From 592e5ca325248a6d8ad2ed8323198621662609a8 Mon Sep 17 00:00:00 2001
From: salvacybersec <salva@opsecti.local>
Date: Sun, 5 Apr 2026 14:43:29 +0300
Subject: [PATCH] docs(03-07): complete emerging/niche + vector DB providers
 plan

---
 .../03-tier-3-9-providers/03-07-SUMMARY.md    | 99 +++++++++++++++++++
 1 file changed, 99 insertions(+)
 create mode 100644 .planning/phases/03-tier-3-9-providers/03-07-SUMMARY.md

diff --git a/.planning/phases/03-tier-3-9-providers/03-07-SUMMARY.md b/.planning/phases/03-tier-3-9-providers/03-07-SUMMARY.md
new file mode 100644
index 0000000..98ea0e3
--- /dev/null
+++ b/.planning/phases/03-tier-3-9-providers/03-07-SUMMARY.md
@@ -0,0 +1,99 @@
+---
+phase: 03-tier-3-9-providers
+plan: 07
+subsystem: providers
+tags: [providers, tier-6, emerging, vector-db, langsmith, pinecone]
+requires: []
+provides:
+  - "15 Tier 6 emerging/niche provider YAMLs"
+  - "LangSmith lsv2_ high-confidence regex"
+  - "Pinecone pcsk_ high-confidence regex"
+  - "Vector DB keyword anchors (Weaviate, Qdrant, Chroma, Milvus, Neon)"
+affects: [pkg/providers/registry]
+tech-stack:
+  added: []
+  patterns: [dual-location YAML, keyword-only detection, high-confidence prefixed regex]
+key-files:
+  created:
+    - providers/reka.yaml
+    - providers/aleph-alpha.yaml
+    - providers/lamini.yaml
+    - providers/writer.yaml
+    - providers/jasper.yaml
+    - providers/typeface.yaml
+    - providers/comet.yaml
+    - providers/wandb.yaml
+    - providers/langsmith.yaml
+    - providers/pinecone.yaml
+    - providers/weaviate.yaml
+    - providers/qdrant.yaml
+    - providers/chroma.yaml
+    - providers/milvus.yaml
+    - providers/neon.yaml
+    - pkg/providers/definitions/reka.yaml
+    - pkg/providers/definitions/aleph-alpha.yaml
+    - pkg/providers/definitions/lamini.yaml
+    - pkg/providers/definitions/writer.yaml
+    - pkg/providers/definitions/jasper.yaml
+    - pkg/providers/definitions/typeface.yaml
+    - pkg/providers/definitions/comet.yaml
+    - pkg/providers/definitions/wandb.yaml
+    - pkg/providers/definitions/langsmith.yaml
+    - pkg/providers/definitions/pinecone.yaml
+    - pkg/providers/definitions/weaviate.yaml
+    - pkg/providers/definitions/qdrant.yaml
+    - pkg/providers/definitions/chroma.yaml
+    - pkg/providers/definitions/milvus.yaml
+    - pkg/providers/definitions/neon.yaml
+  modified: []
+decisions:
+  - "Used high-confidence regex only for documented prefixes (lsv2_, pcsk_); all other Tier 6 providers rely on keyword-only detection to avoid false positives at scale"
+  - "W&B pattern uses low-confidence 40-hex regex gated by keyword pre-filter (no documented prefix)"
+  - "Jasper, Typeface, and all vector DBs use empty verify URL (keyword-only, verification deferred)"
+metrics:
+  duration: ~6m
+  completed: 2026-04-05
+---
+
+# Phase 03 Plan 07: Emerging/Niche Providers + Vector DBs Summary
+
+One-liner: Added 15 Tier 6 emerging/niche provider definitions covering emerging LLM labs, writing tools, observability, and vector databases — completing PROV-06.
+
+## What Was Built
+
+Created 30 YAML files (15 providers x 2 locations) satisfying requirement PROV-06:
+
+**Emerging LLM labs (3):** Reka AI, Aleph Alpha, Lamini
+**Writing tools (3):** Writer (palmyra), Jasper AI, Typeface
+**Observability (3):** Comet ML/Opik, Weights & Biases, LangSmith
+**Vector DBs (6):** Pinecone, Weaviate, Qdrant, Chroma, Milvus/Zilliz, Neon
+
+High-confidence regex was applied only where documented prefixes exist:
+- LangSmith: `lsv2_(pt|sk)_[a-f0-9]{32}_[a-f0-9]{10}`
+- Pinecone: `pcsk_[A-Za-z0-9]{40,}`
+- W&B: 40-hex (confidence: low) gated by keyword pre-filter
+
+All other providers rely on keyword-only detection (env var anchors, domain hostnames) to avoid false positives at scale — consistent with Phase 2 lessons documented in 03-CONTEXT.md.
+
+## Commits
+
+- `fbe9e8b` feat(03-07): add 8 emerging labs, writing tools, observability providers
+- `a73cea3` feat(03-07): add LangSmith and 6 vector DB providers
+
+## Verification
+
+- `go test ./pkg/providers/... -count=1` — PASS
+- `go test ./pkg/engine/... -count=1` — PASS
+- `grep -l 'tier: 6' providers/*.yaml | wc -l` — 15
+- All 15 provider pairs pass `diff providers/X.yaml pkg/providers/definitions/X.yaml`
+
+## Deviations from Plan
+
+None - plan executed exactly as written.
+
+## Self-Check: PASSED
+
+- All 30 YAML files exist (verified via diff)
+- Both commits present in git log (fbbb54b, a73cea3)
+- Tier 6 count = 15 (matches PROV-06 requirement)
+- Provider and engine test suites green