chore: bump version to 1.4.0a2

* chore(deps): update dependency hls.js to v1.6.16

* chore: download vendored hls.js files + add hls to workflow detection loop

The wheel-completeness check failed on the Renovate bump because
vendor-js.yml only iterated katex/hljs/mermaid — so hls.js PRs
never got their files auto-downloaded. Adding hls to the loop so
future Renovate bumps are merge-ready without manual intervention.

Also running the update now to fix this specific PR.

---------

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: Patrick Buckley <buckleypm@gmail.com>

.env.example

@@ -20,10 +20,10 @@ TURNSTONE_JWT_SECRET=changeme-to-32-bytes-of-hex
 
 # -- Database ------------------------------------------------------------------
 # Single-node default is SQLite (zero config). Set these for PostgreSQL:
-# DB_BACKEND=postgresql
+# TURNSTONE_DB_BACKEND=postgresql
 # POSTGRES_USER=turnstone
 # POSTGRES_PASSWORD=changeme
-# DATABASE_URL=postgresql+psycopg://turnstone:changeme@postgres:5432/turnstone
+# TURNSTONE_DB_URL=postgresql+psycopg://turnstone:changeme@postgres:5432/turnstone
 
 # -- Ports ---------------------------------------------------------------------
 # SERVER_PORT=8080

.github/workflows/vendor-js.yml

@@ -48,7 +48,7 @@ jobs:
         id: detect
         run: |
           updates=()
-          for lib in katex hljs mermaid; do
+          for lib in katex hljs mermaid hls; do
             version=$(grep -oE "${lib}-[0-9.]+" pyproject.toml | head -1 | sed "s/${lib}-//")
             [[ -z "$version" ]] && continue
             [[ -d "turnstone/shared_static/${lib}-${version}" ]] && continue

README.md

@@ -53,6 +53,15 @@ pip install turnstone[console]
 turnstone-console --port 8090
 ```
 
+For PostgreSQL (recommended for production):
+
+```bash
+pip install turnstone[postgres]
+export TURNSTONE_DB_BACKEND=postgresql
+export TURNSTONE_DB_URL="postgresql+psycopg://user:pass@localhost:5432/turnstone"
+turnstone-server --port 8080 --base-url http://localhost:8000/v1
+```
+
 ### Docker
 
 ```bash

compose.yaml

@@ -9,7 +9,7 @@
 # Usage:
 #   Infra only:           docker compose up
 #   Single node:          docker compose --profile production up
-#   Production (PG):      DB_BACKEND=postgresql docker compose --profile production up
+#   Production (PG):      TURNSTONE_DB_BACKEND=postgresql docker compose --profile production up
 #   10-node cluster:      docker compose --profile cluster up
 # =============================================================================
 
@@ -94,8 +94,8 @@ services:
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
       - MODEL=${MODEL:-}
       - MCP_CONFIG=${MCP_CONFIG:-}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-sqlite}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-sqlite}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-}
       - TURNSTONE_NODE_ID=${TURNSTONE_NODE_ID:-}
       - TURNSTONE_ADVERTISE_URL=${TURNSTONE_ADVERTISE_URL:-http://server:8080}
     extra_hosts:
@@ -131,8 +131,8 @@ services:
     environment:
       # Generate with: python -c "import secrets; print(secrets.token_hex(32))"
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-sqlite}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-sqlite}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-}
       - TURNSTONE_CONSOLE_URL=http://console:8090
     networks:
       - turnstone-net
@@ -165,8 +165,8 @@ services:
       - TURNSTONE_DISCORD_GUILD=${TURNSTONE_DISCORD_GUILD:-0}
       # Generate with: python -c "import secrets; print(secrets.token_hex(32))"
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-postgresql}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:-turnstone}@postgres:5432/turnstone}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-postgresql}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:-turnstone}@postgres:5432/turnstone}
       - TURNSTONE_CHANNEL_ADVERTISE_URL=http://channel:8091
     networks:
       - turnstone-net
@@ -215,8 +215,8 @@ services:
       TURNSTONE_JWT_SECRET: ${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
       MODEL: ${MODEL:-}
       MCP_CONFIG: ${MCP_CONFIG:-}
-      TURNSTONE_DB_BACKEND: ${DB_BACKEND:-postgresql}
-      TURNSTONE_DB_URL: ${DATABASE_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:?}@postgres:5432/turnstone}
+      TURNSTONE_DB_BACKEND: ${TURNSTONE_DB_BACKEND:-postgresql}
+      TURNSTONE_DB_URL: ${TURNSTONE_DB_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:?}@postgres:5432/turnstone}
       TURNSTONE_NODE_ID: node-1
       TURNSTONE_ADVERTISE_URL: http://server-1:8080
     extra_hosts: ["host.docker.internal:host-gateway"]

