Skip to content

Releases: RoderAI/roder

roder 0.1.2 (2026-06-16)

16 Jun 04:26
11df155

Choose a tag to compare

Features

Fireworks AI inference provider

Add the first-party fireworks inference provider with account-scoped model ids, Fireworks-specific API-key configuration, OpenAI-compatible Responses transport, offline model metadata, model discovery, and app-server provider-list coverage.

Fixes

Added first-class kimi-code (aliases: kimi, moonshot) inference provider and roder-ext-kimi-code crate.

  • Kimi Code subscription OAuth uses the managed API (api.kimi.com/coding/v1) with Kimi device headers and kimi-code-cli User-Agent; API keys still use Moonshot Open Platform (api.moonshot.ai/v1).
  • Catalog entry + kimi-for-coding model (K2.7 Code).
  • Device OAuth against auth.kimi.com with roder auth login kimi-code, TUI/app-server auth/kimi-code/*, and token storage under ~/.roder/auth/kimi-code.json.
  • API key fallback via env/config (KIMI_CODE_API_KEY, RODER_KIMI_CODE_API_KEY).
  • Registered via extension host (always available, like SuperGrok).
  • Docs: docs/roder-kimi-code-provider.md.
  • Live smoke test added (opt-in via RODER_KIMI_CODE_LIVE=1).

roder-core 0.1.2 (2026-06-16)

16 Jun 04:26
11df155

Choose a tag to compare

Fixes

  • Improve context compaction across phases 2–4: prune old tool outputs before full compaction, add LLM state-snapshot summarization with verify/reject, hysteresis coalescing, /compact via thread/compact, context.compaction_skipped metrics, and a Grok-style loop regression fixture. Phase 1 fixes remain: compaction boundary on load, once-per-turn guard, ProviderMetadata exclusion from token estimates, and suffix retention from the last user message.

roder-app-server 0.1.2 (2026-06-16)

16 Jun 04:26
11df155

Choose a tag to compare

Fixes

  • Improve context compaction across phases 2–4: prune old tool outputs before full compaction, add LLM state-snapshot summarization with verify/reject, hysteresis coalescing, /compact via thread/compact, context.compaction_skipped metrics, and a Grok-style loop regression fixture. Phase 1 fixes remain: compaction boundary on load, once-per-turn guard, ProviderMetadata exclusion from token estimates, and suffix retention from the last user message.

Fireworks AI inference provider

Add the first-party fireworks inference provider with account-scoped model ids, Fireworks-specific API-key configuration, OpenAI-compatible Responses transport, offline model metadata, model discovery, and app-server provider-list coverage.

Added first-class kimi-code (aliases: kimi, moonshot) inference provider and roder-ext-kimi-code crate.

  • Kimi Code subscription OAuth uses the managed API (api.kimi.com/coding/v1) with Kimi device headers and kimi-code-cli User-Agent; API keys still use Moonshot Open Platform (api.moonshot.ai/v1).
  • Catalog entry + kimi-for-coding model (K2.7 Code).
  • Device OAuth against auth.kimi.com with roder auth login kimi-code, TUI/app-server auth/kimi-code/*, and token storage under ~/.roder/auth/kimi-code.json.
  • API key fallback via env/config (KIMI_CODE_API_KEY, RODER_KIMI_CODE_API_KEY).
  • Registered via extension host (always available, like SuperGrok).
  • Docs: docs/roder-kimi-code-provider.md.
  • Live smoke test added (opt-in via RODER_KIMI_CODE_LIVE=1).

roder-api 0.1.2 (2026-06-16)

16 Jun 04:25
11df155

Choose a tag to compare

Features

Fireworks AI inference provider

Add the first-party fireworks inference provider with account-scoped model ids, Fireworks-specific API-key configuration, OpenAI-compatible Responses transport, offline model metadata, model discovery, and app-server provider-list coverage.

