Rename all references from storkit to huskies across the codebase:
- .storkit/ directory → .huskies/
- Binary name, Cargo package name, Docker image references
- Server code, frontend code, config files, scripts
- Fix script/test to build frontend before cargo clippy/test
so merge worktrees have frontend/dist available for RustEmbed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The timer tick loop now calls move_story_to_current() before
start_agent(), so stories scheduled from the backlog are moved into the
pipeline automatically when the timer fires. The timer bot command also
accepts backlog stories (previously required current).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
strip_mention_separator now skips all non-ASCII-alphanumeric chars
(emoji, colons, spaces) and returns a slice starting at the first
command character. Fixes mention pills with emoji display names
(e.g. "timmy ⚡️ status") not matching bot commands.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The /help test expected the help overlay to appear, but /help now goes
through botCommand like other slash commands. Updated the test to match.
Also added reader thread join and child.wait() calls to
claude_code.rs to prevent PTY master fd leaks from web UI chat sessions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The reader thread spawned in run_agent_pty_blocking was never joined,
leaving a cloned PTY master fd open after the agent exited. When the
pipeline restarted the agent on the same worktree, the stale fd from
the previous session interfered with the new PTY allocation, causing
Claude Code's bundled ripgrep to crash with:
fatal runtime error: assertion failed: output.write(&bytes).is_ok()
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Builds aarch64-unknown-linux-musl via cross alongside the existing
x86_64 Linux and macOS arm64 targets.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The acceptance gate was hardcoded to run cargo clippy, which fails on
non-Rust projects (Go, Node, etc.). Now the gate only runs script/test
which is project-specific. Clippy is added to storkit's own script/test
so Rust linting is preserved for this project.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The LLM was having the conversation with the user but never following
through with wizard_generate calls. The instructions now spell out
the full workflow: get hint, write content, stage it, show user, confirm.
Also adds "keep moving" instruction so the LLM auto-advances to the
next step after confirmation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@@ -13,17 +13,18 @@ When you start a new session with this project:
- **Be conversational.** Don't show tool names, step numbers, or raw wizard output to the user.
- **Be conversational.** Don't show tool names, step numbers, or raw wizard output to the user.
- **On projects with existing code:** Read the codebase and generate each file, then show the user what you wrote and ask if it looks right.
- **On projects with existing code:** Read the codebase and generate each file, then show the user what you wrote and ask if it looks right.
- **On bare projects with no code:** Ask the user what they want to build, what language/framework they plan to use, and generate files from their answers.
- **On bare projects with no code:** Ask the user what they want to build, what language/framework they plan to use, and generate files from their answers.
- Use `wizard_generate` to create content, show it to the user, then call `wizard_confirm` (they approve), `wizard_retry` (they want changes), or `wizard_skip` (they want to skip this step).
- **You must actually generate the files.** The workflow for each step is: (1) call `wizard_generate` with no args to get a hint, (2) write the file content yourself based on the conversation, (3) call `wizard_generate` again with the `content` argument containing the full file body, (4) show the user what you wrote, (5) call `wizard_confirm` (they approve), `wizard_retry` (they want changes), or `wizard_skip` (they want to skip). Do not stop after discussing — follow through and write the files.
- **Keep moving.** After each step is confirmed, immediately proceed to the next wizard step without waiting for the user to ask.
2. **Check for MCP Tools:** Read `.mcp.json` to discover the MCP server endpoint. Then list available tools by calling:
2. **Check for MCP Tools:** Read `.mcp.json` to discover the MCP server endpoint. Then list available tools by calling:
This returns the full tool catalog (create stories, spawn agents, record tests, manage worktrees, etc.). Familiarize yourself with the available tools before proceeding. These tools allow you to directly manipulate the workflow and spawn subsidiary agents without manual file manipulation.
This returns the full tool catalog (create stories, spawn agents, record tests, manage worktrees, etc.). Familiarize yourself with the available tools before proceeding. These tools allow you to directly manipulate the workflow and spawn subsidiary agents without manual file manipulation.
3. **Read Context:** Check `.storkit/specs/00_CONTEXT.md` for high-level project goals.
3. **Read Context:** Check `.huskies/specs/00_CONTEXT.md` for high-level project goals.
4. **Read Stack:** Check `.storkit/specs/tech/STACK.md` for technical constraints and patterns.
