mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 21:19:18 +00:00
e9fa51d46e
* feat: agent-voice reference skillpack (Mars + Venus) + copy-into-host-repo install paradigm Ships a new skillpack paradigm: gbrain holds the REFERENCE content; `gbrain integrations install agent-voice --target <repo>` COPIES it into the operator's host agent repo where it becomes user-owned and mutable. Future refresh is diff-and-propose against per-file SHA-256 hashes from .gbrain-source.json, not blind overwrite. What ships: - recipes/agent-voice.md entrypoint + recipes/agent-voice/ bundle - Two voice personas (Mars dual-mode SOLO/DEMO, Venus executive assistant) with PII / private-agent-name / hardcoded-path scrubbed out - WebRTC-first browser client (call.html) with ?test=1 gated instrumentation and Web Audio API tee -> MediaRecorder capture for E2E roundtrip testing - Read-only tool router (D14-A allow-list: search, query, get_page, list_pages, find_experts, get_recent_salience, get_recent_transcripts, read_article). Write ops permanently denylisted; opt-in via local override - Persona-aware prompt builder with identity-first composition + Unicode sanitization for OpenAI Realtime API safety - Upstream-error classifier (HTTP 429/500/503 -> soft-fail, plumbing -> hard) - Three SKILL.md skills (voice-persona-mars, voice-persona-venus, voice-post-call) with routing-eval.jsonl fixtures - 99 host-side tests (vitest-compatible, runs in bun) covering registry, prompt-shape privacy guards, tool allow-list, upstream classifier - install/manifest.json + refresh-algorithm.md + post-install-hint.md Privacy infrastructure: - scripts/check-no-pii-in-agent-voice.sh wired into bun run verify Shape regex (phone/email/SSN/JWT/bearer/credit-card) + path patterns + $AGENT_VOICE_PII_BLOCKLIST env-driven name blocklist - scripts/import-from-upstream.sh + scripts/upstream-scrub-table.txt Deterministic refresh from upstream voice-agent source. Placeholder- driven (envsubst-expanded at run time) so no private names land in checked-in files - recipes/agent-voice/code/lib/personas/private-name-blocklist.json Single source of truth for the regex contract (shape categories + path patterns + env-var contract for operator-specific names) src/ surface: - src/commands/integrations.ts gains `install <recipe-id>` subcommand with install_kind: 'local-managed' | 'copy-into-host-repo' discriminator. Path-traversal hardening (rejects '..', absolute paths, symlink escapes). Refuses target == gbrain itself, missing .git, existing files (without --overwrite). Writes .gbrain-source.json with per-file SHA-256. Appends resolver rows to host repo's RESOLVER.md or AGENTS.md. - test/integrations-install.test.ts: 11 cases (happy path, manifest shape, no upstream_repo field per D11-A, resolver appending, file modes, refusal cases, dry-run) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.36.0.0) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(privacy): scrub literal private agent names from prompt-shape tests + guard script The prompt-shape tests carried regex patterns naming the literal banned terms (Garry/Steph/Garrison/Solomon/Herbert/Wintermute) inline. CLAUDE.md's "never use Wintermute in any public artifact" applies to test source files too. Master's check-privacy.sh correctly caught this. Replaced with env-driven check that reads AGENT_VOICE_PII_BLOCKLIST (the single source of truth from private-name-blocklist.json). Same enforcement guarantee via the env var, zero literal names in shipped source. Also scrubbed the literal /data/.openclaw/ from the guard script's comment and the literal 'tell_wintermute' from the venus write-tools test. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: ship all v0.36.0.0 deferred items in this PR (E2E + evals + pipeline + refresh + multilingual + twilio deprecation) Closes the "deferred to follow-up" section of the v0.36.0.0 CHANGELOG. E2E tests + harness (env-gated): - tests/e2e/voice-roundtrip.test.mjs — spawns server, drives puppeteer + fake-audio, three-tier assertions (CONNECTION hard, NON-SILENT hard, SEMANTIC soft via Whisper + LLM judge). Upstream errors (429/500/503, WS 1011/1013) soft-fail via lib/upstream-classifier.mjs. - tests/e2e/voice-full-flow.test.mjs — wraps openclaw doing the install, then runs the roundtrip. Friction-discovery flavor, NOT a ship gate. - tests/e2e/lib/browser-audio.mjs — puppeteer + fake-audio harness; reads window._gbrainTest namespace; PCM RMS-variance helper. - tests/e2e/lib/whisper-judge.mjs — Whisper transcription + LLM-judge for SEMANTIC tier. - tests/e2e/audio-fixtures/utterance-{add,joke,brain-query}.wav — 16kHz mono WAV via `say` + ffmpeg, committed for