diff --git a/.planning/REQUIREMENTS.md b/.planning/REQUIREMENTS.md index 33e6c82..a382124 100644 --- a/.planning/REQUIREMENTS.md +++ b/.planning/REQUIREMENTS.md @@ -21,13 +21,13 @@ Requirements for initial release. Each maps to roadmap phases. - [x] **PROV-01**: 12 Tier 1 Frontier provider YAML definitions (OpenAI, Anthropic, Google AI, Vertex, AWS Bedrock, Azure OpenAI, Meta AI, xAI, Cohere, Mistral, Inflection, AI21) - [x] **PROV-02**: 14 Tier 2 Inference Platform provider definitions (Together, Fireworks, Groq, Replicate, Anyscale, DeepInfra, Lepton, Modal, Baseten, Cerebrium, NovitaAI, Sambanova, OctoAI, Friendli) -- [ ] **PROV-03**: 12 Tier 3 Specialized provider definitions (Perplexity, You.com, Voyage, Jina, Unstructured, AssemblyAI, Deepgram, ElevenLabs, Stability, Runway, Midjourney, HuggingFace) +- [x] **PROV-03**: 12 Tier 3 Specialized provider definitions (Perplexity, You.com, Voyage, Jina, Unstructured, AssemblyAI, Deepgram, ElevenLabs, Stability, Runway, Midjourney, HuggingFace) - [ ] **PROV-04**: 16 Tier 4 Chinese/Regional provider definitions (DeepSeek, Baichuan, Zhipu, Moonshot, Yi, Qwen, Baidu, ByteDance, SenseTime, iFlytek, MiniMax, Stepfun, 360 AI, Kuaishou, Tencent, SiliconFlow) - [ ] **PROV-05**: 11 Tier 5 Infrastructure/Gateway provider definitions (Cloudflare AI, Vercel AI, LiteLLM, Portkey, Helicone, OpenRouter, Martian, Kong, BricksAI, Aether, Not Diamond) - [ ] **PROV-06**: 15 Tier 6 Emerging/Niche provider definitions (Reka, Aleph Alpha, Writer, Jasper, Typeface, Comet, W&B, LangSmith, Pinecone, Weaviate, Qdrant, Chroma, Milvus, Neon, Lamini) - [x] **PROV-07**: 10 Tier 7 Code/Dev Tools provider definitions (GitHub Copilot, Cursor, Tabnine, Codeium, Sourcegraph, CodeWhisperer, Replit AI, Codestral, watsonx, Oracle AI) - [ ] **PROV-08**: 10 Tier 8 Self-Hosted provider definitions (Ollama, vLLM, LocalAI, LM Studio, llama.cpp, GPT4All, text-gen-webui, TensorRT-LLM, Triton, Jan AI) -- [ ] **PROV-09**: 8 Tier 9 Enterprise provider definitions (Salesforce Einstein, ServiceNow, SAP AI Core, Palantir, Databricks, Snowflake, Oracle GenAI, HPE GreenLake) +- [x] **PROV-09**: 8 Tier 9 Enterprise provider definitions (Salesforce Einstein, ServiceNow, SAP AI Core, Palantir, Databricks, Snowflake, Oracle GenAI, HPE GreenLake) - [x] **PROV-10**: Provider YAML schema includes format_version and last_verified date for pattern health tracking ### Input Sources diff --git a/.planning/ROADMAP.md b/.planning/ROADMAP.md index d38aa64..f477732 100644 --- a/.planning/ROADMAP.md +++ b/.planning/ROADMAP.md @@ -83,11 +83,11 @@ Plans: Plans: - [ ] 03-01-PLAN.md — Tier 4 Chinese/regional providers (DeepSeek, Zhipu, Moonshot, Qwen, Baidu, ByteDance, 01.AI, MiniMax, Baichuan, StepFun, SenseTime, iFlytek, Tencent, SiliconFlow, 360 AI, Kuaishou) -- [ ] 03-02-PLAN.md — Tier 3 Specialized (Perplexity, You.com, Voyage, Jina, Unstructured, AssemblyAI, Deepgram, ElevenLabs, Stability, Runway, Midjourney) +- [x] 03-02-PLAN.md — Tier 3 Specialized (Perplexity, You.com, Voyage, Jina, Unstructured, AssemblyAI, Deepgram, ElevenLabs, Stability, Runway, Midjourney) - [x] 03-03-PLAN.md — Tier 5 Infrastructure/Gateway (OpenRouter, LiteLLM, Cloudflare AI, Vercel AI, Portkey, Helicone, Martian, Kong, BricksAI, Aether, Not Diamond) - [x] 03-04-PLAN.md — Tier 7 Code/Dev Tools (GitHub Copilot, Cursor, Tabnine, Codeium, Sourcegraph, CodeWhisperer, Replit AI, Codestral, watsonx, Oracle AI) - [ ] 03-05-PLAN.md — Tier 8 Self-Hosted runtimes (Ollama, vLLM, LocalAI, LM Studio, llama.cpp, GPT4All, text-gen-webui, TensorRT-LLM, Triton, Jan) -- [ ] 03-06-PLAN.md — Tier 9 Enterprise (Salesforce Einstein, ServiceNow, SAP AI Core, Palantir, Databricks, Snowflake, Oracle GenAI, HPE GreenLake) +- [x] 