docs/architecture.md

@@ -696,6 +696,26 @@ agent_model = "claude"
 Each `[models.*]` entry produces a `ModelConfig` with a `provider` field
 (default: `"openai"`). Supported values: `"openai"`, `"anthropic"`, `"google"`,
 and `"openai-compatible"`.
+
+**Per-model sampling overrides:** Each model can specify `temperature`,
+`max_tokens`, and `reasoning_effort` to override the global defaults from
+ConfigStore. When unset (`NULL`), the global default is used.
+
+```toml
+[models.local]
+base_url = "http://localhost:8000/v1"
+model = "qwen3-32b"
+temperature = 0.7
+max_tokens = 8192
+
+[models.o3]
+base_url = "https://api.openai.com/v1"
+api_key = "sk-..."
+model = "o3"
+reasoning_effort = "high"
+# temperature omitted — uses global default
+```
+
 An optional `[models.*.capabilities]` sub-table overrides per-model
 `ModelCapabilities` flags (useful for local models whose capabilities
 cannot be detected programmatically):
@@ -709,9 +729,15 @@ model = "qwen-3.5-vl"
 supports_vision = true
 ```
 
+**Database model definitions:** On server entry points, models can also be
+defined in the `model_definitions` table (admin Models tab). DB models support
+the same per-model sampling overrides. Config.toml models override DB models
+with the same alias in-memory (the DB rows are never modified).
+
 **Lifecycle:**
-1. `load_model_registry()` reads `[models.*]` sections from config.toml and
-   builds a `"default"` entry from CLI `--base-url`/`--model`/`--api-key` args
+1. `load_model_registry()` loads DB model definitions (if storage available),
+   then overlays `[models.*]` from config.toml, then builds a `"default"` entry
+   from CLI `--base-url`/`--model`/`--api-key` args
 2. The registry is passed to the session factory closure in both `cli.py` and
    `server.py`; each workstream resolves its model on creation
 3. `ModelRegistry.get_client()` lazily creates SDK client instances via
@@ -720,7 +746,8 @@ supports_vision = true
 4. `ModelRegistry.get_provider()` lazily creates `LLMProvider` instances via
    `create_provider()` (also cached and thread-safe)
 5. `/model` command shows available models; `/model <alias>` switches the
-   active workstream's client, model, and context window
+   active workstream's client, model, context window, and per-model sampling
+   parameters
 6. `_create_stream_with_retry()` tries the primary model, then each fallback
    alias in order if the primary is unreachable
 7. `_run_agent()` resolves `registry.agent_model` (if set) for plan/task

docs/diagrams/03-core-engine-classes.puml

@@ -295,7 +295,7 @@ class "ModelRegistry" as ModelReg {
     --
     Thread-safe lazy client + provider
     creation. Loaded by load_model_registry()
-    from CLI args + [models.*] config.
+    from DB + [models.*] config + CLI args.
     --
     core/model_registry.py
 }
@@ -306,6 +306,9 @@ class "ModelConfig" as ModelCfg <<frozen>> {
     + base_url: str
     + model: str
     + context_window: int
+    + temperature: float | None
+    + max_tokens: int | None
+    + reasoning_effort: str | None
 }
 
 ' Circuit breaker state

docs/diagrams/png/03-core-engine-classes.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6471e611beebf647f3a191eb16588571a404cc52a43067883a2b6f06dd936376
-size 594676
+oid sha256:474b900448ec04d1117b48a2b55614524721b2f04ac4bda66170bd0a06aae0f2
+size 624573

docs/docker.md

@@ -83,11 +83,15 @@ Auth is always enabled. `TURNSTONE_JWT_SECRET` is required.
 | Variable | Default | Description |
 |----------|---------|-------------|
 | `TURNSTONE_DB_BACKEND` | `sqlite` | Storage backend: `sqlite` or `postgresql` |
-| `TURNSTONE_DB_URL` | — | Database URL (e.g. `postgresql://user:pass@db:5432/turnstone`). For SQLite, defaults to `/data/.turnstone.db` |
+| `TURNSTONE_DB_URL` | — | Database URL (e.g. `postgresql+psycopg://user:pass@postgres:5432/turnstone`). For SQLite, defaults to `/data/.turnstone.db` |
 | `TURNSTONE_DB_POOL_SIZE` | `2` | PostgreSQL connection pool size per process (default: 2 base + 3 overflow = 5 max) |
+| `POSTGRES_USER` | `turnstone` | PostgreSQL container username (used in default `TURNSTONE_DB_URL` for cluster/channel) |
+| `POSTGRES_PASSWORD` | — | PostgreSQL container password (required for production and cluster profiles) |
 
 The database stores workstream history, user accounts, and API tokens. When using JWT auth, a database backend is required for user storage.
 
+> **Upgrading from <1.3.0a4:** Earlier versions used `DB_BACKEND` and `DATABASE_URL` in `.env`, which `compose.yaml` mapped to the `TURNSTONE_`-prefixed names internally. These short aliases have been removed. Rename `DB_BACKEND` → `TURNSTONE_DB_BACKEND` and `DATABASE_URL` → `TURNSTONE_DB_URL` in your `.env` file.
+
 > **Large clusters:** Each turnstone process maintains a small connection pool (5 max). At hundreds of nodes this adds up — use [PgBouncer](pgbouncer.md) in transaction pooling mode between turnstone and PostgreSQL.
 
 > **First-time setup:** After deploying with auth enabled, create an initial admin user by running `turnstone-admin create-user` inside the container:

docs/pgbouncer.md

@@ -67,7 +67,7 @@ services:
 ```
 
