Merge branch 'dev' into feature/acp-sacp-tee-tracing

Resolved conflicts by preserving both feature sets:
- ACP traffic tracing (current branch via sacp-tee proxy)
- Message history persistence (dev branch)

Changes:
- Added both trace_config and nori_home/history_persistence fields to AcpBackendConfig
- Added both acp_trace_enabled and history_persistence to config types
- Preserved enhanced error handling from dev in connection spawning
- Added environment variable support (.envs) to subprocess spawning
- Merged documentation for both features in tui/docs.md

Both features are independent and now work together:
- Trace config enables debugging of ACP JSON-RPC traffic
- History persistence enables message history storage and navigation
🤖 Generated with [Nori](https://nori.ai)

Co-Authored-By: Nori <contact@tilework.tech>

Author: CSRessel

.claude/CLAUDE.md

@@ -70,19 +70,19 @@ You have access to the Nori skills system. Read the full instructions at: /home/
 
 ## Available Skills
 
-Found 17 skills:
+Found 23 skills:
 /home/clifford/Documents/source/nori/cli/.claude/skills/writing-plans/SKILL.md
   Name: Writing-Plans
   Description: Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
 /home/clifford/Documents/source/nori/cli/.claude/skills/webapp-testing/SKILL.md
   Name: webapp-testing
-  Description: Use this skill to build features or debug anything that uses a webapp frontend.
-/home/clifford/Documents/source/nori/cli/.claude/skills/using-skills/SKILL.md
-  Name: Getting Started with Abilities
-  Description: Describes how to use abilities. Read before any conversation.
+  Description: Use this skill to build features that requires modifying a webapp frontend.
 /home/clifford/Documents/source/nori/cli/.claude/skills/using-screenshots/SKILL.md
   Name: Taking and Analyzing Screenshots
   Description: Use this to capture screen context.
+/home/clifford/Documents/source/nori/cli/.claude/skills/using-skills/SKILL.md
+  Name: Getting Started with Abilities
+  Description: Describes how to use abilities. Read before any conversation.
 /home/clifford/Documents/source/nori/cli/.claude/skills/using-git-worktrees/SKILL.md
   Name: Using Git Worktrees
   Description: Use this whenever you need to create an isolated workspace.
@@ -92,18 +92,30 @@ Found 17 skills:
 /home/clifford/Documents/source/nori/cli/.claude/skills/testing-anti-patterns/SKILL.md
   Name: Testing-Anti-Patterns
   Description: Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
-/home/clifford/Documents/source/nori/cli/.claude/skills/test-driven-development/SKILL.md
-  Name: Test-Driven Development (TDD)
-  Description: Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
 /home/clifford/Documents/source/nori/cli/.claude/skills/systematic-debugging/SKILL.md
   Name: Systematic-Debugging
   Description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
+/home/clifford/Documents/source/nori/cli/.claude/skills/test-driven-development/SKILL.md
+  Name: Test-Driven Development (TDD)
+  Description: Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
 /home/clifford/Documents/source/nori/cli/.claude/skills/root-cause-tracing/SKILL.md
   Name: Root-Cause-Tracing
   Description: Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
 /home/clifford/Documents/source/nori/cli/.claude/skills/receiving-code-review/SKILL.md
   Name: Code-Review-Reception
   Description: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
+/home/clifford/Documents/source/nori/cli/.claude/skills/write-noridoc/SKILL.md
+  Name: Write Noridoc
+  Description: Write or update documentation in the server-side noridocs system.
+/home/clifford/Documents/source/nori/cli/.claude/skills/recall/SKILL.md
+  Name: Recall
+  Description: Search the Nori knowledge base for relevant context, solutions, and documentation.
+/home/clifford/Documents/source/nori/cli/.claude/skills/sync-noridocs/SKILL.md
+  Name: Sync Noridocs
+  Description: Sync all local docs.md files to server-side noridocs system.
+/home/clifford/Documents/source/nori/cli/.claude/skills/list-noridocs/SKILL.md
+  Name: List Noridocs
+  Description: List all server-side noridocs, optionally filtered by repository and/or path prefix.
 /home/clifford/Documents/source/nori/cli/.claude/skills/handle-large-tasks/SKILL.md
   Name: Handle-Large-Tasks
   Description: Use this skill to split large plans into smaller chunks. This skill manages your context window for large tasks. Use it when a task will take a long time and cause context issues.
@@ -113,15 +125,21 @@ Found 17 skills:
 /home/clifford/Documents/source/nori/cli/.claude/skills/creating-skills/SKILL.md
   Name: Creating-Skills
   Description: Use when you need to create a new custom skill for a profile - guides through gathering requirements, creating directory structure, writing SKILL.md, and optionally adding bundled scripts
-/home/clifford/Documents/source/nori/cli/.claude/skills/creating-debug-tests-and-iterating/SKILL.md
-  Name: creating-debug-tests-and-iterating
-  Description: Use this skill when faced with a difficult debugging task where you need to replicate some bug or behavior in order to see what is going wrong.
 /home/clifford/Documents/source/nori/cli/.claude/skills/building-ui-ux/SKILL.md
   Name: Building UI/UX
   Description: Use when implementing user interfaces or user experiences - guides through exploration of design variations, frontend setup, iteration, and proper integration
 /home/clifford/Documents/source/nori/cli/.claude/skills/brainstorming/SKILL.md
   Name: Brainstorming
   Description: IMMEDIATELY USE THIS SKILL when creating or develop anything and before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation
+/home/clifford/Documents/source/nori/cli/.claude/skills/memorize/SKILL.md
+  Name: Memorize
+  Description: Use this to save important implementation decisions, patterns, or context to the Nori knowledge base for future sessions.
+/home/clifford/Documents/source/nori/cli/.claude/skills/prompt-analysis/SKILL.md
+  Name: Prompt Analysis
+  Description: Analyze prompts for quality and best practices before sending them to Claude.
+/home/clifford/Documents/source/nori/cli/.claude/skills/read-noridoc/SKILL.md
+  Name: Read Noridoc
+  Description: Read documentation from the server-side noridocs system by file path.
 
