feat: v0.7.0 Ollama provider with local and cloud monitoring#20
Merged
Conversation
Add Ollama provider supporting local instance monitoring (model inventory, loaded models, VRAM/RAM usage) with multi-host support, and alpha-gated cloud usage tracking (session/weekly quotas behind enable_alpha_features). - providers/ollama.py: @register_provider with /api/tags + /api/ps polling, multi-host support, error isolation per host, cloud model detection, cloud API key auth and /api/account/usage probe (alpha, D-053) - config.py: enable_alpha_features flag, [providers.ollama] section, host/hosts mutual exclusivity validation, is_alpha_enabled() helper - 45 new tests (test_ollama.py, test_ollama_cloud.py, test_config.py) - 4 fixture files for mocked Ollama API responses - Research report: docs/research/ollama-v0.7.0-research.md - README: Ollama prerequisites, multi-host config examples - SPEC: v0.7.0 checklist updated Closes #7 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The table and monitor formatters only handled "percent" and "usd" units, showing utilisation (always 0.0) as "0%" for Ollama's count/mb windows. Now displays raw_value with appropriate suffix (e.g. "1", "5,086 MB") and skips the percentage bar for non-percentage units. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Owner
Author
|
Limited Ability to Fully test at this stage. Some test deferred to v0.7.1 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
providers/ollama.py) with@register_provider— polls/api/tags(model inventory) and/api/ps(loaded models, VRAM/RAM) per hosthostor[[providers.ollama.hosts]]array, with host-prefixed window names and error isolation per hostollama.com/api/account/usagewhenenable_alpha_features = trueandcloud_enabled = true; API key auth via credential chain; one-time stderr warning;alpha: truein extrasenable_alpha_featuresflag in[general],[providers.ollama]section with host validation,is_alpha_enabled()helpertest_ollama.py,test_ollama_cloud.py, andtest_config.py(481 total pass)docs/research/ollama-v0.7.0-research.mdCloses #7
Test plan
uv run pytest)ollama serve+uv run llm-monitor -p ollama --now)enable_alpha_features = trueValueError🤖 Generated with Claude Code