Adds an AI-providers docs page for Mixlayer (OpenAI-compatible inference
for open models like GLM and Qwen) and a nav entry, documenting the
OpenAI-Compatible setup for both VS Code and the CLI.
- Remove AI Providers link from Getting Started Configuration (has own section)
- Remove self-referencing subLinks throughout nav files
- Separate AI Adoption Dashboard into its own section in Collaborate
- Reduce redundant navigation entries for cleaner UX
* Add Atomic Chat as a first-class local provider.
Ship the atomic-chat plugin with auto-discovery on localhost:1337, register the provider in models.dev fixtures, and document setup for VS Code and CLI.
* Remove dead code
Removed atomicChat provider mapping from legacy migration.
* Update Atomic Chat provider icon to theme-colored vector.
Replace the embedded raster icon with a currentColor SVG symbol so it matches provider icon styling and inherits UI color consistently.
* Allow optional API key for local Atomic Chat and LM Studio providers.
Load the atomic-chat plugin despite named constant exports, register local-server auth in the plugin, and let CLI and VS Code connect with an empty key on localhost.
* Gate Atomic Chat discovery behind explicit opt-in
* Update packages/plugin-atomic-chat/src/utils/should-probe-atomic-chat.ts
* Remove dead branch in atomic-chat model ref probe.
Drop the modelID check (never equals provider key) and the duplicate providerID branch.
* Fix PR CI: register atomic chat plugin and complete i18n.
Restore atomic-chat in default-plugins after main merge, add missing sidebar locale keys, and annotate shared upstream diffs.
* Format i18n locale files and ProviderConnectDialog with Prettier.
* Address PR review: docs order, narrow annotations, plugin fixes.
Reorder local-models providers per maintainer feedback; use inline kilocode_change markers in dialog-provider. Share ModelStatusCache, fix config discovery abort/timeout, throw on fetch failure, and resolve bot review warnings.
* Align dialog-provider with upstream keymap bindings after rebase.
Restore useBindings instead of useKeyboard so shared-file diff stays minimal and passes annotation checks.
* Update packages/kilo-vscode/webview-ui/src/components/settings/ProviderConnectDialog.tsx
* Deduplicate Atomic Chat /v1/models fetch on config discovery.
Use a single shared models endpoint request in enhanceConfig instead of separate health and discovery calls.
* Fix kilo-code-bot review: import provider key and log cache errors.
Export ATOMIC_CHAT_PROVIDER_KEY from local-providers for the webview, log cache warm failures, and throw on network errors in fetchModelsEndpoint.
* fix(plugin-atomic-chat): harden discovery and reduce chat toasts
Reuse auto-detect model list to avoid duplicate /v1/models calls, wire AbortSignal into fetch, replace silent catches with logging, and only surface validation errors in chat.params.
* fix(plugin-atomic-chat): refresh model cache on chat validation retries
Bypass the 15s model list cache after the first failed attempt so retryWithBackoff can observe newly loaded models.
* Update packages/plugin-atomic-chat/src/utils/index.ts
* fix(plugin-atomic-chat): repair categorizeError not_found branch
Restore return statement and map "not loaded" validation errors to not_found after bot commit broke the if block.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: kilo-code-bot[bot] <240665456+kilo-code-bot[bot]@users.noreply.github.com>
* docs(kilo-docs): scaffold Wasteland docs section
Add stub pages for the Wasteland federated work protocol under
gastown/wasteland/ and register them in the code-with-ai nav.
SideNav only renders one level of subLinks, so Wasteland pages are
flattened into the Gastown subLinks list with a 'Wasteland: ' prefix.
Content for each stub will be filled in by later beads in the convoy.
* docs(kilo-docs): noindex Wasteland stub pages until content lands
Adds a noindex frontmatter flag (read by _app.tsx, emits a robots
noindex,nofollow meta tag) and applies it to the 7 Wasteland stub
pages. Stubs are intentionally thin in this scaffolding PR;
follow-up beads will flesh them out and remove the flag.