4. **Read Stack:** Check `.huskies/specs/tech/STACK.md` for technical constraints and patterns.
5. **Check Work Items:** Look at `.storkit/work/1_backlog/` and `.storkit/work/2_current/` to see what work is pending.
5. **Check Work Items:** Look at `.huskies/work/1_backlog/` and `.huskies/work/2_current/` to see what work is pending.
---
---
@@ -237,7 +238,7 @@ If a user hands you this document and says "Apply this process to my project":
Story Kit includes a chat bot that can be connected to one messaging platform at a time. The bot handles commands, LLM conversations, and pipeline notifications.
Story Kit includes a chat bot that can be connected to one messaging platform at a time. The bot handles commands, LLM conversations, and pipeline notifications.
**Only one transport can be active at a time.** To configure the bot, copy the appropriate example file to `.storkit/bot.toml`:
**Only one transport can be active at a time.** To configure the bot, copy the appropriate example file to `.huskies/bot.toml`:
| Transport | Example file | Webhook endpoint |
| Transport | Example file | Webhook endpoint |
|-----------|-------------|-----------------|
|-----------|-------------|-----------------|
@@ -247,7 +248,7 @@ Story Kit includes a chat bot that can be connected to one messaging platform at
@@ -118,8 +118,8 @@ To support both Remote and Local models, the system implements a `ModelProvider`
Multiple instances can run simultaneously in different worktrees. To avoid port conflicts:
Multiple instances can run simultaneously in different worktrees. To avoid port conflicts:
- **Backend:** Set `STORKIT_PORT` to a unique port (default is 3001). Example: `STORKIT_PORT=3002 cargo run`
- **Backend:** Set `HUSKIES_PORT` to a unique port (default is 3001). Example: `HUSKIES_PORT=3002 cargo run`
- **Frontend:** Run `npm run dev` from `frontend/`. It auto-selects the next unused port. It reads `STORKIT_PORT` to know which backend to talk to, so export it before running: `export STORKIT_PORT=3002 && cd frontend && npm run dev`
- **Frontend:** Run `npm run dev` from `frontend/`. It auto-selects the next unused port. It reads `HUSKIES_PORT` to know which backend to talk to, so export it before running: `export HUSKIES_PORT=3002 && cd frontend && npm run dev`
When running in a worktree, use a port that won't conflict with the main instance (3001). Ports 3002+ are good choices.
When running in a worktree, use a port that won't conflict with the main instance (3001). Ports 3002+ are good choices.
As a storkit user with multiple Claude Max subscriptions, I want the system to automatically rotate to a different account when one gets rate limited, so that agents and chat don't stall out waiting for limits to reset.
As a huskies user with multiple Claude Max subscriptions, I want the system to automatically rotate to a different account when one gets rate limited, so that agents and chat don't stall out waiting for limits to reset.
## Acceptance Criteria
## Acceptance Criteria
- [ ] OAuth login flow stores credentials per-account (keyed by email), not overwriting previous accounts
- [ ] OAuth login flow stores credentials per-account (keyed by email), not overwriting previous accounts
- [ ] GET /oauth/status returns all stored accounts and their status (active, rate-limited, expired)
- [ ] GET /oauth/status returns all stored accounts and their status (active, rate-limited, expired)
- [ ] When the active account hits a rate limit, storkit automatically swaps to the next available account's refresh token, refreshes, and retries
- [ ] When the active account hits a rate limit, huskies automatically swaps to the next available account's refresh token, refreshes, and retries
- [ ] The bot sends a notification in Matrix/WhatsApp when it swaps accounts
- [ ] The bot sends a notification in Matrix/WhatsApp when it swaps accounts
- [ ] If all accounts are rate limited, the bot surfaces a clear message with the time until the earliest reset
- [ ] If all accounts are rate limited, the bot surfaces a clear message with the time until the earliest reset
- [ ] A new /oauth/authorize login adds to the account pool rather than replacing the current credentials
- [ ] A new /oauth/authorize login adds to the account pool rather than replacing the current credentials
@@ -10,7 +10,7 @@ The `prompt_permission` MCP tool returns plain text ("Permission granted for '..