Fixes

  • Improve context compaction across phases 2–4: prune old tool outputs before full compaction, add LLM state-snapshot summarization with verify/reject, hysteresis coalescing, /compact via thread/compact, context.compaction_skipped metrics, and a Grok-style loop regression fixture. Phase 1 fixes remain: compaction boundary on load, once-per-turn guard, ProviderMetadata exclusion from token estimates, and suffix retention from the last user message.
  • SuperGrok now lists only Grok Build 0.1 (500k context) and Grok Composer 2.5 Fast (200k context), with curated catalog metadata instead of raw xAI /models discovery.

Added first-class kimi-code (aliases: kimi, moonshot) inference provider and roder-ext-kimi-code crate.

  • Kimi Code subscription OAuth uses the managed API (api.kimi.com/coding/v1) with Kimi device headers and kimi-code-cli User-Agent; API keys still use Moonshot Open Platform (api.moonshot.ai/v1).
  • Catalog entry + kimi-for-coding model (K2.7 Code).
  • Device OAuth against auth.kimi.com with roder auth login kimi-code, TUI/app-server auth/kimi-code/*, and token storage under ~/.roder/auth/kimi-code.json.
  • API key fallback via env/config (KIMI_CODE_API_KEY, RODER_KIMI_CODE_API_KEY).
  • Registered via extension host (always available, like SuperGrok).
  • Docs: docs/roder-kimi-code-provider.md.
  • Live smoke test added (opt-in via RODER_KIMI_CODE_LIVE=1).

roder v0.1.1

15 Jun 22:23
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Features

First-party image generation providers (OpenAI GPT Image and Google Gemini Nano Banana)

Provider-neutral image generation through the core media API: an image-capable
MediaGenerationRequest/multi-output MediaGenerationResponse contract, a new
ProvidedService::MediaGenerator extension service, a runtime media generation
service backing the canonical media_generate_image tool with a deterministic
offline fallback, new roder-ext-openai-images (gpt-image-2 plus legacy ids)
and roder-ext-google-images (Nano Banana 2/Pro/base) provider crates,
[media.image_generation] config, media/image/providers/list and
media/image/generate app-server methods, roder media CLI commands, palette
entries, and regenerated schemas/SDK stubs. Live provider smokes stay opt-in
behind RODER_OPENAI_IMAGE_LIVE / RODER_GEMINI_IMAGE_LIVE.

One-command Roder package install (roder install npm:/git:/path)

Roder packages bundle process extensions, skills, slash commands, and themes
behind a root roder.toml manifest. Install from npm, git (shorthand, SSH,
raw URLs, pinned refs), or local paths; manage with roder packages list|resources|enable|disable|approve|filter|sync|init, roder remove,
roder update, and ephemeral -e loading. Resources surface through the
existing skills/commands/theme registries; the process-extension protocol
gains manifest-declared tool providers served over tools/call. New
app-server packages/* methods, a /packages builtin, and a Packages
palette section round out the surfaces. npm lifecycle scripts stay disabled
unless --allow-scripts is passed, and package process extensions never
launch before explicit approval.

Fixes

  • Add a stdio Agent Client Protocol v1 adapter backed by the Roder app-server runtime.

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

roder-web-search v0.1.1

15 Jun 22:26
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Fixes

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

Ensure Cargo crates inherit the workspace README, document npm and PyPI publishing steps in package READMEs, and add a registry README verifier for future publishes.

roder-usage-analytics v0.1.1

15 Jun 22:26
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Fixes

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

Ensure Cargo crates inherit the workspace README, document npm and PyPI publishing steps in package READMEs, and add a registry README verifier for future publishes.

roder-tui v0.1.1

15 Jun 22:26
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Features

One-command Roder package install (roder install npm:/git:/path)

Roder packages bundle process extensions, skills, slash commands, and themes
behind a root roder.toml manifest. Install from npm, git (shorthand, SSH,
raw URLs, pinned refs), or local paths; manage with roder packages list|resources|enable|disable|approve|filter|sync|init, roder remove,
roder update, and ephemeral -e loading. Resources surface through the
existing skills/commands/theme registries; the process-extension protocol
gains manifest-declared tool providers served over tools/call. New
app-server packages/* methods, a /packages builtin, and a Packages
palette section round out the surfaces. npm lifecycle scripts stay disabled
unless --allow-scripts is passed, and package process extensions never
launch before explicit approval.

