sigit-code 1.0.2__tar.gz → 1.0.4__tar.gz

{sigit_code-1.0.2 → sigit_code-1.0.4}/.agents/skills/agent-client-protocol/SKILL.md

@@ -1,4 +1,9 @@
-# Skill: Agent Client Protocol (ACP) — Rust Implementation
+---
+name: agent-client-protocol
+description: Implement or debug Agent Client Protocol (ACP) support in Rust for siGit Code. Use when working on ACP JSON-RPC over stdio, the agent-client-protocol crate, session or prompt handlers, streaming notifications, or editor integration.
+---
+
+# Agent Client Protocol
 
 ## Overview
 
@@ -311,4 +316,4 @@ Editor                          Agent
 10. **Never write to stdout except JSON-RPC** — any library that prints to
     stdout (`mistralrs` model metadata, stray `println!`, whatever) will
     corrupt the wire. Redirect diagnostics to stderr. If a dependency writes
-    to stdout internally, fix it or suppress it before shipping.
+    to stdout internally, fix it or suppress it before shipping.

{sigit_code-1.0.2 → sigit_code-1.0.4}/.agents/skills/ai-assisted-coding/SKILL.md

@@ -1,4 +1,9 @@
-# Skill: AI-Assisted Coding Agents — Onde Inference Integration
+---
+name: ai-assisted-coding
+description: Build or maintain AI-assisted coding features in Rust using Onde Inference. Use when working on ChatEngine integration, model loading, streaming inference, history management, sampling config, or local coding-agent architecture.
+---
+
+# AI-Assisted Coding
 
 ## Overview
 
@@ -358,4 +363,4 @@ For sandboxed environments (iOS, tvOS, Android):
 6. **Forgetting that `generate()` doesn't update history** — use it for
    one-shot enhancements (prompt expansion, code review) that shouldn't pollute
    the main conversation. Use `send_message()` / `stream_message()` for the
-   primary turn loop.
+   primary turn loop.

sigit_code-1.0.4/.agents/skills/branding/SKILL.md

@@ -0,0 +1,178 @@
+---
+name: branding
+description: Keep siGit Code branding, naming, and package references consistent. Use when editing docs, release notes, UI copy, package metadata, setup guides, or any prose that mentions the product, CLI, company, or Onde Inference.
+---
+
+# Branding
+
+## Overview
+
+Use this file when writing docs, release notes, UI copy, package metadata, or setup guides for this repository.
+
+The short version:
+
+- **Product / brand name:** `siGit Code`
+- **CLI command:** `sigit`
+- **Rust crate:** `sigit`
+- **npm package:** `@smbcloud/sigit`
+- **PyPI package:** `sigit-code`
+- **Company name:** `smbCloud`
+- **LLM backend name:** `Onde Inference`
+
+The most common mistake is mixing the product name with the command name.
+
+---
+
+## Primary rule
+
+When you mean the product, write **`siGit Code`** exactly like that.
+
+Correct:
+
+- `siGit Code is a local coding agent.`
+- `siGit Code works in Zed over ACP.`
+- `siGit Code shares its model cache with the desktop app on macOS.`
+
+Wrong:
+
+- `Sigit Code`
+- `SiGit Code`
+- `siGit`
+- `sigit Code`
+- `SIGIT`
+
+Do not shorten the product name to just `siGit` in documentation or marketing copy unless there is a very specific reason and the surrounding text makes it unmistakable.
+
+---
+
+## Use lowercase names for commands and packages
+
+Use lowercase `sigit` when you mean the executable, crate, repo slug, or package name.
+
+Examples:
+
+- Run `sigit` in a terminal.
+- Install with `cargo install sigit`.
+- Install with `npm install -g @smbcloud/sigit`.
+- Install with `pip install sigit-code`.
+- The repository is `getsigit/sigit`.
+
+This distinction matters:
+
+- **Brand / product:** `siGit Code`
+- **Command / package / repo:** `sigit`
+
+---
+
+## Recommended wording patterns
+
+### Product description
+
+Prefer:
+
+- `siGit Code is a local coding agent.`
+- `siGit Code runs on your machine.`
+- `siGit Code works with any codebase.`
+
+Avoid:
+
+- `siGit is a local coding agent.`
+- `sigit is a coding assistant.`
+- `The siGit product...`
+
+### Install instructions
+
+Prefer:
+
+- `Install siGit Code with Cargo:`
+- `Install siGit Code from npm:`
+- To start siGit Code, run `sigit`.
+
+That keeps the brand name in prose and the command name in code.
+
+### Editor setup
+
+In UI-facing examples, keep the displayed agent name as `siGit Code`.
+
+Example:
+
+```/dev/null/branding-example.json#L1-8
+{
+  "agent_servers": {
+    "siGit Code": {
+      "type": "custom",
+      "command": "/absolute/path/to/sigit"
+    }
+  }
+}
+```
+
+The visible name is `siGit Code`. The executable path is `sigit`.
+
+---
+
+## Other names that should stay consistent
+
+### smbCloud
+
+Always write `smbCloud` with a lowercase `smb` and uppercase `C`.
+
+Correct:
+
+- `smbCloud`
+
+Wrong:
+
+- `SMBCloud`
+- `SmbCloud`
+- `smbcloud`
+
+### Onde Inference
+
+Use `Onde Inference` when referring to the product or project.
+
+Use `onde` when referring to the Rust crate.
+
+Examples:
+
+- `siGit Code uses Onde Inference as its local LLM backend.`
+- The Rust dependency is `onde`.
+
+### ACP
+
+Use `ACP` for the protocol acronym.
+
+Preferred long form:
+
+- `Agent Client Protocol (ACP)` on first mention when useful
+
+---
+
+## Copy checklist
+
+Before you finish any docs or release-note edit, check these quickly:
+
+1. Did you use `siGit Code` for the product name?
+2. Did you keep `sigit` lowercase for commands and package names?
+3. Did you keep `smbCloud` cased correctly?
+4. Did you keep `Onde Inference` cased correctly in prose?
+5. In setup examples, does the visible editor label say `siGit Code` while the command stays `sigit`?
+
+---
+
+## Fast replacements
+
+Common fixes:
+
+- `siGit is` -> `siGit Code is`
+- `siGit works` -> `siGit Code works`
+- `siGit knows` -> `siGit Code knows`
+- `On macOS, siGit` -> `On macOS, siGit Code`
+- `Sigit` -> usually `siGit Code` or `sigit`, depending on context
+
+When in doubt, ask:
+
+> Am I talking about the branded product, or the literal command/package name?
+
+If it is the product, use `siGit Code`.
+If it is something users type or install, use `sigit`.

