `groq` | openai | `https://api.groq.com/openai/v1` | `GROQ_API_KEY` |
 | `together` | openai | `https://api.together.xyz/v1` | `TOGETHER_API_KEY` |
 | `deepseek` | openai | `https://api.deepseek.com/v1` | `DEEPSEEK_API_KEY` |
+| `kimi` | openai | `https://api.moonshot.ai/v1` | `MOONSHOT_API_KEY` |
 | `mistral` | openai | `https://api.mistral.ai/v1` | `MISTRAL_API_KEY` |
 | `gemini` | openai | `https://generativelanguage.googleapis.com/v1beta/openai` | `GEMINI_API_KEY` |
+| `qwen` | openai | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1` | `DASHSCOPE_API_KEY` |
 | `ollama` | openai | `http://localhost:11434/v1` | — |
 | `llamacpp` | openai | `http://localhost:8080/v1` | — |
 | `github-copilot` | github-copilot | from session token | `GITHUB_COPILOT_OAUTH_TOKEN` or `--login` (unofficial, see below) |
@@ -307,7 +330,19 @@ timeout_secs = 300
 max_retries = 3
 ```
 
-Other per-provider fields: `max_tokens_param` (`max_tokens`, or `max_completion_tokens`
+`qwen` is Qwen Cloud (Alibaba Cloud Model Studio), e.g. `--model qwen/qwen3.8-max`. The
+preset uses the Singapore endpoint. API keys are bound to a region, so for another region
+or your workspace domain override `base_url`, e.g.
+`https://dashscope-us.aliyuncs.com/compatible-mode/v1` or
+`https://<WorkspaceId>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1`.
+
+`kimi` is the Kimi API from platform.kimi.ai, e.g. `--model kimi/kimi-k3` or
+`kimi/kimi-k2.7-code`. The preset drops `temperature` (K3 fixes it) and sets
+`replay_reasoning = true`, which sends each assistant message's `reasoning_content` back
+as thinking models like K3 require. Set `extra_body = { reasoning_effort = "low" }` to
+make K3 think less.
+
+Other per-provider fields: `replay_reasoning`, `max_tokens_param` (`max_tokens`, or `max_completion_tokens`
 which is the `openai` default), `retry_initial_backoff_ms`, `retry_max_backoff_ms` and
 `retryable_statuses`.
 
@@ -384,6 +419,10 @@ Streaming uses server-sent events. Set `stream = false` on a provider whose endp
 support it. ACP mode doesn't stream text, but sends each response's reasoning as an
 `agent_thought_chunk` update.
 
+Every message (your prompt, answers, tool calls and results, thinking, notes) starts with
+the local time as `HH:MM:SS`. The prompt's time is rewritten when you press Enter, so it
+shows when the message was sent. Turn this off with `timestamps = false`.
+
 ## Status Line and Compaction
 
 In an interactive terminal the bottom row shows the provider/model, context usage
@@ -393,8 +432,22 @@ count, and what the agent is doing. It uses a terminal scroll region, follows re
 off when stdin/stdout isn't a TTY or `AGENTIC_NO_STATUS` is set.
 
 The context window comes from, in order: `context_window` in the config, `context_window`
-on the provider, a built-in table of known models, then 128k. If a provider rejects a
-request as too long, the harness takes the limit from the error, compacts, and retries once.
+on the provider, the window the endpoint reports, a built-in table of known models, then
+128k. `/context` shows which one applied. If a provider rejects a request as too long, the
+harness takes the limit from the error, compacts, and retries once.
+
+The endpoint is asked at startup and on `/model` (at most 5 seconds; skipped when config
+sets the window). The window a server has *loaded* is preferred over the model's maximum:
+
+| Server | Source |
+|---|---|
+| vLLM | `/v1/models` `max_model_len` |
+| DwarfStar ds4, OpenRouter, Together, Kimi | `/models` `context_length` |
+| Groq / Mistral | `/models` `context_window` / `max_context_length` |
+| llama.cpp | `/props` `n_ctx` (per slot) |
+| LM Studio | `/api/v0/models` `loaded_context_length` |
+| Ollama | `/api/ps` for a loaded model, else `num_ctx`; never the model maximum, since Ollama runs with a smaller default |
+| GitHub Copilot | `/models` `max_prompt_tokens` |
 
 Compaction asks the current model to summarize older messages, keeping the recent tail
 (up to 20k tokens, never starting at a tool result). Auto-compaction runs before a model
@@ -424,6 +477,39 @@ Instructions are read again when a session is resumed, so edits to `AGENTS.md` t
 `/context` lists the loaded files. To turn loading off, set `project_instructions = false`,
 or set `AGENTIC_NO_PROJECT_INSTRUCTIONS`.
