docs(02-02): complete tier 1 medium/low-confidence providers plan

This commit is contained in:
salvacybersec
2026-04-05 14:12:49 +03:00
parent d74200b5ef
commit a8c0a6db62
4 changed files with 118 additions and 19 deletions

View File

@@ -19,8 +19,8 @@ Requirements for initial release. Each maps to roadmap phases.
### Providers
- [ ] **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)
- [ ] **PROV-02**: 14 Tier 2 Inference Platform provider definitions (Together, Fireworks, Groq, Replicate, Anyscale, DeepInfra, Lepton, Modal, Baseten, Cerebrium, NovitaAI, Sambanova, OctoAI, Friendli)
- [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)
- [ ] **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)

View File

@@ -64,10 +64,10 @@ Plans:
**Plans**: 5 plans
Plans:
- [ ] 02-01-PLAN.md — Tier 1 high-confidence prefixed providers (OpenAI upgrade, Anthropic upgrade, Google AI, Vertex AI, AWS Bedrock, xAI)
- [ ] 02-02-PLAN.md — Tier 1 keyword-anchored providers (Azure OpenAI, Meta AI, Cohere, Mistral, Inflection, AI21)
- [ ] 02-03-PLAN.md — Tier 2 inference platforms batch 1 (Groq, Replicate, Anyscale, Together, Fireworks, Baseten, DeepInfra)
- [ ] 02-04-PLAN.md — Tier 2 inference platforms batch 2 (Lepton, Modal, Cerebrium, Novita, SambaNova, OctoAI, Friendli)
- [x] 02-01-PLAN.md — Tier 1 high-confidence prefixed providers (OpenAI upgrade, Anthropic upgrade, Google AI, Vertex AI, AWS Bedrock, xAI)
- [x] 02-02-PLAN.md — Tier 1 keyword-anchored providers (Azure OpenAI, Meta AI, Cohere, Mistral, Inflection, AI21)
- [x] 02-03-PLAN.md — Tier 2 inference platforms batch 1 (Groq, Replicate, Anyscale, Together, Fireworks, Baseten, DeepInfra)
- [x] 02-04-PLAN.md — Tier 2 inference platforms batch 2 (Lepton, Modal, Cerebrium, Novita, SambaNova, OctoAI, Friendli)
- [ ] 02-05-PLAN.md — Registry guardrail test: assert 12 Tier 1 + 14 Tier 2 + regex compilation
### Phase 3: Tier 3-9 Providers

View File

@@ -2,15 +2,15 @@
gsd_state_version: 1.0
milestone: v1.0
milestone_name: milestone
status: planning
stopped_at: Completed 01-foundation 01-05-PLAN.md
last_updated: "2026-04-05T09:32:56.054Z"
last_activity: 2026-04-05
status: executing
stopped_at: Completed 02-tier-1-2-providers 02-03-PLAN.md
last_updated: "2026-04-05T11:12:42.470Z"
last_activity: 2026-04-05 -- Phase 02 execution started
progress:
total_phases: 18
completed_phases: 1
total_plans: 5
completed_plans: 5
total_plans: 10
completed_plans: 9
percent: 20
---
@@ -21,14 +21,14 @@ progress:
See: .planning/PROJECT.md (updated 2026-04-04)
**Core value:** Detect leaked LLM API keys across more providers and more internet sources than any other tool, with active verification to confirm keys are real and alive.
**Current focus:** Phase 1Foundation
**Current focus:** Phase 02tier-1-2-providers
## Current Position
Phase: 2 of 18 (tier 1 2 providers)
Plan: Not started
Status: Ready to plan
Last activity: 2026-04-05
Phase: 02 (tier-1-2-providers) — EXECUTING
Plan: 1 of 5
Status: Executing Phase 02
Last activity: 2026-04-05 -- Phase 02 execution started
Progress: [██░░░░░░░░] 20%
@@ -55,6 +55,8 @@ Progress: [██░░░░░░░░] 20%
| Phase 01-foundation P02 | 9 | 2 tasks | 11 files |
| Phase 01-foundation P04 | 5min | 2 tasks | 12 files |
| Phase 01-foundation P05 | 4min | 2 tasks | 8 files |
| Phase 02-tier-1-2-providers P02 | 1m | 2 tasks | 12 files |
| Phase 02-tier-1-2-providers P03 | 3min | 2 tasks | 14 files |
## Accumulated Context
@@ -86,6 +88,6 @@ None yet.
## Session Continuity
Last session: 2026-04-05T09:28:33.649Z
Stopped at: Completed 01-foundation 01-05-PLAN.md
Last session: 2026-04-05T11:12:42.467Z
Stopped at: Completed 02-tier-1-2-providers 02-03-PLAN.md
Resume file: None

