Merge branch 'worktree-agent-a090b6ec'

.planning/phases/03-tier-3-9-providers/03-05-SUMMARY.md

@@ -0,0 +1,89 @@
+---
+phase: 03-tier-3-9-providers
+plan: 05
+subsystem: providers
+tags: [providers, tier-8, self-hosted, runtimes, keyword-only]
+requires: [pkg/providers/schema.go, pkg/providers/registry.go]
+provides:
+  - Ollama, vLLM, LocalAI, LM Studio, llama.cpp provider definitions
+  - GPT4All, text-generation-webui, TensorRT-LLM, Triton, Jan AI provider definitions
+  - 10 Tier 8 self-hosted runtime keyword anchors for OSINT correlation
+affects: [pkg/providers/definitions/]
+tech_added: []
+patterns: [keyword-only detection for providers without documented key formats]
+files_created:
+  - providers/ollama.yaml
+  - providers/vllm.yaml
+  - providers/localai.yaml
+  - providers/lmstudio.yaml
+  - providers/llamacpp.yaml
+  - providers/gpt4all.yaml
+  - providers/text-gen-webui.yaml
+  - providers/tensorrt-llm.yaml
+  - providers/triton.yaml
+  - providers/jan.yaml
+  - pkg/providers/definitions/ollama.yaml
+  - pkg/providers/definitions/vllm.yaml
+  - pkg/providers/definitions/localai.yaml
+  - pkg/providers/definitions/lmstudio.yaml
+  - pkg/providers/definitions/llamacpp.yaml
+  - pkg/providers/definitions/gpt4all.yaml
+  - pkg/providers/definitions/text-gen-webui.yaml
+  - pkg/providers/definitions/tensorrt-llm.yaml
+  - pkg/providers/definitions/triton.yaml
+  - pkg/providers/definitions/jan.yaml
+files_modified: []
+decisions:
+  - "Used keyword-only detection (no regex patterns) for all 10 runtimes — self-hosted stacks typically lack standardized key formats; this avoids Phase 2's false-positive lessons"
+  - "Captured localhost port anchors (11434, 8080, 1234, 5000) to enable later OSINT/Shodan correlation even when no key is present"
+  - "Included CLI-flag and env-var keywords (OLLAMA_HOST, VLLM_API_KEY, LOCALAI_API_KEY, etc.) as detection anchors"
+requirements: [PROV-08]
+metrics:
+  tasks_completed: 2
+  files_created: 20
+  duration: "~3 min"
+  completed: "2026-04-05"
+---
+
+# Phase 3 Plan 05: Tier 8 Self-Hosted Runtimes Summary
+
+**One-liner:** 10 Tier 8 self-hosted LLM runtime provider YAMLs (Ollama, vLLM, LocalAI, LM Studio, llama.cpp, GPT4All, text-generation-webui, TensorRT-LLM, Triton, Jan AI) using keyword-only detection.
+
+## What Was Built
+
+Satisfies PROV-08. Twenty YAML files dual-located in `providers/` and `pkg/providers/definitions/`, each defining a Tier 8 self-hosted runtime. Because self-hosted stacks rarely use bearer-token API keys with documented formats, all definitions rely exclusively on keyword-based anchors — localhost endpoints, CLI flags, environment variable names, and project identifiers — enabling Aho-Corasick pre-filter matches during scanning and OSINT/recon correlation in later phases.
+
+## Tasks Executed
+
+| Task | Name | Commit | Files |
+| ---- | ---- | ------ | ----- |
+| 1 | Ollama, vLLM, LocalAI, LM Studio, llama.cpp YAMLs | 370dca0 | 10 files |
+| 2 | GPT4All, text-gen-webui, TensorRT-LLM, Triton, Jan AI YAMLs | 367cfed | 10 files |
+
+## Verification
+
+- `go test ./pkg/providers/... -count=1` — PASS
+- `go test ./pkg/engine/... -count=1` — PASS
+- `grep -l 'tier: 8' providers/*.yaml | wc -l` — 10
+- All 20 files byte-identical between `providers/` and `pkg/providers/definitions/`
+- All 10 YAMLs omit `patterns:` field (keyword-only)
+
+## Deviations from Plan
+
+None — plan executed exactly as written.
+
+## Self-Check: PASSED
+
+- providers/ollama.yaml — FOUND
+- providers/vllm.yaml — FOUND
+- providers/localai.yaml — FOUND
+- providers/lmstudio.yaml — FOUND
+- providers/llamacpp.yaml — FOUND
+- providers/gpt4all.yaml — FOUND
+- providers/text-gen-webui.yaml — FOUND
+- providers/tensorrt-llm.yaml — FOUND
+- providers/triton.yaml — FOUND
+- providers/jan.yaml — FOUND
+- All 10 pkg/providers/definitions/*.yaml twins — FOUND
+- Commit 370dca0 — FOUND
+- Commit 367cfed — FOUND

pkg/providers/definitions/gpt4all.yaml

@@ -0,0 +1,16 @@
+format_version: 1
+name: gpt4all
+display_name: GPT4All
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "gpt4all"
+  - "nomic-ai"
+  - "GPT4ALL_API_KEY"
+  - "gpt4all.io"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/jan.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: jan
+display_name: Jan AI
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "jan-ai"
+  - "janhq"
+  - "JAN_API_KEY"
+  - "jan.ai"
+  - "cortex-cpp"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/llamacpp.yaml