 Check if any of these skills are relevant to the user's task. If relevant, use the Read tool to load the skill before proceeding.
 

.claude/settings.json

@@ -22,12 +22,6 @@
       "Bash(cargo t:*)",
       "Bash(cargo search:*)"
     ],
-    "additionalDirectories": [
-      ".claude/profiles",
-      ".claude/skills",
-      "/home/clifford/Documents/source/nori/cli/.claude/profiles",
-      "/home/clifford/Documents/source/nori/cli/.claude/skills"
-    ],
     "sandbox": {
       "filesystem": {
         "read": {

.claude/skills/creating-debug-tests-and-iterating/SKILL.md

@@ -18,7 +18,6 @@ Place marker on the line immediately before the test function/block definition.<
 <system-reminder>If you have more than one test that you need to write, you should write all of them before moving to the GREEN phase.</system-reminder>
 3. Write the minimal amount of code necessary to make the test pass (GREEN phase)
 4. Verify the test now passes due to the behavior of the application.
-    - If you go through three loops without making progress, switch to running `/home/clifford/Documents/source/nori/cli/skills/creating-debug-tests-and-iterating`
 5. Refactor the code to clean it up.
 6. Verify tests still pass.
 </required>

.claude/skills/test-driven-development/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: webapp-testing
-description: Use this skill to build features or debug anything that uses a webapp frontend.
+description: Use this skill to build features that requires modifying a webapp frontend.
 ---
 
 <required>

.claude/skills/webapp-testing/SKILL.md

@@ -13,20 +13,18 @@ description: Use when design is complete and you need detailed implementation ta
 - Think about questions or areas that require clarity. Add them to the plan.
 - Emphasize how you will test your plan.
 - Present plan to user.
-</required>
+  </required>
 
 # Guidelines
 
 ## Overview
 
-Create a comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD.
+Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD.
 
