feat(phase2): 'claude' provider — measurement-grounded interpreter via local Claude Code CLI (no Gemini credits) - #153
Merged
Conversation
- Fix unittest slash-path form → dotted module form in apps/backend/AGENTS.md - Add UPDATE_PHASE1_GOLDEN re-baseline command to CLAUDE.md Tripwire #4 - Add first-time Playwright install line to CLAUDE.md frontend commands - Add record_artifact pointer to analysis_runtime.py entry in CLAUDE.md - Add --source/--output invocation to build_live12_catalogue.py entry - Reconcile Node version in apps/ui/AGENTS.md against package.json (no engines field) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
… Claude Code CLI ASA_PHASE2_PROVIDER=claude routes producer_summary interpretation to ClaudeCliProvider: runs the operator's local Claude Code CLI headless (--safe-mode, --tools "", --no-session-persistence), prompt via stdin, profile responseSchema converted from Gemini dialect and enforced via --json-schema. Text-only by design — grounds on the prompt's embedded Phase 1 JSON; audio is never sent; no GEMINI_API_KEY needed. Output flows through the identical parse/citation/catalogue/recommendations.v1 tail. Default-off; gemini stays the product default (mirrors the MOSS pattern). Live verification on a real track (no Gemini key): 26/26 cards cited, 0 invented citation paths, recommendations.v1 envelope 26 entries, full-surface coverage; 6 warn-and-keep catalogue annotations. Also adds audits/owner-assessment-2026-06-10.md (whole-project audit write-up). Tests: tests.test_phase2_provider 42/42; tests.test_server 224/224 (Gemini path behavior-preserved); full backend discover green. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…is unset The advisory review action has failed every PR since 2026-06-09 in ~25s because the repo secret resolves empty. Gate the steps on secret presence so a missing credential yields a passing job with skipped steps instead of a red check. Re-add the secret in Settings → Secrets → Actions to restore actual reviews. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…eal tracks Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The claude-code-action token exchange validates that the workflow file on a PR branch matches the default branch exactly; any divergence (or the file's absence on pre-workflow branches — the actual cause of the 2026-06-09+ failures) yields 401 'Workflow validation failed'. The skip guard added in f6d61e5 therefore could never help and itself tripped the validation; reverting to main's exact content lets the review run. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…clusive, no fallback/ensemble; Gemini stays default; claude is local-CLI-only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
slittycode
added a commit
that referenced
this pull request
Jun 10, 2026
Summarizes current state (PR #153 merged, Claude provider live-verified), lists required owner steps (Ableton renders, asa-ableton Gate β), and documents the Gemini→Claude provider context for the recommendation-proof campaign. Co-Authored-By: Claude Sonnet 4.6 <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.
Why
Gemini API credits ran out, blocking Phase 2 interpretation entirely. This adds a third
selectable provider (mirroring the MOSS pattern, default-off): `ASA_PHASE2_PROVIDER=claude`
runs the operator's local Claude Code CLI headless as a text-only interpreter — it
grounds on the prompt's embedded Phase 1 JSON and never receives the audio, needs no
`GEMINI_API_KEY`, and rides the operator's existing Claude Code login.
What
--output-format json --safe-mode --tools "" --no-session-persistence`, prompt via stdin,
profile `responseSchema` converted from Gemini dialect to JSON Schema and enforced via
`--json-schema`; prefers the CLI's validated `structured_output`, falls back to
fence-stripped text. Typed errors (`CLAUDE_CLI_UNAVAILABLE/FAILED/TIMEOUT/BAD_OUTPUT`);
non-zero exits surface the CLI's stdout error event. 600 s default timeout (a full
producer_summary prompt measures ~6 min on the CLI default model).
concerns behind `external_provider is None`.
incl. the real PHASE2_RESPONSE_SCHEMA, subprocess failure modes, and an integration test
proving the claude branch flows through the shared parse/citation/catalogue/
recommendations.v1 tail with no GEMINI_API_KEY set).
`audits/owner-assessment-2026-06-10.md` (whole-project audit write-up).
Live verification (real track, no Gemini key)
`VTSS – Can't Catch Me` end-to-end through the staged API: 26/26 device cards cited,
0 invented citation paths (Gemini's documented bar on this track: 22/22), 26-entry
`recommendations.v1` envelope, full-surface coverage, authoritative BPM/key echoed exactly;
6 warn-and-keep catalogue annotations (working as designed). The same output also produced
asa-ableton's first real Gate α receipt (11/11 fidelity, skip-rate 60.7%).
Verification
🤖 Generated with Claude Code