build(deps): pin GA MAF packages, drop [all] meta, add lockfile

The `agent-framework[all]` meta package pulls still-beta integrations
(azure-ai-search/cosmos/ollama/...) that force --prerelease and drag in an
ALPHA pydantic — unacceptable for the IR/validation layer (B1). Per the
official Semantic Kernel -> Agent Framework migration guide, install only
the packages we actually need:

- agent-framework-core / -foundry / -openai (all GA)
- pydantic pinned to stable 2.x (>=2.11,<3)

Resolves cleanly on the stable channel (pydantic 2.13.4, was 2.14.0a1).
Only remaining pre-release pin is Azure's own azure-ai-inference
(transitive via -foundry; no stable release exists yet). uv.lock committed
for reproducibility.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H9FyyENxebxVThjrn9et8C

pyproject.toml

@@ -5,8 +5,14 @@ description = "Generic framework on Microsoft Agent Framework for per-project co
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-    # MAF core. Foundry-provider-pakke/-extra avklares ved Foundry-wiring (Fase 0/1).
-    "agent-framework>=1.8.0",
+    # MAF — GA-pakker, IKKE meta-pakken `agent-framework`. Metaen drar `agent-framework-core[all]`,
+    # og `[all]` trekker inn de fortsatt-beta integrasjonene (azure-ai-search/cosmos/ollama/…) som
+    # tvinger pre-releases og drar med en ALPHA pydantic. Offisiell guide: installer kun det du trenger.
+    # Beta-integrasjoner legges til per-fase (med snevert pre-release-scope) når de faktisk trengs.
+    "agent-framework-core>=1.9.0",     # kjerne (GA)
+    "agent-framework-foundry>=1.8.2",  # Azure/Foundry-profil: FoundryChatClient (GA)
+    "agent-framework-openai>=1.8.2",   # OpenAI + OpenAI-kompatible lokale endpoints (GA) → lokal profil
+    "pydantic>=2.11,<3",               # IR/validering (B1) — eksplisitt pin til STABIL 2.x, aldri alpha
 ]
 
 [project.optional-dependencies]