reproducibility. - test/fixtures/claw-test-scenarios/voice-agent-install/{BRIEF.md, scenario.json, expected.json} — labeled BENCHMARK_FRICTION, blocks_ship=false. LLM-judge persona evals + synthetic canonical baselines: - tests/evals/judge.mjs — gateway-routed 3-model (Claude + GPT + Gemini) harness with 4-strategy JSON repair + 2/3-quorum aggregation (per the v0.27.x cross-modal pattern). Pass criterion: every axis mean ≥7 AND no model <5. - tests/evals/fixtures/{mars-solo,mars-demo,venus,persona-routing,mars-multilingual}.jsonl — 5 fixture sets covering all axes. - tests/evals/{mars-eval,venus-eval,mars-multilingual-eval,persona-routing-eval}.mjs — per-axis drivers. - tests/evals/baseline-runs/canonical/*.json — agent-authored synthetic exemplars (PII-impossible by construction; demonstrate expected pass shape; never overwrite with live model output). - tests/evals/baseline-runs/.gitignore — live receipts excluded. DIY pipeline (Option B): - code/pipeline.mjs — streaming STT (Deepgram nova-2) + LLM (Claude Sonnet 4.6 streaming SSE with sentence-boundary TTS dispatch) + TTS (Cartesia primary, OpenAI TTS fallback). 20-turn history cap, exponential-backoff reconnects, 25s keepalives, VAD presets (quiet/normal/noisy/very_noisy), barge-in via STT speechStart → LLM interrupt. Modular adapters for swapping providers. --refresh mode (D3-A diff-and-propose): - src/commands/integrations.ts: refreshRecipeIntoHostRepo() + classifyForRefresh() implementing the five states from refresh-algorithm.md (unchanged-identical, unchanged-stale, locally-modified, source-deleted, host-deleted, new-in-manifest). Transaction journal at .gbrain-source.refresh.log. Default policy: preserve operator's local edits (keep-mine); --auto take-theirs to overwrite; --dry-run for preview. - test/integrations-install.test.ts: 7 new test cases pinning each classification state + default-preserve behavior + take-theirs overwrite + transaction journal + refusal on uninstalled target. Mars multilingual restore: - code/lib/personas/mars.mjs: explicit cross-lingual rule (Mandarin, Spanish, French, Japanese, Korean default to English but follow the speaker). Voice (Orus) supports the languages natively. - tests/unit/mars-prompt-shape.test.mjs: assertion flipped from "MUST NOT claim multilingual" to "declares cross-lingual capability with English bias." - tests/evals/fixtures/mars-multilingual.jsonl: 5 fixtures across Mandarin/Spanish/Japanese/French + explicit switch-back, pinned by mars-multilingual-eval.mjs. Twilio recipe deprecation: - recipes/twilio-voice-brain.md: deprecation banner pointing at agent-voice.md. Frontmatter version bumped to 0.8.2. Will be removed in v0.37. Verify: bun run verify clean, 6736+ unit tests pass, 18/18 install+refresh tests pass, 96/98 host-side persona/tool/classifier tests pass (2 skipped env-gated). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: update CHANGELOG — all v0.36.0.0 deferred items now shipped in this PR Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rebump version v0.36.0.0 → v0.37.0.0 Captures the wave-1 + wave-2 scope at the v0.37 slot. The bump reflects the size of what this PR ships: copy-into-host-repo install paradigm (new install_kind discriminator + new install/refresh subcommand) + Mars/Venus voice agent reference + 5,500+ LOC of vendored scrubbed code + 4 LLM-judge eval suites + 2 env-gated E2E test suites + DIY Option B pipeline + 18-case install subcommand test coverage. A minor bump felt too small. Side fix: privacy guard caught two stale literal "wintermute" and "/data/.openclaw/" references in wave-2 files (voice-full-flow.test.mjs comment, expected.json blocklist payload). Both replaced with env-driven references to $AGENT_VOICE_PII_BLOCKLIST matching the D15-A pattern from the original review. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rebump v0.37.0.0 → v0.40.0.0 Jumps past the v0.37/v0.38/v0.39 slots master might claim in subsequent PRs. The wave's scope (copy-into-host-repo skillpack paradigm + agent-voice + install/refresh + LLM-judge evals + DIY pipeline + Mars multilingual) justifies a larger version arithmetic step. Files bumped: - VERSION 0.37.0.0 → 0.40.0.0 - package.json 0.37.0.0 → 0.40.0.0 - CHANGELOG.md header + "To take advantage of v0.40.0.0" block - recipes/twilio-voice-brain.md deprecation banner (now "removed in v0.41") - recipes/agent-voice/tests/evals/mars-multilingual-eval.mjs comment Left alone: master's pre-existing "v0.37+" roadmap labels in src/core/calibration/*, src/core/cycle/*, DESIGN.md, CLAUDE.md, etc. Those are master's author-intent references to "the next planned release" relative to master's frame at the time — rewriting them just to keep numbering consistent would overreach. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
