Conversation
Added a section for reporting issues in the README.
…opencode install Five additive features landing together. The provider abstraction is load-bearing for the rest. - providers/: Provider ABC and normalized error taxonomy in base.py; PiShockProvider extracted out of server.py; OpenShockProvider talks to api.openshock.app (or self-hosted via base_url) over httpx with the OpenShockToken header; MockProvider replaces dry_run's MagicMock-spec gymnastics. Config gains [provider] kind = "pishock" or "openshock" with sub-tables; legacy [auth] still loads as a pishock back-compat shim. New errors (DeviceOfflineError, DevicePausedError, ShockNotAllowedError, ProviderAuthError, ProviderError) are the seam server.py catches on. - reason: optional str on the rlaif tool, clipped to 200 chars, threaded through safety.authorize onto OpRecord. Audit-only, never gates the call. Surfaces in rlaif_log. - [tool] purpose preamble: operator-authored string prepended to the rlaif tool description. compose_rlaif_description keeps the spec frame byte-for-byte at the tail; test_server.py still locks the frame. - rlaif log --stats: histograms (intensity buckets, refusal reasons, hourly volume) plus counts and an intensity*duration_s energy proxy. Pure read of the existing jsonl, no MCP round-trip. - opencode auto-install: OpencodeJsonAdapter handles opencode's mcp.<name> schema with command-as-array. JSONC files redirect to rlaif snippet opencode. Tests: 219 (was 105). pyright strict clean, ruff clean, rlaif dry-run green. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CodeQL flagged init.py:write_text as cleartext storage of sensitive data (rule py/clear-text-storage-sensitive-data). The storage is intentional — rlaif is a single-user CLI, config.toml is chmod 0600 immediately after the write, and the pattern matches every MCP client we generate snippets for. Adding a 7-line block comment at the call site so the rationale is discoverable from the code, not just from the dismissed alert. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
a9lim
added a commit
that referenced
this pull request
Apr 30, 2026
Pulls the duplicated authorize -> fire -> commit|rollback shape out of handle_rlaif_negative and handle_rlaif_positive into a private _fire_channel helper. Each handler still owns its own typed-error dispatch table, so Provider and RewardProvider namespaces stay disjoint at the call site (CLAUDE.md hard rule #8). The watchdog no-refund contract (hard rule #6) is encoded as the single refund=False entry in the positive-channel table. Co-Authored-By: Claude Opus 4.7 (1M context) <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.
better hermes support