03-06-PLAN.md — Tier 9 Enterprise (Salesforce Einstein, ServiceNow, SAP AI Core, Palantir, Databricks, Snowflake, Oracle GenAI, HPE GreenLake) - [ ] 03-07-PLAN.md — Tier 6 Emerging/Niche (Reka, Aleph Alpha, Lamini, Writer, Jasper, Typeface, Comet, W&B, LangSmith, Pinecone, Weaviate, Qdrant, Chroma, Milvus, Neon) - [ ] 03-08-PLAN.md — Tier 3-9 guardrail test: lock 108 total providers, per-tier counts, and name sets diff --git a/.planning/STATE.md b/.planning/STATE.md index 282dd83..b7c75dc 100644 --- a/.planning/STATE.md +++ b/.planning/STATE.md @@ -3,14 +3,14 @@ gsd_state_version: 1.0 milestone: v1.0 milestone_name: milestone status: executing -stopped_at: Completed 02-tier-1-2-providers 02-05-PLAN.md -last_updated: "2026-04-05T11:42:39.202Z" +stopped_at: Completed 03-06-PLAN.md +last_updated: "2026-04-05T11:42:57.673Z" last_activity: 2026-04-05 progress: total_phases: 18 completed_phases: 2 total_plans: 18 - completed_plans: 12 + completed_plans: 14 percent: 20 --- @@ -26,7 +26,7 @@ See: .planning/PROJECT.md (updated 2026-04-04) ## Current Position Phase: 03 (tier-3-9-providers) — EXECUTING -Plan: 2 of 8 +Plan: 4 of 8 Status: Ready to execute Last activity: 2026-04-05 @@ -61,6 +61,8 @@ Progress: [██░░░░░░░░] 20% | Phase 02-tier-1-2-providers P04 | 1min | 2 tasks tasks | 14 files files | | Phase 02-tier-1-2-providers P05 | 2min | 1 tasks | 1 files | | Phase 03-tier-3-9-providers P04 | 3m | 2 tasks | 20 files | +| Phase 03-tier-3-9-providers P02 | 70 | 2 tasks | 22 files | +| Phase 03-tier-3-9-providers P06 | 3m | 2 tasks | 16 files | ## Accumulated Context @@ -79,6 +81,7 @@ Recent decisions affecting current work: - [Phase 01-foundation]: Per-installation salt via settings table -- no hardcoded salt in production code - [Phase 01-foundation]: Exit code semantics: 0=clean, 1=keys-found, 2=error for CI/CD integration - [Phase 02-tier-1-2-providers]: AWS Bedrock verify URL left empty — SigV4 signing deferred to Phase 5 verification engine +- [Phase 03-tier-3-9-providers]: Keyword-only detection for providers without documented key prefixes (You.com, Unstructured, Runway, Midjourney) to avoid false positives. ### Pending Todos @@ -93,6 +96,6 @@ None yet. ## Session Continuity -Last session: 2026-04-05T11:16:08.292Z -Stopped at: Completed 02-tier-1-2-providers 02-05-PLAN.md +Last session: 2026-04-05T11:42:57.670Z +Stopped at: Completed 03-06-PLAN.md Resume file: None diff --git a/.planning/phases/03-tier-3-9-providers/03-02-SUMMARY.md b/.planning/phases/03-tier-3-9-providers/03-02-SUMMARY.md new file mode 100644 index 0000000..c590e88 --- /dev/null +++ b/.planning/phases/03-tier-3-9-providers/03-02-SUMMARY.md @@ -0,0 +1,106 @@ +--- +phase: 03-tier-3-9-providers +plan: 02 +subsystem: providers +tags: [providers, tier-3, specialized, voice, image, embeddings] +requires: [PROV-10-schema, embed-loader] +provides: [PROV-03] +affects: [pkg/providers/registry, engine/detector] +tech_stack_added: [] +patterns: [dual-location-yaml, keyword-only-fallback, tight-prefix-regex] +files_created: + - providers/perplexity.yaml + - providers/you.yaml + - providers/voyage.yaml + - providers/jina.yaml + - providers/unstructured.yaml + - providers/assemblyai.yaml + - providers/deepgram.yaml + - providers/elevenlabs.yaml + - providers/stability.yaml + - providers/runway.yaml + - providers/midjourney.yaml + - pkg/providers/definitions/perplexity.yaml + - pkg/providers/definitions/you.yaml + - pkg/providers/definitions/voyage.yaml + - pkg/providers/definitions/jina.yaml + - pkg/providers/definitions/unstructured.yaml + - pkg/providers/definitions/assemblyai.yaml + - pkg/providers/definitions/deepgram.yaml + - pkg/providers/definitions/elevenlabs.yaml + - pkg/providers/definitions/stability.yaml + - pkg/providers/definitions/runway.yaml + - pkg/providers/definitions/midjourney.yaml +files_modified: [] +decisions: + - "Providers without documented key prefixes (You.com, Unstructured, Runway, Midjourney) use keyword-only detection (no regex) to avoid Phase 2 false-positive regression." + - "Providers with documented prefixes (Perplexity pplx-, Jina jina_, Voyage pa-, Stability sk-) use tight regex with high/medium confidence." + - "ElevenLabs/Deepgram/AssemblyAI use hex alphanumeric patterns with low confidence + entropy_min 4.0 — keyword pre-filter guards against noise." + - "Midjourney has no official API; verify block uses empty URL as sentinel (no active verification possible)." +metrics: + duration_seconds: 70 + tasks_completed: 2 + files_changed: 22 + completed_at: "2026-04-05T11:42:06Z" +--- + +# Phase 3 Plan 02: Tier 3 Specialized Providers Summary + +11 specialized Tier 3 LLM/AI providers added (search, embeddings, voice, image/video) across dual-location YAML, bringing total Tier 3 count to 12 with pre-existing huggingface. + +## What Was Built + +### Task 1: Search + Embeddings (commit `7ad9588`) + +Added 6 providers covering search APIs and embedding/document-processing services: + +| Provider | Type | Detection | +|----------|------|-----------| +| Perplexity AI | Search LLM | `pplx-[A-Za-z0-9]{48,}` (high) | +| You.com | Search | keyword-only | +| Voyage AI | Embeddings | `pa-[A-Za-z0-9_\-]{40,}` (medium) | +| Jina AI | Embeddings | `jina_[A-Za-z0-9]{40,}` (high) | +| Unstructured.io | Doc processing | keyword-only | +| AssemblyAI | Voice (STT) | `[a-f0-9]{32}` (low) | + +### Task 2: Voice + Image/Video (commit `0ac12e5`) + +Added 5 providers covering speech, image, and video generation: + +| Provider | Type | Detection | +|----------|------|-----------| +| Deepgram | Voice (STT) | `[a-f0-9]{40}` (low) | +| ElevenLabs | Voice (TTS) | `[a-f0-9]{32}` (low), `XI_API_KEY` | +| Stability AI | Image | `sk-[A-Za-z0-9]{48}` (medium) | +| Runway | Video | keyword-only | +| Midjourney | Image | keyword-only (no official API) | + +All 11 provider YAMLs dual-located (`providers/` + `pkg/providers/definitions/`) to satisfy the embed loader contract. + +## Key Decisions + +- **Keyword-only where no documented format exists.** Per Phase 3 lessons-learned, providers without distinctive prefixes (You.com, Unstructured, Runway, Midjourney) rely solely on keyword pre-filtering to avoid false positives. +- **Tight regex for documented prefixes.** Perplexity (`pplx-`), Jina (`jina_`), Voyage (`pa-`), Stability (`sk-`) use prefix-anchored regex with high/medium confidence. +- **Low-confidence hex patterns backed by keyword pre-filter.** ElevenLabs, Deepgram, and AssemblyAI use hex-alphanumeric regex (32 or 40 chars) with `confidence: low` and `entropy_min: 4.0` — the Aho-Corasick keyword filter ensures these only fire on matched contexts. +- **Midjourney verify sentinel.** Midjourney has no first-party API; VerifySpec uses empty URL/status fields as a sentinel for "cannot actively verify." + +## Verification + +- `go test ./pkg/providers/... -count=1` → **PASS** +- `go test ./pkg/engine/... -count=1` → **PASS** +- `diff providers/.yaml pkg/providers/definitions/.yaml` for all 11 providers → identical +- `grep -l 'tier: 3' providers/*.yaml | wc -l` → **12** (PROV-03 satisfied) + +## Deviations from Plan + +None — plan executed exactly as written. + +## Requirements Satisfied + +- **PROV-03**: 12 Tier 3 Specialized providers (11 new + pre-existing huggingface) + +## Self-Check: PASSED + +- All 22 files present on disk. +- Commits `7ad9588` and `0ac12e5` exist on current branch. +- `go test ./pkg/providers/... ./pkg/engine/...` green after each task.