Roadmap orchestration dashboard and multi-worker fan-out

Redesign the roadmap TUI workspace as an orchestration dashboard with progress
header, status strip, tree-style worker rows, and windowed scrolling. Add
orchestrator prompt rules in roder-roadmap and fan-out controls in the TUI:
S spawns up to eight workers across ready tasks and s spawns one for the
focused task.

Fixes

  • Put Models first in the Ctrl+P menu

First-party image generation providers (OpenAI GPT Image and Google Gemini Nano Banana)

Provider-neutral image generation through the core media API: an image-capable
MediaGenerationRequest/multi-output MediaGenerationResponse contract, a new
ProvidedService::MediaGenerator extension service, a runtime media generation
service backing the canonical media_generate_image tool with a deterministic
offline fallback, new roder-ext-openai-images (gpt-image-2 plus legacy ids)
and roder-ext-google-images (Nano Banana 2/Pro/base) provider crates,
[media.image_generation] config, media/image/providers/list and
media/image/generate app-server methods, roder media CLI commands, palette
entries, and regenerated schemas/SDK stubs. Live provider smokes stay opt-in
behind RODER_OPENAI_IMAGE_LIVE / RODER_GEMINI_IMAGE_LIVE.

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

Ensure Cargo crates inherit the workspace README, document npm and PyPI publishing steps in package READMEs, and add a registry README verifier for future publishes.

roder-tools v0.1.1

15 Jun 22:26
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Fixes

First-party image generation providers (OpenAI GPT Image and Google Gemini Nano Banana)

Provider-neutral image generation through the core media API: an image-capable
MediaGenerationRequest/multi-output MediaGenerationResponse contract, a new
ProvidedService::MediaGenerator extension service, a runtime media generation
service backing the canonical media_generate_image tool with a deterministic
offline fallback, new roder-ext-openai-images (gpt-image-2 plus legacy ids)
and roder-ext-google-images (Nano Banana 2/Pro/base) provider crates,
[media.image_generation] config, media/image/providers/list and
media/image/generate app-server methods, roder media CLI commands, palette
entries, and regenerated schemas/SDK stubs. Live provider smokes stay opt-in
behind RODER_OPENAI_IMAGE_LIVE / RODER_GEMINI_IMAGE_LIVE.

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

Ensure Cargo crates inherit the workspace README, document npm and PyPI publishing steps in package READMEs, and add a registry README verifier for future publishes.

Make grep and glob tools reliable for agents

Transcript analysis showed 44% of grep calls and 46% of glob calls returned empty results, mostly from the tool contract fighting model conventions. This change:

  • treats grep queries as regex by default (models habitually send a|b patterns without setting regex: true, which previously matched nothing as a literal), with a clear error and literal-mode hint for invalid patterns
  • replaces empty zero-match output with an explanation of what was searched (mode, case, scope, engine, file counts) plus remedial hints
  • backs glob with globset, adding {a,b}, [..] and proper ** support, and resolves absolute or ~ patterns inside the workspace instead of silently matching nothing; patterns outside the workspace now error clearly
  • searches explicitly scoped ignored directories (node_modules, dist, gitignored paths) by relaxing ancestor ignore rules when the caller names such a path directly
  • passes the canonicalized search path to the engine so ~, symlink, and case differences no longer silently drop every indexed match
  • invalidates the cached search index after shell and exec commands so files they create are found by the next grep

roder-thread-store v0.1.1

15 Jun 22:26
764d7d3

Choose a tag to compare

0.1.1 (2026-06-15)

Fixes

Package-specific registry READMEs

Add package-specific README files for every Cargo crate, ensure npm and PyPI package READMEs link to roder.sh, and tighten the registry README verifier to require package-local documentation.

Registry README metadata and publish checklists

Ensure Cargo crates inherit the workspace README, document npm and PyPI publishing steps in package READMEs, and add a registry README verifier for future publishes.