v1.1.0

What's Changed

• feat(onboarding): add a demo mode that runs without an API key by @mangit955 in #57
• fix(onboarding): point demo mode at a host that exists by @mangit955 in #58
• feat(runtime): judge a command's risk by where it will run by @mangit955 in #59

Full Changelog: v1.0.0...v1.1.0

v1.0.0

What's Changed

• feat(runtime): give each project its own conversations by @mangit955 in #52
• chore: remove dead code and unify two repeated patterns by @mangit955 in #53
• chore(tui): give the interface one palette, one grid and one glyph set by @mangit955 in #54
• feat(tools): add a persistent repl, background processes and image reading by @mangit955 in #55
• feat(runtime): start interactive sessions fresh instead of continuing by @mangit955 in #56

Full Changelog: v0.9.0...v1.0.0

v0.9.0

What's Changed

• chore: remove unused imports and dead ui plumbing by @mangit955 in #50
• chore: stop shipping two claims nothing exercised by @mangit955 in #51

Full Changelog: v0.8.2...v0.9.0

v0.8.2

What's Changed

• Chore/prune agent worktrees by @mangit955 in #49

Full Changelog: v0.8.1...v0.8.2

v0.8.1

What's Changed

• fix(tui): stop a chord answering the diff you are reviewing by @mangit955 in #47
• feat(tui): stop the interface and the step budget fighting the user by @mangit955 in #48

Full Changelog: v0.8.0...v0.8.1

v0.8.0

What's Changed

• feat(runtime): let a session plan without touching the repo by @mangit955 in #43
• feat(provider): run GPT as a first-class provider by @mangit955 in #42
• fix(provider): send the offered tool list, not the whole registry by @mangit955 in #44
• fix(tests): say which host the wire test means by @mangit955 in #45
• refactor: move the agent loop and the provider clients out of config/ by @mangit955 in #46

Full Changelog: v0.7.0...v0.8.0

v0.6.4

What's Changed

• fix(config): don't refuse to start over another tool's API key by @mangit955 in #27

Full Changelog: v0.6.3...v0.6.4

v0.6.3

What's Changed

• feat(runtime): measure token usage and prompt composition per iteration by @mangit955 in #22
• fix(docs): regenerate surface.json for the 0.6.2 version bump by @mangit955 in #23
• feat(runtime): record whether a turn left its edits unverified by @mangit955 in #24
• fix(docs): derive the site version from package.json instead of snaps… by @mangit955 in #25
• feat(harbor): report token usage and context composition per trial by @mangit955 in #26

Full Changelog: v0.6.2...v0.6.3

v0.6.2

What's Changed

• fix(approval): enforce workspace boundaries for all write commands by @mangit955 in #17
• fix(edit-file): require unique matches and add explicit replace_all support by @mangit955 in #18
• fix(cli): unify model catalog and improve models command UX by @mangit955 in #19
• Fix/hermetic tests and linux timeout by @mangit955 in #20
• feat: benchmark WoopCode on Harbor datasets via an installed-agent integration by @mangit955 in #21

Full Changelog: v0.6.1...v0.6.2

v0.6.1

What's Changed

• feat: created landing page by @mangit955 in #16

Full Changelog: v0.6.0...v0.6.1