feat(03-02): add search and embeddings Tier 3 providers

- Perplexity (pplx- prefix, high confidence)
- You.com (keyword-only)
- Voyage AI (pa- prefix, medium confidence)
- Jina AI (jina_ prefix, high confidence)
- Unstructured.io (keyword-only)
- AssemblyAI (hex32, low confidence)

pkg/providers/definitions/assemblyai.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: assemblyai
+display_name: AssemblyAI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "assemblyai"
+  - "ASSEMBLYAI_API_KEY"
+  - "api.assemblyai.com"
+  - "assembly.ai"
+patterns:
+  - regex: '[a-f0-9]{32}'
+    entropy_min: 4.0
+    confidence: low
+verify:
+  method: GET
+  url: https://api.assemblyai.com/v2/transcript
+  headers:
+    authorization: "{KEY}"
+  valid_status: [200]
+  invalid_status: [401, 403]

pkg/providers/definitions/jina.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: jina
+display_name: Jina AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "jina"
+  - "JINA_API_KEY"
+  - "api.jina.ai"
+  - "jinaai"
+patterns:
+  - regex: 'jina_[A-Za-z0-9]{40,}'
+    entropy_min: 4.0
+    confidence: high
+verify:
+  method: GET
+  url: https://api.jina.ai/v1/models
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200]
+  invalid_status: [401, 403]

pkg/providers/definitions/perplexity.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: perplexity
+display_name: Perplexity AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "perplexity"
+  - "PERPLEXITY_API_KEY"
+  - "pplx-"
+  - "api.perplexity.ai"
+patterns:
+  - regex: 'pplx-[A-Za-z0-9]{48,}'
+    entropy_min: 4.0
+    confidence: high
+verify:
+  method: POST
+  url: https://api.perplexity.ai/chat/completions
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

pkg/providers/definitions/unstructured.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: unstructured
+display_name: Unstructured.io
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "unstructured"
+  - "UNSTRUCTURED_API_KEY"
+  - "api.unstructured.io"
+  - "unstructuredio"
+verify:
+  method: GET
+  url: https://api.unstructured.io/general/v0/general
+  headers:
+    unstructured-api-key: "{KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

pkg/providers/definitions/voyage.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: voyage
+display_name: Voyage AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "voyage"
+  - "VOYAGE_API_KEY"
+  - "voyageai"
+  - "api.voyageai.com"
+patterns:
+  - regex: 'pa-[A-Za-z0-9_\-]{40,}'
+    entropy_min: 4.0
+    confidence: medium
+verify:
+  method: POST
+  url: https://api.voyageai.com/v1/embeddings
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

pkg/providers/definitions/you.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: you
+display_name: You.com
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "you.com"
+  - "YDC_API_KEY"
+  - "YOU_API_KEY"
+  - "api.ydc-index.io"
+verify:
+  method: GET
+  url: https://api.ydc-index.io/search
+  headers:
+    X-API-Key: "{KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

providers/assemblyai.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: assemblyai
+display_name: AssemblyAI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "assemblyai"
+  - "ASSEMBLYAI_API_KEY"
+  - "api.assemblyai.com"
+  - "assembly.ai"
+patterns:
+  - regex: '[a-f0-9]{32}'
+    entropy_min: 4.0
+    confidence: low
+verify:
+  method: GET
+  url: https://api.assemblyai.com/v2/transcript
+  headers:
+    authorization: "{KEY}"
+  valid_status: [200]
+  invalid_status: [401, 403]

providers/jina.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: jina
+display_name: Jina AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "jina"
+  - "JINA_API_KEY"
+  - "api.jina.ai"
+  - "jinaai"
+patterns:
+  - regex: 'jina_[A-Za-z0-9]{40,}'
+    entropy_min: 4.0
+    confidence: high
+verify:
+  method: GET
+  url: https://api.jina.ai/v1/models
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200]
+  invalid_status: [401, 403]

providers/perplexity.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: perplexity
+display_name: Perplexity AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "perplexity"
+  - "PERPLEXITY_API_KEY"
+  - "pplx-"
+  - "api.perplexity.ai"
+patterns:
+  - regex: 'pplx-[A-Za-z0-9]{48,}'
+    entropy_min: 4.0
+    confidence: high
+verify:
+  method: POST
+  url: https://api.perplexity.ai/chat/completions
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

providers/unstructured.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: unstructured
+display_name: Unstructured.io
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "unstructured"
+  - "UNSTRUCTURED_API_KEY"
+  - "api.unstructured.io"
+  - "unstructuredio"
+verify:
+  method: GET
+  url: https://api.unstructured.io/general/v0/general
+  headers:
+    unstructured-api-key: "{KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

providers/voyage.yaml

@@ -0,0 +1,21 @@
+format_version: 1
+name: voyage
+display_name: Voyage AI
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "voyage"
+  - "VOYAGE_API_KEY"
+  - "voyageai"
+  - "api.voyageai.com"
+patterns:
+  - regex: 'pa-[A-Za-z0-9_\-]{40,}'
+    entropy_min: 4.0
+    confidence: medium
+verify:
+  method: POST
+  url: https://api.voyageai.com/v1/embeddings
+  headers:
+    Authorization: "Bearer {KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]

providers/you.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: you
+display_name: You.com
+tier: 3
+last_verified: "2026-04-05"
+keywords:
+  - "you.com"
+  - "YDC_API_KEY"
+  - "YOU_API_KEY"
+  - "api.ydc-index.io"
+verify:
+  method: GET
+  url: https://api.ydc-index.io/search
+  headers:
+    X-API-Key: "{KEY}"
+  valid_status: [200, 400]
+  invalid_status: [401, 403]