@@ -0,0 +1,18 @@
+format_version: 1
+name: llamacpp
+display_name: llama.cpp server
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "llama.cpp"
+  - "llama-cpp"
+  - "llama_cpp"
+  - "LLAMA_API_KEY"
+  - "ggml"
+  - "gguf"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/lmstudio.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: lmstudio
+display_name: LM Studio
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "lmstudio"
+  - "lm-studio"
+  - "LMSTUDIO_API_KEY"
+  - "localhost:1234"
+  - "lmstudio.ai"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/localai.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: localai
+display_name: LocalAI
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "localai"
+  - "LOCALAI_API_KEY"
+  - "go-skynet"
+  - "localai.io"
+  - "localhost:8080"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/ollama.yaml

@@ -0,0 +1,19 @@
+format_version: 1
+name: ollama
+display_name: Ollama
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "ollama"
+  - "OLLAMA_HOST"
+  - "OLLAMA_API_KEY"
+  - "OLLAMA_MODELS"
+  - "localhost:11434"
+  - "127.0.0.1:11434"
+  - "api/generate"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/tensorrt-llm.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: tensorrt-llm
+display_name: NVIDIA TensorRT-LLM
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "tensorrt-llm"
+  - "trtllm"
+  - "TRTLLM_API_KEY"
+  - "tensorrt_llm"
+  - "nvidia-nim"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/text-gen-webui.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: text-gen-webui
+display_name: text-generation-webui (oobabooga)
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "text-generation-webui"
+  - "oobabooga"
+  - "TEXTGEN_API_KEY"
+  - "text-gen-webui"
+  - "localhost:5000"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/triton.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: triton
+display_name: NVIDIA Triton Inference Server
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "triton-inference-server"
+  - "tritonserver"
+  - "TRITON_API_KEY"
+  - "triton_grpc"
+  - "v2/models"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

pkg/providers/definitions/vllm.yaml

@@ -0,0 +1,18 @@
+format_version: 1
+name: vllm
+display_name: vLLM
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "vllm"
+  - "VLLM_API_KEY"
+  - "vllm-openai"
+  - "--api-key"
+  - "openai.api_server"
+  - "vllm.entrypoints"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/gpt4all.yaml

@@ -0,0 +1,16 @@
+format_version: 1
+name: gpt4all
+display_name: GPT4All
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "gpt4all"
+  - "nomic-ai"
+  - "GPT4ALL_API_KEY"
+  - "gpt4all.io"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/jan.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: jan
+display_name: Jan AI
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "jan-ai"
+  - "janhq"
+  - "JAN_API_KEY"
+  - "jan.ai"
+  - "cortex-cpp"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/llamacpp.yaml

@@ -0,0 +1,18 @@
+format_version: 1
+name: llamacpp
+display_name: llama.cpp server
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "llama.cpp"
+  - "llama-cpp"
+  - "llama_cpp"
+  - "LLAMA_API_KEY"
+  - "ggml"
+  - "gguf"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/lmstudio.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: lmstudio
+display_name: LM Studio
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "lmstudio"
+  - "lm-studio"
+  - "LMSTUDIO_API_KEY"
+  - "localhost:1234"
+  - "lmstudio.ai"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/localai.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: localai
+display_name: LocalAI
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "localai"
+  - "LOCALAI_API_KEY"
+  - "go-skynet"
+  - "localai.io"
+  - "localhost:8080"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/ollama.yaml

@@ -0,0 +1,19 @@
+format_version: 1
+name: ollama
+display_name: Ollama
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "ollama"
+  - "OLLAMA_HOST"
+  - "OLLAMA_API_KEY"
+  - "OLLAMA_MODELS"
+  - "localhost:11434"
+  - "127.0.0.1:11434"
+  - "api/generate"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/tensorrt-llm.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: tensorrt-llm
+display_name: NVIDIA TensorRT-LLM
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "tensorrt-llm"
+  - "trtllm"
+  - "TRTLLM_API_KEY"
+  - "tensorrt_llm"
+  - "nvidia-nim"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/text-gen-webui.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: text-gen-webui
+display_name: text-generation-webui (oobabooga)
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "text-generation-webui"
+  - "oobabooga"
+  - "TEXTGEN_API_KEY"
+  - "text-gen-webui"
+  - "localhost:5000"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/triton.yaml

@@ -0,0 +1,17 @@
+format_version: 1
+name: triton
+display_name: NVIDIA Triton Inference Server
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "triton-inference-server"
+  - "tritonserver"
+  - "TRITON_API_KEY"
+  - "triton_grpc"
+  - "v2/models"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []

providers/vllm.yaml

@@ -0,0 +1,18 @@
+format_version: 1
+name: vllm
+display_name: vLLM
+tier: 8
+last_verified: "2026-04-05"
+keywords:
+  - "vllm"
+  - "VLLM_API_KEY"
+  - "vllm-openai"
+  - "--api-key"
+  - "openai.api_server"
+  - "vllm.entrypoints"
+verify:
+  method: GET
+  url: ""
+  headers: {}
+  valid_status: []
+  invalid_status: []