 Assume they are a talented developer. However, assume that they know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
 
 Do not add code, but include enough detail that the necessary code is obvious.
 
-Do not write a file to disk unless explicitly asked.
-
 ## Bite-Sized Task Granularity
 
 **Each step is one action (2-5 minutes):**
@@ -91,3 +89,10 @@ types. Your tests should NOT simply test mocks. Always test actual behavior.</sy
 
 ---
 ```
+
+## Remember
+
+- Exact file paths always, taking into account worktrees
+- Exact commands with expected output
+- Reference relevant skills with @ syntax
+- DRY, YAGNI, TDD

.claude/skills/writing-plans/SKILL.md

@@ -11,6 +11,10 @@ jobs:
     defaults:
       run:
         working-directory: ./codex-rs
+    env:
+      # Disable sccache wrapper from .cargo/config.toml since it's not available
+      # in the cargo-deny Docker container.
+      RUSTC_WRAPPER: ""
     steps:
       - name: Checkout
         uses: actions/checkout@v6

.github/workflows/cargo-deny.yml

@@ -6,8 +6,7 @@
 
 **One CLI, multiple AI providers.** Nori is a local AI coding agent that lets you switch between Claude, Gemini, and Codex. All from the same native CLI.
 
-<!-- TODO: Add TUI screenshot here -->
-<!-- ![Nori TUI Screenshot](assets/screenshot.png) -->
+![Nori TUI Screenshot](https://raw.githubusercontent.com/tilework-tech/nori-cli/refs/heads/dev/assets/nori-cli_2026-01-13.png)
 
 ## Install
 
@@ -23,23 +22,24 @@ Or download binaries from [GitHub Releases](https://github.com/tilework-tech/nor
 nori
 ```
 
-That's it. Nori launches an interactive TUI where you can chat, run commands, and let the AI assist with your codebase.
+That's it. The agent you choose will rely on existing auth if you have previously been using Claude Code, Codex, or Gemini on this system (and if not, login instructions are below). Nori launches an interactive TUI where you can chat, run commands, and let the AI assist with your codebase.
 
 ## Providers
 
 Each provider you plan to use needs to be authenticated separately before use. Switch between AI providers with the `/agent` command:
 
 | Provider | Command | Authentication |
 |----------|---------|----------------|
-| Claude | `npm i -g @zed-industries/claude-code-acp` (default) | `npx @anthropic-ai/claude-code setup-token` |
+| Claude | `npm i -g @zed-industries/claude-code-acp` (default) | `npx @anthropic-ai/claude-code` and then follow the login flow |
 | Gemini | `npm i -g @google/gemini-cli --experimental-acp` | `npx @google/gemini-cli` and then `/auth` |
 | OpenAI | `npm i -g @zed-industries/codex-acp` | `npx @openai/codex login` |
 
 ## Features
 
 - **Multi-provider**: Anthropic's Claude Code, Google DeepMind's Gemini, and OpenAI's Codex
-- **Sandboxed execution**: Commands run in OS-level security sandboxes
+- **Improved terminal interface**: Fast incremental renders in Ratatui, double buffered scrollback history, and built in Rust for performance
 - **Coming Soon!**
+    - **Sandboxed execution**: Commands run in OS-level security sandboxes
     - **MCP integration**: Connect to Model Context Protocol servers for extended tools
     - **Session persistence**: Save and resume conversations with `nori resume`
     - **Multi-agent orchestration**: Alternate between multiple agent sessions
@@ -48,6 +48,8 @@ Each provider you plan to use needs to be authenticated separately before use. S
 
 Nori CLI is built on the great work within [OpenAI Codex CLI](https://github.com/openai/codex).
 
+Nori CLI is working with the great protocol led by [Zed Industries](https://github.com/agentclientprotocol/agent-client-protocol) for orchestrating agents.
+
 ## License
 
 [Apache-2.0](LICENSE)