sigit_code-1.0.4/.agents/skills/sigit-code-release/SKILL.md

@@ -0,0 +1,57 @@
+---
+name: sigit-code-release
+description: Prepare and verify siGit Code releases. Use when bumping versions, checking Cargo, npm, or PyPI package metadata, validating release notes, confirming CI readiness, or assembling a release checklist for a new siGit Code version.
+---
+
+# siGit Code Release
+
+Use this skill when preparing a release for this repository.
+
+## Focus areas
+
+- Keep the branded product name as `siGit Code` in prose and `sigit` for commands, crate names, repo paths, and package identifiers.
+- Verify version consistency across release surfaces, but respect which files are real sources of truth versus generated or release-time rewritten artifacts.
+- Check release-facing docs such as `README.md`, `CHANGELOG.md`, workflow notes, and package metadata for stale version references or incorrect naming.
+- Validate the local release path pragmatically: formatting, linting, targeted tests, and any repo-specific release checks that matter for the requested version.
+
+## Working approach
+
+1. Read the files that define the release version and distribution metadata before proposing any changes.
+2. Treat `Cargo.toml` as the primary release version source for the Rust crate and the PyPI package in this repository.
+3. Check how the release workflows rewrite or derive versions before editing checked-in npm or Python metadata.
+4. Prefer targeted verification commands that match CI or packaging workflows already present in the repository.
+5. Report blockers clearly: failed checks, version mismatches, missing changelog entries, or unpublished packaging changes.
+
+## Repo-specific release rules
+
+- Bump the crate version in `Cargo.toml`.
+- Update the root `sigit` package entry in `Cargo.lock` when the crate version changes.
+- Add or update the top changelog entry in `CHANGELOG.md` for the release being cut.
+- Do not treat `npm/sigit/package.json` `0.0.0-dev` as a bug by default. The npm release workflow rewrites it at publish time using `npm/scripts/render-main-package.cjs` and the release tag.
+- Do not add a hardcoded version to `pypi/pyproject.toml` for normal releases. PyPI uses `maturin` with `dynamic = ["version"]` and derives the published package version from `Cargo.toml`.
+- Release workflows are tag-driven. `release-github.yml`, `release-npm.yml`, and `release-pypi.yml` all derive `RELEASE_VERSION` from a `v*.*.*` tag or a manually supplied tag input.
+
+## Typical files to inspect
+
+- `Cargo.toml`
+- `Cargo.lock`
+- `CHANGELOG.md`
+- `README.md`
+- `npm/sigit/package.json`
+- `npm/scripts/render-main-package.cjs`
+- `npm/`
+- `pypi/`
+- `.github/workflows/`
+
+## Release checklist
+
+- Version bump is applied everywhere it needs to be.
+- `Cargo.toml` and the root crate entry in `Cargo.lock` match.
+- `CHANGELOG.md` has a correct top entry for the new release.
+- `npm/sigit/package.json` is left at `0.0.0-dev` unless the packaging flow itself changed.
+- `pypi/pyproject.toml` still uses dynamic versioning unless there is a deliberate packaging change.
+- Release workflows still derive their version from the tag as expected.
+- Release notes or changelog entries match the actual changes.
+- CI-equivalent local checks pass for the relevant platform or target.
+- Package names, install commands, and branding stay consistent.
+- Any known release limitations are called out explicitly.