 
+## Skills
+
+A skill is a folder with a `SKILL.md`: YAML front matter with a `name` and a `description`,
+then instructions, plus any scripts or reference files it needs. Only the name and description
+of each skill go into the system prompt, under a "Skills" heading (8 KiB at most). When a task
+matches one, the model calls `load_skill`, which returns the instructions (32 KiB at most),
+the skill's directory, and a list of its other files for `read_file`.
+
+Skills are found in this order, and the first skill with a given name wins:
+
+1. **Repository**: `.agents/skills`, `.github/skills` and `.claude/skills` under the git root,
+   at any depth up to four folders (`skills/<group>/<skill>/SKILL.md` works).
+2. **`ai.lock`**: skills pinned by [spm](https://github.com/camunda/spm-cli). Each locked
+   skill is loaded, and so is each skill bundled in a locked plugin (its
+   `.claude-plugin/plugin.json` `skills` folder, default `skills/`). Hooks, commands and MCP
+   servers in plugins are not loaded.
+3. **User**: `~/.agents/skills`.
+
+nano-coder reads `ai.lock` itself and never runs `spm install`, which edits the workspace
+(`.gitignore`, vendor folders). Changes like that would end up in commits and PRs. Each
+pinned commit is read from spm's store (`$SPM_HOME/store`, default `~/.spm/store`) if it is
+there. Otherwise it is fetched once into the nano-coder cache (`<cache dir>/nano-coder/skills`).
+`ai.lock` is committed to the repository, so its entries are checked the way spm checks them:
+a full 40-character commit, a store key that matches the URL and commit, and paths that stay
+inside the checkout. Fetches are limited to `skills.allowed_hosts` (`"file"` allows
+`file://`). With `fetch = false`, only commits already in the spm store or the cache are used.
+An `ai.json` without an `ai.lock` is skipped with a warning, because unpinned references are
+never resolved.
+
+Skills are found again when a session starts or is resumed. Problems are listed at startup
+and by `/skills` (and returned as `_meta.skillWarnings` over ACP); they never stop a session.
+To turn skills off, set `skills.enabled = false` or set `NANO_CODER_NO_SKILLS`.
+
 ## Task Plans
 
 The `plan_*` tools give the agent a plan that lives outside the conversation. This helps most
@@ -479,6 +565,8 @@ When `persist_sessions` is on, each conversation is written to `<session_dir>/<i
 The file is an append-only log whose first record is a versioned header, followed by
 `input`, `message`, `turn_end` and `replace` (compaction / system-prompt reset) records.
 Resume a session with `--resume <id>` or ACP `session/load`.
+Record times and each message's `timestamp` are RFC 3339 with the local UTC offset
+(for example `2026-09-24T13:02:12.44+12:00`). Older logs with UTC times still load.
 
 - An unsupported format version is an explicit error on resume.
 - Only records ending in a newline count as committed. A half-written last line from a

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nanobpm/nano-coder",
-  "version": "0.1.0",
+  "version": "0.2.1",
   "description": "A 6MB coding agent. Run a fleet on your laptop.",
   "license": "Apache-2.0",
   "repository": {
@@ -31,9 +31,9 @@
     "node": ">=18"
   },
   "optionalDependencies": {
-    "@nanobpm/nano-coder-darwin-arm64": "0.1.0",
-    "@nanobpm/nano-coder-darwin-x64": "0.1.0",
-    "@nanobpm/nano-coder-linux-arm64": "0.1.0",
-    "@nanobpm/nano-coder-linux-x64": "0.1.0"
+    "@nanobpm/nano-coder-darwin-arm64": "0.2.1",
+    "@nanobpm/nano-coder-darwin-x64": "0.2.1",
+    "@nanobpm/nano-coder-linux-arm64": "0.2.1",
+    "@nanobpm/nano-coder-linux-x64": "0.2.1"
   }
 }