llmkit

Imported from dpoage/llmkit (AGENTS.md). Install upstream with npx skills add dpoage/llmkit. Copyright stays with the author.

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd prime for full workflow context.

Architecture in one line: Issues live in a local Dolt database (.beads/dolt/); cross-machine sync uses bd dolt push/pull (a git-compatible protocol), stored under refs/dolt/data on your git remote — separate from refs/heads/* where your code lives. .beads/issues.jsonl is a passive export, not the wire protocol.

See SYNC_CONCEPTS.md for the one-screen overview and anti-patterns (don't treat JSONL as the source of truth; don't bd import during normal operation; don't reach for third-party Dolt hosting before trying the default).

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts.

Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.

Use these forms instead:

# Force overwrite without prompting
cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file

# For recursive operations
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Other commands that may prompt:

• scp - use -o BatchMode=yes for non-interactive
• ssh - use -o BatchMode=yes to fail instead of prompting
• apt-get - use -y flag
• brew - use HOMEBREW_NO_AUTO_UPDATE=1 env var

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work
bd close <id>         # Complete work

Rules

• Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
• Run bd prime for detailed command reference and session close protocol
• Use bd remember for persistent knowledge — do NOT use MEMORY.md files

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.

Agent Context Profiles

The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions.

• Conservative (default): Use bd for task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked. At handoff, report changed files, validation, and suggested next commands.
• Minimal: Keep tool instruction files as pointers to bd prime; use the same conservative git policy unless active instructions say otherwise.
• Team-maintainer: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of session close. A current "do not commit" or "do not push" instruction still wins.

Session Completion

This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and orchestrator instructions.

1. File issues for remaining work - Create beads for anything that needs follow-up
2. Run quality gates (if code changed) - Tests, linters, builds
3. Update issue status - Close finished work, update in-progress items
4. Handle git/sync by active profile:

   # Conservative/minimal/default: report status and proposed commands; wait for approval.
   git status
   
   # Team-maintainer opt-in only, unless current instructions forbid it:
   git pull --rebase
   git push
   git status

5. Hand off - Summarize changes, validation, issue status, and any blocked sync/commit/push step

Critical rules:

• Explicit user or orchestrator instructions override this Beads block.
• Do not commit or push without clear authority from the active profile or the current user request.
• If a required sync or push is blocked, stop and report the exact command and error.

Beads Issue Tracker

Use Beads (bd) for durable task tracking in repositories that include it. Use the beads skill at .agents/skills/beads/SKILL.md (project install) or ~/.agents/skills/beads/SKILL.md (global install) for Beads workflow guidance, then use the bd CLI for issue operations.

Quick Reference

bd ready                # Find available work
bd show <id>            # View issue details
bd update <id> --claim  # Claim work
bd close <id>           # Complete work
bd prime                # Refresh Beads context

Rules

• Use bd for all task tracking; do not create markdown TODO lists.
• Run bd prime when Beads context is missing or stale. Codex 0.129.0+ can load Beads context automatically through native hooks; use /hooks to inspect or toggle them.
• Keep persistent project memory in Beads via bd remember; do not create ad hoc memory files.

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.

Keep in sync: everything from ## Build & Test to the end of this file is byte-identical to CLAUDE.md (bead llmkit-ygq.20). Edit both files in the same commit, then verify with diff <(sed -n '/^## Build/,$p' AGENTS.md) <(sed -n '/^## Build/,$p' CLAUDE.md).

Build & Test

The suites, commands, and skip rules live in docs/testing.md; run the scoped checks your task names, not the whole gate.

Acceptance rule: any change to an adapter, the agent loop, or a llmkit.Capabilities field must name its hermetic test and its live case; provider/live_registry_test.go enforces this in the plain go test ./... suite.

Exact local live run (compat lane; costs real money). The operator env file path lives here, never in docs/:

set -a; . ~/.config/bugbot/env; set +a
export LLMKIT_LIVE_COMPAT_API_KEY="$MINIMAX_API_KEY"
export LLMKIT_LIVE_COMPAT_BASE_URL=https://api.minimax.io/v1
export LLMKIT_LIVE_COMPAT_MODEL=MiniMax-M3
export LLMKIT_LIVE_COMPAT_CAPS=parallel_tool_calls,prompt_caching
go test -tags live -count=1 ./provider/ ./agent/ ./examples/... -v

Architecture

Read docs/design.md for the layering and the decision records. Read each package's contract with go doc, run from the repository root:

Conventions

• Per-role block rule: user messages carry text/image/document blocks; assistant text/thinking; system and tool-result text only — enforced before any wire call. Canonical: go doc github.com/dpoage/llmkit.
• Usage.InputTokens is the total prompt size and includes the cache-read and cache-creation subsets; use ChargeableTokens for discounted math. Canonical: go doc github.com/dpoage/llmkit.
• Capabilities enforcement classes live in the field docs in llmkit.go; do not restate them here, because nothing guards this file against the code (llmkit-ygq.21). Canonical: go doc github.com/dpoage/llmkit and docs/capabilities.md.