{sigit_code-1.0.2 → sigit_code-1.0.4}/.agents/skills/tool-calling/SKILL.md

@@ -1,4 +1,9 @@
-# Skill: Tool Calling in siGit Code
+---
+name: tool-calling
+description: Implement or debug tool calling in siGit Code across the app, Onde Inference, and mistral.rs. Use when working on tool schemas, execution loops, model support, session cwd handling, or tool-call troubleshooting.
+---
+
+# Tool Calling
 
 ## Overview
 
@@ -287,4 +292,4 @@ The `qwen3_8b()` constructor only exists in the local Onde SDK until it's pushed
 | `sigit/src/setup.rs` | HF cache setup pointing to shared App Group container |
 | `onde/src/inference/types.rs` | `ToolDefinition`, `ToolCallRequest`, `ToolResult`, `ToolAwareResult` |
 | `onde/src/inference/engine.rs` | `send_message_with_tools()`, `send_tool_results()`, `attach_tools()`, `parse_tool_calls()`, `replay_history_with_tools()`, `GgufModelConfig::qwen3_8b()` |
-| `onde/src/inference/models.rs` | Model constants and `SUPPORTED_MODELS` array |
+| `onde/src/inference/models.rs` | Model constants and `SUPPORTED_MODELS` array |

sigit_code-1.0.4/CHANGELOG.md

@@ -0,0 +1,156 @@
+# Changelog
+
+## 1.0.4
+
+This release tightens up the terminal experience and finishes a few release-facing cleanup items.
+
+### What changed
+
+- Added bold rich-text rendering in the TUI for assistant replies, so `**text**` now displays with terminal styling instead of raw markdown markers
+- Refreshed the bundled skill metadata to follow the current Agent Skills `SKILL.md` format
+- Synced the crate release metadata for the `1.0.4` cut
+
+## 1.0.3
+
+This is the cleanup release for the editor-side startup problems.
+
+### What changed
+
+- Fixed ACP sessions failing on the first real prompt because the server claimed the model was ready before anything had actually been loaded
+- Changed ACP startup so the default model loads lazily on the first non-slash prompt instead of pretending it is already in memory
+- Kept `initialize` and `session/new` lightweight while still sending proper progress updates once model loading begins
+- Updated the Onde integration to `1.0.0`
+- Removed a few dependencies we were no longer using
+
+## 1.0.2
+
+This release was supposed to fix the ACP auth breakage. It did fix the stdout pollution problem, but it turned out not to be the whole story.
+
+### What changed
+
+- Delayed model loading in ACP mode so startup diagnostics would not leak into protocol stdout during the auth handshake
+- Tightened up the ACP startup path for editor integrations
+- Refreshed some README wording while cutting `1.0.2`
+
+## 1.0.1
+
+The first patch after `1.0.0` was mostly about making model loading and model switching feel less opaque.
+
+### What changed
+
+- Added ToolCall-based progress UI for startup model loading and downloading
+- Improved model-switch progress reporting in ACP clients
+- Fixed model-load error handling so failed switches did not leave the UI in a weird state
+- Cleaned up a few status messages and docs while the release was going out
+
+## 1.0.0 (2026)
+
+siGit Code has been living in real smbCloud repos for a while now. At some point it stopped feeling like an experiment, so we called it 1.0.
+
+### What this release is
+
+siGit Code is a local coding agent. It runs a quantized model on your machine, talks to editors over ACP, and can read files, run commands, fetch web pages, and write code without sending your project to a hosted API.
+
+You can install it with Cargo, pip, npm, or Homebrew and use it like any other tool on your machine.
+
+### What shipped in 1.0
+
+#### Editor integration
+
+This is the core of the project.
+
+Zed and VS Code can talk to siGit Code over ACP. Multi-turn sessions work. Tool calling works. Session forking works. Working-directory context works. That was the original goal, and it feels solid now.
+
+#### Terminal UI
+
+The terminal UI started as a side quest and turned out to be useful. You get a full-screen ratatui chat, streaming tokens, a spinner while the model is busy, and a model picker you can open in the middle of a session.
