Skip to content

Releases: sunilp/jam-cli

v0.11.4

25 Mar 03:58

Choose a tag to compare

  • Clean output by default: just 'Thinking...' and 'Searching codebase...'
  • --verbose flag shows full planning, tool calls, verifier, critic logs
  • --quiet suppresses everything
  • Non-code questions keep project context, skip codebase search

v0.11.3

25 Mar 03:56

Choose a tag to compare

  • Fix: non-code questions retain project context (workspace, symbols, past sessions) while skipping codebase search
  • 'what's next in phase 2' now gives project-aware answers without hallucinating from irrelevant file searches

v0.11.2

25 Mar 03:52

Choose a tag to compare

  • Fix: jam ask no longer enters codebase search mode for non-code questions
  • General/strategy/planning questions now answered directly without tool loops

v0.11.1

25 Mar 03:49

Choose a tag to compare

  • Bridge file (~/.jam/copilot-bridge.json) for reliable Copilot detection in any terminal
  • jam models set command to set default model
  • Default Copilot model auto-detected from VSCode
  • Windows CI test fixes

v0.11.0 — Windows Support

23 Mar 17:26

Choose a tag to compare

Windows Compatibility

Jam now works on Windows (PowerShell, cmd.exe, VSCode terminal).

  • jam ports — Windows netstat support
  • jam vibes — pure Node.js, no Unix shell commands
  • jam completion — PowerShell tab completion
  • Sandbox — cmd.exe on Windows
  • Path display — normalized separators
  • npx/npm — .cmd shim resolution on Windows
  • Process signals — cross-platform termination

CI

  • Windows added to CI matrix
  • Homebrew formula auto-updates on release

v0.10.0 — Jam has a personality

22 Mar 10:04

Choose a tag to compare

Jam has a personality

Jam is no longer a generic AI assistant. It is now the senior dev who has seen everything — direct, opinionated, and warm without being corporate.

Personality across all touchpoints

  • JAM_SOUL — central personality definition prepended to all AI system prompts
  • System prompts — ask, chat, run, go, planner, worker all speak with jam voice
  • Command prompts — trace, verify, commit AI prompts updated
  • Error messages — all 25 error hints rewritten to be empathetic and actionable
  • Status messages — run and go progress output is direct and concise
  • jam doctor — conversational output (Checking your setup... You are good to go.)
  • jam init — welcoming first-run (Welcome to Jam. Let me figure out what you have got...)
  • Fortune cookies — 8 new developer wisdoms in jam vibes

Fixes

  • All ESLint errors resolved (CI was failing on lint)
  • tree-sitter parser handles grammar loading failures gracefully
  • TypeScript extractor findEnclosingFunction correctly skips variable_declarator for plain assignments
  • SQL tests fall back to regex mode when tree-sitter-sql grammar is ABI-incompatible

v0.9.0 — Agent Engine: Orchestrator, Parallel Workers, Workspace Intelligence

20 Mar 18:43

Choose a tag to compare

Agent Engine

Jam now has a full autonomous agent engine powering both jam go (interactive console) and jam run (one-shot).

Highlights

  • Orchestrator — Decomposes tasks into subtasks with a dependency graph, dispatches parallel workers, merges results
  • Parallel Workers — Independent subtasks run concurrently (up to 3 by default, configurable with --workers)
  • Workspace Intelligence — Profiles your project code style, test patterns, naming conventions, and frameworks before writing code. Cached in .jam/workspace-profile.json
  • Tiered Permissions — Commands classified as safe/moderate/dangerous with automatic approval or confirmation
  • OS Sandboxsandbox-exec (macOS) / unshare/firejail (Linux) restricts filesystem access to workspace
  • Multimodal Input--image flag for vision-capable models (OpenAI, Anthropic, Gemini, Ollama/llava)
  • File-Lock Protocol — Prevents parallel workers from conflicting on shared files, with deadlock detection

New Commands & Flags

  • jam go — Interactive agent console with /stop, /status, /help, /exit
  • jam go --auto — Fully autonomous mode
  • jam run --auto — Autonomous one-shot (implies --yes)
  • --workers <n> — Max parallel workers
  • --image <path> — Attach image for vision models
  • --no-sandbox — Disable OS-level sandbox
  • --file <path> — Read task from file (jam run)
  • JAM_LEGACY_RUN=1 — Fallback to pre-0.9 run behavior

Stats

  • 28 new files in src/agent/
  • 158 new tests (811 total)
  • Zero new dependencies

v0.8.7 — jam go: Interactive Agent Mode

17 Mar 18:42

Choose a tag to compare

New Features

  • jam go — Claude Code-like interactive agent session
    • Full write tools: write_file, apply_patch, run_command, git operations
    • Reads your codebase, plans changes, writes code, runs tests
    • Permission enforcement via toolPolicy config
    • Streaming output with tool execution indicators
    • Session persistence
    • Ctrl+C to interrupt, double Ctrl+C to exit

Bug Fixes

  • verify, diff, review, commit, patch now work with Copilot proxy (removed incorrect tool-support guard)
  • Only jam run requires tool-calling provider support

v0.8.6 — Fix: verify, diff, review, commit, patch work with Copilot proxy

17 Mar 18:31

Choose a tag to compare

Bug Fixes

  • Removed incorrect tool-support guard from verify, diff, review, commit, and patch commands
  • These commands only use streaming (not tool calling) and now work correctly with the Copilot proxy backend
  • Only jam run retains the tool-support guard since it actually uses tool calling

v0.8.5 — VSCode Context: explain this, selection, git root

17 Mar 18:19

Choose a tag to compare

New Features

  • jam explain with no args uses the active VSCode editor file
  • jam explain this works naturally in VSCode terminal
  • Selected text in VSCode editor is explained when using jam explain
  • All git commands (jam review, jam commit, jam diff, etc.) now resolve the correct git root from the active editor file — fixes 'Failed to determine current branch' errors in multi-repo workspaces
  • New /v1/context endpoint on the VSCode proxy server

Bug Fixes

  • jam doctor shows keytar/ripgrep as warnings [!] instead of failures [x]
  • Copilot adapter lazily initializes — all commands work without explicit validateCredentials()