View File

@@ -0,0 +1,97 @@
---
phase: 02-tier-1-2-providers
plan: 02
subsystem: providers
tags: [providers, yaml, tier-1, keyword-anchoring]
requires: [pkg/providers/schema.go, pkg/providers/loader.go, pkg/providers/registry.go]
provides:
- Azure OpenAI 32-hex pattern provider definition
- Meta AI (Llama API) LLM|-prefixed token provider definition
- Cohere 40-char token provider definition
- Mistral AI 32-char keyword-anchored provider definition
- Inflection AI (Pi) opaque-token provider definition
- AI21 Labs 32+-char keyword-anchored provider definition
affects: [providers/, pkg/providers/definitions/]
tech_stack:
added: []
patterns: [yaml-provider-definitions, dual-location-embed, keyword-ac-prefilter]
key_files:
created:
- providers/azure-openai.yaml
- providers/meta-ai.yaml
- providers/cohere.yaml
- providers/mistral.yaml
- providers/inflection.yaml
- providers/ai21.yaml
- pkg/providers/definitions/azure-openai.yaml
- pkg/providers/definitions/meta-ai.yaml
- pkg/providers/definitions/cohere.yaml
- pkg/providers/definitions/mistral.yaml
- pkg/providers/definitions/inflection.yaml
- pkg/providers/definitions/ai21.yaml
modified: []
decisions:
- Low-confidence regex (generic character classes) compensated by strong keyword lists for Aho-Corasick pre-filtering
- Azure OpenAI and Inflection use empty verify blocks (no stable public endpoint / requires deployment URL)
- Meta AI pattern anchors on LLM| literal prefix to reduce false positives
metrics:
duration: 1m
tasks: 2
files: 12
completed: "2026-04-05T11:11:55Z"
requirements: [PROV-01]
---
# Phase 2 Plan 2: Tier 1 Medium/Low-Confidence Providers Summary
Added 6 Tier 1 LLM provider YAML definitions (Azure OpenAI, Meta AI, Cohere, Mistral, Inflection, AI21) with strong keyword lists anchoring generic opaque-token regex patterns, completing Tier 1 at 12/12.
## What Was Built
Created 12 YAML files (6 providers x dual location) covering the remaining Tier 1 providers that lack distinctive high-confidence prefix patterns. These providers rely on Aho-Corasick keyword pre-filtering (azure, cohere, mistral, jamba, PI_API_KEY, etc.) to reduce false positives since their key formats are opaque hex/alphanumeric tokens.
- **Azure OpenAI**: 32-hex pattern, no verify endpoint (requires per-deployment URL)
- **Meta AI**: `LLM|` literal prefix anchor, api.llama.com verify endpoint
- **Cohere**: 40-char alphanumeric, api.cohere.ai verify endpoint
- **Mistral AI**: 32-char alphanumeric, api.mistral.ai verify endpoint
- **Inflection AI**: 40+-char token, no public verify endpoint
- **AI21 Labs**: 32+-char alphanumeric, api.ai21.com/studio verify endpoint
All providers dual-located for Go embed.FS (pkg/providers/definitions/) and user visibility (providers/). Registry loader test passes with all 9 providers (3 existing + 6 new).
## Tasks Completed
| Task | Name | Commit | Files |
|------|-----------------------------------------|---------|-------|
| 1 | Azure OpenAI, Meta AI, Cohere YAMLs | bca8422 | 6 |
| 2 | Mistral, Inflection, AI21 YAMLs | adad602 | 6 |
## Verification
- `go test ./pkg/providers/... -count=1` -- PASS (0.037s)
- `diff` on all 6 provider pairs -- no drift between providers/ and pkg/providers/definitions/
- `grep -l 'tier: 1' providers/*.yaml | wc -l` -- 12 (matches Tier 1 complete criterion)
## Deviations from Plan
None - plan executed exactly as written.
## Decisions Made
- **Empty verify blocks for Azure OpenAI and Inflection**: Azure OpenAI requires per-deployment URL (`https://{resource}.openai.azure.com/...`) which cannot be hardcoded; Inflection lacks a stable public verify endpoint. Both use empty `url: ""` and empty status arrays to signal "verification unsupported" for Phase 5.
- **Low confidence on all 6**: Generic character-class regex patterns would cause high false-positive rates without keyword anchoring, so confidence is marked `low` and the AC automaton carries the detection weight.
## Key Links
- Provider `keywords[]` feeds `NewRegistry()` which builds the Aho-Corasick DFA across all providers
- Aho-Corasick pre-filter gates per-pattern regex evaluation (established in Phase 01)
## Self-Check: PASSED
All 12 files verified present:
- providers/{azure-openai,meta-ai,cohere,mistral,inflection,ai21}.yaml -- FOUND
- pkg/providers/definitions/{azure-openai,meta-ai,cohere,mistral,inflection,ai21}.yaml -- FOUND
Commits verified:
- bca8422 -- FOUND
- adad602 -- FOUND