Walks through what the thumbs up/down feature does in both the VS Code
extension and the CLI/TUI, why ratings matter, exactly what gets sent
when a user rates a response, and how to disable it via VS Code's
telemetry setting or KILO_TELEMETRY_LEVEL. Privacy claims are scoped
to the rating event itself; broader telemetry questions defer to
PRIVACY.md.
Linked from the Productivity Tools group in the Code With AI nav,
between Voice Transcription and the Agent Behavior subsection.
* fix(kilo-docs): rewrite zenmux doc and add to nav sidebar
Rewrite zenmux.md to match the standard provider doc format
(openrouter, minimax, etc.) and add ZenMux entry to ai-providers nav.
Changes:
- Add sidebar_label frontmatter, Website link, consistent section names
- Remove unrelated API code examples and product feature descriptions
- Add Supported Transforms and Tips and Notes sections
- Fix typo (Visi -> Visit) and codicon syntax
- Add ZenMux to ai-providers nav config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Update packages/kilo-docs/pages/ai-providers/zenmux.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* chore: update nix node_modules hashes
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: kilo-maintainer[bot] <kilo-maintainer[bot]@users.noreply.github.com>
Flesh out all 7 sub-pages with comprehensive content:
- Quick Start: town creation, PAT setup, first task flow
- Concepts: towns, beads, convoys, rigs, agents, micro-adversarial loops
- The Mayor: capabilities, tools, communication tips
- Sling Work: single tasks, convoys, staged convoys, DAG execution
- Code Review: refinery pipeline, adversarial loops, merge strategies
- Settings: models, GitHub PAT, merge strategy, env vars, custom instructions
- Troubleshooting: common failure modes and fixes
Includes React Flow diagram placeholders (TODO comments) describing
what each interactive diagram should visualize.
Also moves Gastown nav link under Platforms section with sub-links and
updates page title to 'Gas Town by Kilo'.
Add initial page structure for /code-with-ai/gastown/ with overview,
quick-start, concepts, mayor, sling-work, code-review, settings, and
troubleshooting pages. Register the section in the sidebar nav config.
* docs(kilo-docs): document codebase indexing for CLI and new VS Code extension
The existing Codebase Indexing page was flagged as legacy-only. Rewrite it to
cover the new shared implementation in the CLI and VS Code extension, including
the `/indexing` command, the `indexing` config section, LanceDB, and the full
list of supported embedding providers.
* docs(kilo-docs): address review feedback on codebase indexing
- Add a top-level warning that indexing is experimental in the CLI and
new VS Code extension
- Add a new 'Enabling the feature' section that documents the
`experimental.semantic_indexing` flag and where to toggle it (CLI
`kilo.jsonc`, VS Code Experimental settings, or legacy direct config)
- Split Embedding Providers and Vector Stores into new-platform vs
VSCode (Legacy) tabs so the legacy section only lists providers it
actually supports (OpenAI, Gemini, Ollama; Qdrant only)
- Fix the Vercel AI Gateway link to point at the product docs
(https://vercel.com/docs/ai-gateway) instead of the raw API endpoint
- Clarify that the Mistral indexing provider uses a La Plateforme API
key, not the Codestral key from the autocomplete setup guide
- Call out the experimental flag prerequisite at each configuration
entry point
* docs(kilo-docs): rename combined tab to 'VSCode & CLI'
* chore: revert unrelated package-lock changes
* docs(kilo-docs): order tabs VSCode, CLI, VSCode (Legacy)
* docs(kilo-docs): consolidate platform-specific indexing docs into one tabs block
Initial high-level design proposal for thumbs up/down feedback on
assistant messages. Covers the problem motivation, scope, payload
differences between Kilo Gateway and direct providers, and open
questions. Implementation details intentionally kept out — those
belong in the PR diff.
Document the plugin system for the Kilo CLI: installation paths, hooks
reference, custom tools, examples, and troubleshooting. Plugins were
previously only covered in upstream OpenCode docs.