 Then point turnstone services at PgBouncer instead of PostgreSQL
-directly by changing the `DATABASE_URL` (or `TURNSTONE_DB_URL`):
+directly by changing `TURNSTONE_DB_URL`:
 
 ```bash
 # Before (direct)

docs/settings.md

@@ -36,6 +36,31 @@ users to the admin Settings API.
 
 ---
 
+## Per-Model Sampling Overrides
+
+The global `model.temperature`, `model.max_tokens`, and `model.reasoning_effort`
+settings serve as cluster-wide defaults. Individual models can override these
+via per-model settings in the `model_definitions` table (admin Models tab).
+
+Resolution order for sampling parameters:
+
+| Priority | Source |
+|----------|--------|
+| 1 (highest) | Per-model override (set in Models tab) |
+| 2 | Global default (set in Settings tab) |
+| 3 | Registry default (code) |
+
+When a per-model override is `NULL` (empty in the UI), the global default is
+used. Switching models via `/model <alias>` re-resolves sampling parameters
+from the new model's overrides or global defaults.
+
+**Removed settings:** `model.name` and `model.context_window` have been removed
+from ConfigStore. Model names and context windows are now configured per-model
+in the Models tab. A startup warning is logged if these keys appear in
+`config.toml`.
+
+---
+
 ## Bootstrap vs ConfigStore
 
 **Bootstrap settings** are required before storage is available (database
@@ -49,12 +74,12 @@ connection, Redis, auth secrets, server bind address). These stay in
 | Auth | `[auth]` | config.toml / env |
 | Console bind | `[console]` | config.toml / env |
 
-**ConfigStore settings** (51 settings) are loaded from the database after
-storage initialization:
+**ConfigStore settings** are loaded from the database after storage
+initialization:
 
 | Section | Settings |
 |---------|----------|
-| `model` | name, temperature, max_tokens, reasoning_effort, context_window |
+| `model` | default_alias, temperature, max_tokens, reasoning_effort |
 | `session` | instructions, retention_days, compact_max_tokens, auto_compact_pct |
 | `tools` | timeout, truncation, agent_max_turns, skip_permissions, search, search_threshold, search_max_results |
 | `server` | workstream_idle_timeout, max_workstreams |

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "turnstone"
-version = "1.3.0a3"
+version = "1.4.0a2"
 description = "Multi-node AI orchestration platform with tool use, agent routing, and cluster simulation."
 readme = "README.md"
 license = "BUSL-1.1"
@@ -80,7 +80,7 @@ include = [
   "turnstone/shared_static/katex-0.16.45/**/*",
   "turnstone/shared_static/hljs-11.11.1/**/*",
   "turnstone/shared_static/mermaid-11.14.0/**/*",
-  "turnstone/shared_static/hls-1.6.15/**/*",
+  "turnstone/shared_static/hls-1.6.16/**/*",
   "turnstone/sdk/py.typed",
   "turnstone/deploy/*.yaml",
 ]

tests/test_config_store.py

@@ -87,8 +87,8 @@ class TestSetGetRoundTrip:
         assert store.get("tools.skip_permissions") is False
 
     def test_str(self, store):
-        store.set("model.name", "gpt-5")
-        assert store.get("model.name") == "gpt-5"
+        store.set("model.default_alias", "gpt5-prod")
+        assert store.get("model.default_alias") == "gpt5-prod"
 
 
 # ---------------------------------------------------------------------------
@@ -165,10 +165,10 @@ class TestStoredKeys:
         assert store.stored_keys() == frozenset()
         store.set("tools.timeout", 30)
         assert store.stored_keys() == frozenset({"tools.timeout"})
-        store.set("model.name", "gpt-5")
-        assert store.stored_keys() == frozenset({"tools.timeout", "model.name"})
+        store.set("model.default_alias", "gpt5-prod")
+        assert store.stored_keys() == frozenset({"tools.timeout", "model.default_alias"})
         store.delete("tools.timeout")
-        assert store.stored_keys() == frozenset({"model.name"})
+        assert store.stored_keys() == frozenset({"model.default_alias"})
 
 