+
+It runs on macOS and Linux. Windows gets ACP and editor mode for now. The Windows terminal UI is still unfinished.
+
+#### Tool calling
+
+This is the part that makes siGit Code feel like an agent instead of a chat box. The loop can run up to 10 rounds per message.
+
+Available tools:
+
+- `read_file` / `write_file` / `delete_file`
+- `list_directory` / `search_files`
+- `run_command`, with an optional working directory
+- `read_website`, which fetches a URL and strips it down to readable text
+
+The model can call a tool, inspect the result, and keep going until it has a real answer.
+
+#### Model support
+
+The model list ended up wider than we expected for 1.0:
+
+- Qwen 3 1.7B, 4B, 8B, and 14B
+- Qwen 2.5 1.5B and 3B
+- Qwen 2.5 Coder 1.5B, 3B, and 7B
+- DeepSeek Coder 6.7B
+
+They are all GGUF models and they all come from Hugging Face on first run.
+
+Qwen 3 is the interesting one. It uses extended thinking mode. The model reasons inside `<think>...</think>` blocks before answering. The TUI strips those blocks out and renders them dimmed above the reply, so you can see what happened without turning the whole conversation into noise.
+
+The 8B model is the desktop default. Mobile stays on 1.7B because iOS gives apps roughly 2 to 3 GB of memory, and we learned the hard way that 3B can blow up on an iPhone 16e.
+
+#### Model picker
+
+The model picker shows:
+
+- what is already cached locally
+- what can be downloaded
+- which models support tool calling
+- whether the local cache looks healthy
+
+You can open it with `/models` in the TUI or through the editor config option. Switching models happens in the background and the UI stays alive while the download or load is in progress.
+
+#### smbCloud context
+
+siGit Code knows smbCloud repos better than a generic coding assistant does. It understands the difference between platform-user flows and tenant-app auth flows, how `Project`, `FrontendApp`, `AuthApp`, and GresIQ fit together, and why Next.js SSR deploys are not the same thing as the generic git-push path.
+
+Outside smbCloud, it backs off and behaves like a normal coding agent.
+
+#### Distribution
+
+Distribution took an unreasonable amount of time, honestly.
+
+There are prebuilt binaries for macOS, Linux, and Windows on both arm64 and x64 where relevant, plus install paths through Cargo, PyPI, npm, and Homebrew:
+
+- `cargo install sigit`
+- `pip install sigit-code`
+- `npm install -g @smbcloud/sigit`
+- `brew install sigit`
+
+Getting that whole pipeline to behave across CI, crates.io, PyPI, npm, and Homebrew was basically its own project.
+
+### What still does not work
+
+The Windows terminal UI is still missing.
+
+ACP and editor mode work on Windows. The part that is still missing is the interactive full-screen terminal UI. The blocker is Unix-specific terminal handling that has not been abstracted cleanly yet.
+
+### Changes since 0.1.2
+
+- Added Qwen 3 14B support
+- Added Qwen 3 `<think>` block parsing and separate rendering in the TUI
+- Moved all TUI code into `#[cfg(unix)]`, which fixed a pile of dead-code errors on Windows CI
+- Added live download progress during model switches, including cancellation with Ctrl+C
+- Added model download and loading progress in the Zed agent config panel
+- Added an animated spinner during model switching
+- Added Qwen 2.5 Coder 7B
+- Added downloadable models to the picker, not just locally cached ones
+- Made model selection persist across restarts
+- Added session working-directory support
+- Moved model picker logic into a platform-independent module so Windows can compile without the TUI
+- Added the `/models N` shortcut for picking a model by number
+- Added the `read_website` tool
+- Improved `read_file` handling and empty-reply detection
+- Added async tool execution
+- Fixed CI cross-compilation for macOS, iOS, Linux, and Windows
+- Added npm, PyPI, and Homebrew distribution
+
+---
+
+*© 2026 [smbCloud](https://smbcloud.xyz/) (Splitfire AB).*