57 lines
3.0 KiB
Plaintext
57 lines
3.0 KiB
Plaintext
# Substitution table for scripts/import-from-upstream.sh.
|
|
#
|
|
# Format: one substitution per line, tab-separated:
|
|
# <from-regex>\t<to-literal>\t<comment>
|
|
#
|
|
# Lines starting with '#' are comments. Blank lines are ignored.
|
|
#
|
|
# CONVENTION: the FROM column may reference shell-expanded environment variables
|
|
# (e.g. ${PRIVATE_AGENT_NAME}, ${OPERATOR_FIRST_NAME}). The import script runs
|
|
# `envsubst` on the table before applying sed so the literal private values
|
|
# NEVER appear in this checked-in file. Set those env vars in $AGENT_VOICE_SUBSTITUTIONS
|
|
# (pipe-separated key=value pairs) when invoking the script:
|
|
#
|
|
# AGENT_VOICE_SUBSTITUTIONS="PRIVATE_AGENT_NAME=...|OPERATOR_FIRST_NAME=..." \
|
|
# scripts/import-from-upstream.sh --from $UPSTREAM_VOICE_REPO --to recipes/agent-voice/code/
|
|
#
|
|
# COMMENT discipline: comments describe the SHAPE of what's being scrubbed in
|
|
# functional terms ("private agent codename, capitalized form") without naming
|
|
# the actual value. Future grep against this file should reveal mechanics, not
|
|
# private identifiers.
|
|
|
|
# === Hardcoded private filesystem paths ===
|
|
/data/\.openclaw/workspace/ $BRAIN_ROOT/ # private hardcoded brain path, replace with operator env var
|
|
/data/\.openclaw/ $AGENT_HOME/ # private hardcoded agent root, replace with operator env var
|
|
|
|
# === Private name substitutions (env-driven) ===
|
|
# These rows depend on $AGENT_VOICE_SUBSTITUTIONS values; the import script
|
|
# expands them via envsubst before applying. Each row references a placeholder
|
|
# variable; the variable's value is the literal name to find. Two casings each:
|
|
# lowercase for slugs/paths, capitalized for prose.
|
|
\b${PRIVATE_AGENT_NAME_LC}\b the daemon # private upstream agent codename, lowercase
|
|
\b${PRIVATE_AGENT_NAME_TC}\b The daemon # private upstream agent codename, capitalized
|
|
\b${OPERATOR_FIRST_NAME}\b you # operator addressee
|
|
\b${OPERATOR_FIRST_NAME_LC}\b you # operator addressee, lowercase form
|
|
\b${FAMILY_MEMBER_1}\b [family-member] # family member name 1
|
|
\b${FAMILY_MEMBER_2}\b [family-member] # family member name 2
|
|
\b${FAMILY_MEMBER_3}\b [family-member] # family member name 3
|
|
\b${FAMILY_MEMBER_4}\b [family-member] # family member name 4
|
|
\b${FAMILY_MEMBER_5}\b [family-member] # family member name 5
|
|
\b${THERAPIST_1}\b [therapist] # therapist name 1
|
|
\b${THERAPIST_2}\b [therapist] # therapist name 2
|
|
|
|
# === File renames (handled separately by the import script's rename pass) ===
|
|
# These are NOT sed substitutions; the import script reads this section and
|
|
# performs file-level mv. The format is: __RENAME__\t<from-path>\t<to-path>
|
|
__RENAME__ lib/twilio-venus-bridge.mjs lib/twilio-bridge.mjs
|
|
__RENAME__ lib/venus-tools.mjs lib/voice-tools.mjs
|
|
__RENAME__ venus.html public/call.html
|
|
__RENAME__ web-client.html public/call.html
|
|
__RENAME__ directory.html public/directory.html
|
|
__RENAME__ rnnoise-processor.js public/rnnoise-processor.js
|
|
__RENAME__ rnnoise-sync.js public/rnnoise-sync.js
|
|
|
|
# === package.json metadata ===
|
|
"name":[ ]*"[^"]*voice[^"]*" "name": "agent-voice" # strip upstream package name
|
|
"private":[ ]*true "private": false # allow downstream installs from copy
|