## How to Reproduce
## How to Reproduce
1. Start the storkit server and open the web UI
1. Start the huskies server and open the web UI
2. Chat with the claude-code-pty model
2. Chat with the claude-code-pty model
3. Ask it to do something that requires a tool NOT in `.claude/settings.json` allow list (e.g. `wc -l /etc/hosts`, or WebFetch to a non-allowed domain)
3. Ask it to do something that requires a tool NOT in `.claude/settings.json` allow list (e.g. `wc -l /etc/hosts`, or WebFetch to a non-allowed domain)
@@ -6,7 +6,7 @@ name: "Retry limit for mergemaster and pipeline restarts"
## User Story
## User Story
As a developer using storkit, I want pipeline auto-restarts to have a configurable retry limit so that failing agents don't loop infinitely consuming CPU and API credits.
As a developer using huskies, I want pipeline auto-restarts to have a configurable retry limit so that failing agents don't loop infinitely consuming CPU and API credits.
These markers are phrases that appear in the scaffold templates (`server/src/io/fs.rs` lines 233 and 269). The detection logic (`is_template_or_missing` at line 59) checks if the file *contains* the marker string. But these phrases are generic enough that real project content can contain them too — especially when the project being managed IS an agentic code assistant (i.e. storkit managing itself).
These markers are phrases that appear in the scaffold templates (`server/src/io/fs.rs` lines 233 and 269). The detection logic (`is_template_or_missing` at line 59) checks if the file *contains* the marker string. But these phrases are generic enough that real project content can contain them too — especially when the project being managed IS an agentic code assistant (i.e. huskies managing itself).
## The Fix
## The Fix
Replace the content-based marker detection with a dedicated sentinel comment that only exists in untouched scaffold templates. The sentinel should be something that would never appear in real content, like an HTML comment:
Replace the content-based marker detection with a dedicated sentinel comment that only exists in untouched scaffold templates. The sentinel should be something that would never appear in real content, like an HTML comment:
```
```
<!-- storkit:scaffold-template -->
<!-- huskies:scaffold-template -->
```
```
Changes needed:
Changes needed:
1. **`server/src/io/onboarding.rs`**: Replace `TEMPLATE_MARKER_CONTEXT` and `TEMPLATE_MARKER_STACK` with a single `TEMPLATE_SENTINEL` constant set to `"<!-- storkit:scaffold-template -->"`. Update `check_onboarding_status` to use it for both context and stack checks.
1. **`server/src/io/onboarding.rs`**: Replace `TEMPLATE_MARKER_CONTEXT` and `TEMPLATE_MARKER_STACK` with a single `TEMPLATE_SENTINEL` constant set to `"<!-- huskies:scaffold-template -->"`. Update `check_onboarding_status` to use it for both context and stack checks.
2. **`server/src/io/fs.rs`**: Add `<!-- storkit:scaffold-template -->` as the first line of both `STORY_KIT_CONTEXT` and `STORY_KIT_STACK` template constants (lines 233 and 269).
2. **`server/src/io/fs.rs`**: Add `<!-- huskies:scaffold-template -->` as the first line of both `STORY_KIT_CONTEXT` and `STORY_KIT_STACK` template constants (lines 233 and 269).
3. **`server/src/io/onboarding.rs` tests**: Update the test `needs_onboarding_true_when_specs_contain_scaffold_markers` to use the sentinel instead of the old marker phrases. Also add a test confirming that content containing "Agentic AI Code Assistant" WITHOUT the sentinel does NOT trigger onboarding.
3. **`server/src/io/onboarding.rs` tests**: Update the test `needs_onboarding_true_when_specs_contain_scaffold_markers` to use the sentinel instead of the old marker phrases. Also add a test confirming that content containing "Agentic AI Code Assistant" WITHOUT the sentinel does NOT trigger onboarding.
@@ -42,7 +42,7 @@ Changes needed:
## Acceptance Criteria
## Acceptance Criteria
- [ ] Scaffold templates contain the sentinel `<!-- storkit:scaffold-template -->` as first line
- [ ] Scaffold templates contain the sentinel `<!-- huskies:scaffold-template -->` as first line
- [ ] `needs_onboarding()` returns false for projects whose specs contain "Agentic AI Code Assistant" but NOT the sentinel
- [ ] `needs_onboarding()` returns false for projects whose specs contain "Agentic AI Code Assistant" but NOT the sentinel
- [ ] `needs_onboarding()` returns true for untouched scaffold content (which contains the sentinel)
- [ ] `needs_onboarding()` returns true for untouched scaffold content (which contains the sentinel)
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Timmy
dave
Dave