 # ---------------------------------------------------------------------------

tests/test_model_definition_storage.py

@@ -161,3 +161,54 @@ class TestModelDefinitionStorage:
         assert m["capabilities"] == "{}"
         assert m["enabled"] is True
         assert m["created_by"] == ""
+        # Per-model sampling params default to None (use global default)
+        assert m["temperature"] is None
+        assert m["max_tokens"] is None
+        assert m["reasoning_effort"] is None
+
+    def test_create_with_sampling_params(self, db: SQLiteBackend) -> None:
+        did = _make_id()
+        db.create_model_definition(
+            definition_id=did,
+            alias="sampling",
+            model="gpt-5",
+            temperature=0.7,
+            max_tokens=8192,
+            reasoning_effort="high",
+        )
+        m = db.get_model_definition(did)
+        assert m is not None
+        assert m["temperature"] == 0.7
+        assert m["max_tokens"] == 8192
+        assert m["reasoning_effort"] == "high"
+
+    def test_create_with_zero_temperature(self, db: SQLiteBackend) -> None:
+        """temperature=0.0 is a valid override, distinct from None."""
+        did = _make_id()
+        db.create_model_definition(
+            definition_id=did, alias="zero-temp", model="o3", temperature=0.0
+        )
+        m = db.get_model_definition(did)
+        assert m is not None
+        assert m["temperature"] == 0.0
+
+    def test_update_sampling_params(self, db: SQLiteBackend) -> None:
+        did = _make_id()
+        db.create_model_definition(definition_id=did, alias="upd-samp", model="gpt-5")
+        db.update_model_definition(did, temperature=1.2, max_tokens=4096, reasoning_effort="low")
+        m = db.get_model_definition(did)
+        assert m is not None
+        assert m["temperature"] == 1.2
+        assert m["max_tokens"] == 4096
+        assert m["reasoning_effort"] == "low"
+
+    def test_clear_sampling_params(self, db: SQLiteBackend) -> None:
+        """Setting sampling params to None clears them back to global default."""
+        did = _make_id()
+        db.create_model_definition(
+            definition_id=did, alias="clear-samp", model="gpt-5", temperature=0.9
+        )
+        db.update_model_definition(did, temperature=None)
+        m = db.get_model_definition(did)
+        assert m is not None
+        assert m["temperature"] is None

tests/test_model_registry.py

@@ -51,6 +51,31 @@ class TestModelConfig:
         cfg = ModelConfig(alias="test", base_url="http://x", api_key="sk-secret-key", model="m")
         assert "sk-secret-key" not in repr(cfg)
 
+    def test_sampling_params_default_none(self) -> None:
+        cfg = ModelConfig(alias="x", base_url="x", api_key="x", model="x")
+        assert cfg.temperature is None
+        assert cfg.max_tokens is None
+        assert cfg.reasoning_effort is None
+
+    def test_sampling_params_set(self) -> None:
+        cfg = ModelConfig(
+            alias="x",
+            base_url="x",
+            api_key="x",
+            model="x",
+            temperature=0.7,
+            max_tokens=8192,
+            reasoning_effort="high",
+        )
+        assert cfg.temperature == 0.7
+        assert cfg.max_tokens == 8192
+        assert cfg.reasoning_effort == "high"
+
+    def test_zero_temperature_distinct_from_none(self) -> None:
+        cfg = ModelConfig(alias="x", base_url="x", api_key="x", model="x", temperature=0.0)
+        assert cfg.temperature == 0.0
+        assert cfg.temperature is not None
+
 
 # ---------------------------------------------------------------------------
 # ModelRegistry
@@ -483,6 +508,58 @@ class TestLoadModelRegistryWithDB:
             reg = load_model_registry("http://x/v1", "x", "x", storage=storage)
         assert reg.get_config("caps-model").capabilities == {"supports_vision": True}
 
+    def test_db_sampling_params_loaded(self) -> None:
+        """Per-model sampling params from DB are carried in ModelConfig."""
+        storage = _MockStorage(
+            [
+                {
+                    "alias": "hot-model",
+                    "model": "m",
+                    "provider": "openai",
+                    "base_url": "",
+                    "api_key": "",
+                    "context_window": 32768,
+                    "capabilities": "{}",
+                    "enabled": True,
+                    "temperature": 1.5,
+                    "max_tokens": 4096,
+                    "reasoning_effort": "high",
+                }
+            ]
+        )
+        with patch("turnstone.core.model_registry.load_config", return_value={}):
+            reg = load_model_registry("http://x/v1", "x", "x", storage=storage)
+        cfg = reg.get_config("hot-model")
+        assert cfg.temperature == 1.5
+        assert cfg.max_tokens == 4096
+        assert cfg.reasoning_effort == "high"
+
+    def test_db_sampling_params_null_means_none(self) -> None:
+        """NULL sampling params in DB map to None (use global default)."""
+        storage = _MockStorage(
+            [
+                {
+                    "alias": "null-model",
+                    "model": "m",
+                    "provider": "openai",
+                    "base_url": "",
+                    "api_key": "",
+                    "context_window": 32768,
+                    "capabilities": "{}",
+                    "enabled": True,
+                    "temperature": None,
+                    "max_tokens": None,
+                    "reasoning_effort": None,
+                }
+            ]
+        )
+        with patch("turnstone.core.model_registry.load_config", return_value={}):
+            reg = load_model_registry("http://x/v1", "x", "x", storage=storage)
+        cfg = reg.get_config("null-model")
+        assert cfg.temperature is None
+        assert cfg.max_tokens is None
+        assert cfg.reasoning_effort is None
+
     def test_db_default_alias_not_clobbered(self) -> None:
         """DB model with alias='default' is not overwritten by CLI args."""
         storage = _MockStorage(
@@ -688,6 +765,45 @@ class TestSessionModelCommand:
         assert session.context_window == 64000
         assert "Switched to" in session.ui.infos[-1]
 
+    def test_model_switch_applies_sampling_params(self) -> None:
+        reg = ModelRegistry(
+            models={
+                "default": ModelConfig("default", "x", "x", "default-model"),
+                "hot": ModelConfig(
+                    "hot",
+                    "y",
+                    "y",
+                    "hot-model",
+                    temperature=1.5,
+                    max_tokens=2048,
+                    reasoning_effort="high",
+                ),
+            },
+            default="default",
+        )
+        session = _make_session(registry=reg, model_alias="default")
+        assert session.temperature == 0.5  # initial global default
+        session.handle_command("/model hot")
+        assert session.temperature == 1.5
+        assert session.max_tokens == 2048
+        assert session.reasoning_effort == "high"
+
+    def test_model_switch_none_params_reverts_to_global(self) -> None:
+        """Switching to a model with no overrides reverts to global defaults."""
+        reg = ModelRegistry(
+            models={
+                "hot": ModelConfig("hot", "x", "x", "hot-model", temperature=1.5),
+                "plain": ModelConfig("plain", "y", "y", "plain-model"),
+            },
+            default="hot",
+        )
+        session = _make_session(registry=reg, model_alias="hot")
+        session.temperature = 1.5  # as set by per-model override
+        # Without a config_store, fallback keeps current value (CLI sessions).
+        # With a config_store, it would revert to the global default.
+        session.handle_command("/model plain")
+        assert session.temperature == 1.5  # no config_store → keeps current
+
     def test_model_switch_unknown_alias(self) -> None:
         reg = ModelRegistry(
             models={"default": ModelConfig("default", "x", "x", "test-model")},

tests/test_providers.py

@@ -152,6 +152,52 @@ class TestOpenAIProvider:
     def test_provider_name(self) -> None:
         assert self.provider.provider_name == "openai-compatible"
 
+    # -- _apply_thinking_mode -------------------------------------------------
+
+    def test_thinking_mode_none_does_nothing(self) -> None:
+        """No thinking params injected when thinking_mode is 'none'."""
+        caps = ModelCapabilities(thinking_mode="none")
+        extra_body: dict[str, Any] = {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert "enable_thinking" not in extra_body["chat_template_kwargs"]
+
+    def test_thinking_mode_manual_injects_param(self) -> None:
+        """Manual thinking mode injects enable_thinking into chat_template_kwargs."""
+        caps = ModelCapabilities(thinking_mode="manual")
+        extra_body: dict[str, Any] = {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert extra_body["chat_template_kwargs"]["enable_thinking"] is True
+        assert extra_body["chat_template_kwargs"]["reasoning_effort"] == "medium"
+
+    def test_thinking_mode_custom_param(self) -> None:
+        """Custom thinking_param (e.g. Granite's 'thinking') is used."""
+        caps = ModelCapabilities(thinking_mode="manual", thinking_param="thinking")
+        extra_body: dict[str, Any] = {"chat_template_kwargs": {}}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert extra_body["chat_template_kwargs"]["thinking"] is True
+        assert "enable_thinking" not in extra_body["chat_template_kwargs"]
+
+    def test_thinking_mode_does_not_override_explicit(self) -> None:
+        """If operator explicitly set the param to False, provider respects it."""
+        caps = ModelCapabilities(thinking_mode="manual")
+        extra_body: dict[str, Any] = {"chat_template_kwargs": {"enable_thinking": False}}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert extra_body["chat_template_kwargs"]["enable_thinking"] is False
+
+    def test_thinking_mode_creates_ctk_if_missing(self) -> None:
+        """Creates chat_template_kwargs dict if not present in extra_body."""
+        caps = ModelCapabilities(thinking_mode="manual")
+        extra_body: dict[str, Any] = {}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert extra_body["chat_template_kwargs"]["enable_thinking"] is True
+
+    def test_thinking_mode_adaptive(self) -> None:
+        """Adaptive thinking mode also injects the param."""
+        caps = ModelCapabilities(thinking_mode="adaptive")
+        extra_body: dict[str, Any] = {"chat_template_kwargs": {}}
+        OpenAIProvider._apply_thinking_mode(extra_body, caps)
+        assert extra_body["chat_template_kwargs"]["enable_thinking"] is True
+
     # -- _sanitize_messages ---------------------------------------------------
 
     def test_sanitize_messages_none_content_no_tool_calls(self) -> None:

tests/test_server_compat.py

@@ -0,0 +1,273 @@
+"""Tests for turnstone.core.server_compat — profile suggestion and merging."""
+
+from __future__ import annotations
+
+from typing import Any
+from unittest.mock import MagicMock
+
+from turnstone.core.providers._openai_chat import OpenAIChatCompletionsProvider
+from turnstone.core.providers._protocol import ModelCapabilities
+from turnstone.core.server_compat import merge_server_compat, suggest_profile
+
+# ---------------------------------------------------------------------------
+# suggest_profile
+# ---------------------------------------------------------------------------
+
+
+class TestSuggestProfile:
+    def test_vllm_gemma4(self) -> None:
+        p = suggest_profile("vllm", "google/gemma-4-31B-it")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+        assert p["capabilities"]["thinking_param"] == "enable_thinking"
+        assert p["server_compat"]["extra_body"]["skip_special_tokens"] is False
+
+    def test_vllm_gemma3(self) -> None:
+        p = suggest_profile("vllm", "google/gemma-3-27b-it")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+
+    def test_vllm_qwen3(self) -> None:
+        p = suggest_profile("vllm", "Qwen/Qwen3-8B")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+        assert p["capabilities"]["thinking_param"] == "enable_thinking"
+        # Qwen doesn't need skip_special_tokens workaround
+        assert "extra_body" not in p.get("server_compat", {})
+
+    def test_vllm_qwq(self) -> None:
+        p = suggest_profile("vllm", "Qwen/QwQ-32B")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+
+    def test_vllm_granite(self) -> None:
+        p = suggest_profile("vllm", "ibm-granite/granite-3.2-2b-instruct")
+        assert p["capabilities"]["thinking_param"] == "thinking"
+
+    def test_vllm_deepseek_r1(self) -> None:
+        p = suggest_profile("vllm", "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
+        assert p["capabilities"]["thinking_param"] == "thinking"
+
+    def test_vllm_deepseek_v3_no_thinking(self) -> None:
+        """DeepSeek-V3 is a chat model, not a reasoning model — no thinking profile."""
+        p = suggest_profile("vllm", "deepseek-ai/DeepSeek-V3-0324")
+        assert "capabilities" not in p
+        assert p["server_compat"]["server_type"] == "vllm"
+
+    def test_vllm_non_thinking_model(self) -> None:
+        p = suggest_profile("vllm", "meta-llama/Llama-3-70B-Instruct")
+        assert "capabilities" not in p
+        assert p["server_compat"]["server_type"] == "vllm"
+
+    def test_llama_cpp_non_thinking(self) -> None:
+        p = suggest_profile("llama.cpp", "some-model")
+        assert p["server_compat"]["server_type"] == "llama.cpp"
+        assert "capabilities" not in p
+
+    def test_llama_cpp_gemma_thinking(self) -> None:
+        """llama.cpp with Gemma model gets thinking profile with reasoning_format."""
+        p = suggest_profile("llama.cpp", "gemma-4-E4B-it.gguf")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+        assert p["server_compat"]["extra_body"]["reasoning_format"] == "auto"
+
+    def test_llama_cpp_qwen_thinking(self) -> None:
+        p = suggest_profile("llama.cpp", "Qwen3-8B-Q4_K_M.gguf")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+
+    def test_sglang(self) -> None:
+        p = suggest_profile("sglang", "some-model")
+        assert p["server_compat"]["server_type"] == "sglang"
+
+    def test_unknown_server(self) -> None:
+        assert suggest_profile("unknown", "foo") == {}
+
+    def test_empty_inputs(self) -> None:
+        assert suggest_profile("", "") == {}
+
+    def test_openai_compatible_fallback(self) -> None:
+        """Generic openai-compatible without a specific profile."""
+        assert suggest_profile("openai-compatible", "some-local-model") == {}
+
+    def test_case_insensitive_model_match(self) -> None:
+        """Model matching should be case-insensitive."""
+        p = suggest_profile("vllm", "Google/GEMMA-4-31B-IT")
+        assert p["capabilities"]["thinking_mode"] == "manual"
+
+    def test_holo_requires_holo2(self) -> None:
+        """Short 'holo' prefix shouldn't false-match; 'holo2' should match."""
+        p_short = suggest_profile("vllm", "some-org/hologram-7b")
+        assert "capabilities" not in p_short
+        p_long = suggest_profile("vllm", "some-org/Holo2-14B")
+        assert p_long["capabilities"]["thinking_mode"] == "manual"
+
+    def test_suggest_returns_deep_copy(self) -> None:
+        """Mutating the returned profile should not affect future calls."""
+        p1 = suggest_profile("vllm", "google/gemma-4-31B-it")
+        p1["capabilities"]["thinking_mode"] = "none"
+        p2 = suggest_profile("vllm", "google/gemma-4-31B-it")
+        assert p2["capabilities"]["thinking_mode"] == "manual"
+
+
+# ---------------------------------------------------------------------------
+# merge_server_compat
+# ---------------------------------------------------------------------------
+
+
+class TestMergeServerCompat:
+    def test_empty_compat_returns_base_only(self) -> None:
+        base = {"reasoning_effort": "medium"}
+        result = merge_server_compat(base, {})
+        assert result == {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+
+    def test_extra_body_merged_top_level(self) -> None:
+        base = {"reasoning_effort": "medium"}
+        compat = {"extra_body": {"skip_special_tokens": False}}
+        result = merge_server_compat(base, compat)
+        assert result["skip_special_tokens"] is False
+        assert "chat_template_kwargs" in result
+
+    def test_full_vllm_gemma_compat(self) -> None:
+        base = {"reasoning_effort": "medium"}
+        compat = {
+            "server_type": "vllm",
+            "extra_body": {"skip_special_tokens": False},
+        }
+        result = merge_server_compat(base, compat)
+        assert result == {
+            "chat_template_kwargs": {"reasoning_effort": "medium"},
+            "skip_special_tokens": False,
+        }
+
+    def test_extra_body_chat_template_kwargs_deep_merged(self) -> None:
+        """chat_template_kwargs in extra_body is deep-merged, operator wins."""
+        base = {"reasoning_effort": "medium"}
+        compat = {
+            "extra_body": {
+                "chat_template_kwargs": {"custom_flag": True, "reasoning_effort": "high"},
+                "skip_special_tokens": False,
+            },
+        }
+        result = merge_server_compat(base, compat)
+        # Operator values win over base
+        assert result["chat_template_kwargs"]["custom_flag"] is True
+        assert result["chat_template_kwargs"]["reasoning_effort"] == "high"
+        assert result["skip_special_tokens"] is False
+
+    def test_extra_body_chat_template_kwargs_non_dict_ignored(self) -> None:
+        """Non-dict chat_template_kwargs in extra_body is safely ignored."""
+        base = {"reasoning_effort": "medium"}
+        compat = {"extra_body": {"chat_template_kwargs": "bad"}}
+        result = merge_server_compat(base, compat)
+        assert result["chat_template_kwargs"] == {"reasoning_effort": "medium"}
+
+    def test_base_not_mutated(self) -> None:
+        base = {"reasoning_effort": "medium"}
+        compat = {"extra_body": {"skip_special_tokens": False}}
+        merge_server_compat(base, compat)
+        assert "skip_special_tokens" not in base
+
+    def test_non_dict_extra_body_ignored(self) -> None:
+        """Gracefully handle malformed server_compat."""
+        base = {"reasoning_effort": "medium"}
+        result = merge_server_compat(base, {"extra_body": 42})
+        assert result == {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+
+
+# ---------------------------------------------------------------------------
+# End-to-end: session merge + provider thinking mode
+# ---------------------------------------------------------------------------
+
+
+class TestEndToEndRequestShaping:
+    """Compose both layers — session builds extra_params, provider applies thinking."""
+
+    def test_vllm_gemma_full_flow(self) -> None:
+        """Session merges server workarounds, provider adds thinking param."""
+        caps = ModelCapabilities(thinking_mode="manual", thinking_param="enable_thinking")
+        base_ctk = {"reasoning_effort": "medium"}
+        server_compat = {
+            "server_type": "vllm",
+            "extra_body": {"skip_special_tokens": False},
+        }
+        # Step 1: session merges
+        extra_params = merge_server_compat(base_ctk, server_compat)
+        # