release: v0.4.0 — opt-in AI assistant + one-click remediation#9
Open
jboero wants to merge 1 commit into
Open
Conversation
Adds an opt-in, bring-your-own-model AI assistant and one-click remediation. AI assistant - "🤖 Ask a Crossplane expert" chat, promoted to the root of the tray menu. - "🤖 AI Help" on any unhealthy resource: diagnoses it and proposes a fix. - AI design wizard wired into the resource-authoring form. - Two providers: Claude via the official anthropic SDK with your own API key (optional `[ai]` extra / python3-anthropic), or ANY OpenAI-compatible endpoint (vLLM/Ollama/llama.cpp) for local/airgapped use — no key, nothing leaves your network. Streaming, reasoning-model support, configured-language replies, brevity + emoji. Safety - Cluster read access is opt-in and read-only by default; state is redacted (secrets/tokens/keys stripped) before anything is sent. - Separate, clearly-labelled cluster-modify opt-in. The model only proposes a kubectl command or manifest; a stop-sequence halts generation at the proposal (so it can't hallucinate the change already applied), up-tray flags anything destructive, runs it only after explicit confirmation, and feeds the real output back into the conversation. Remediation - One-click fixes for unhealthy managed resources and packages, surfaced on the health/status dialogs. Packaging / docs - Version bumped to 0.4.0 (pyproject, __init__, spec + changelog). - Suggests: python3-anthropic; `[ai]` optional-dependency in pyproject. - README AI-assistant section + COPR install; About dialog notes the assistant. - All new user-facing strings translated across 16 locales (i18n gate green). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
v0.4.0
Adds an opt-in, bring-your-own-model AI assistant and one-click remediation.
AI assistant
anthropicSDK with your own API key (optional[ai]extra /python3-anthropic), or any OpenAI-compatible endpoint (vLLM/Ollama/llama.cpp) for local/airgapped use — no key, nothing leaves your network. Streaming, reasoning-model support, configured-language replies, brevity + emoji.Safety
kubectlcommand or manifest; a stop-sequence halts generation at the proposal (so it can't hallucinate the change already applied), up-tray flags anything destructive, runs it only after explicit confirmation, and feeds the real output back into the conversation.Remediation
Packaging / docs
pyproject.toml,__init__.py, RPM spec + changelog).Suggests: python3-anthropic;[ai]optional dependency.Verification
python tools/i18n_check.py→ PASS (0 missing / 0 placeholder mismatch, 16 locales)python -m up_tray --self-test→ ALL CHECKS PASSED🤖 Generated with Claude Code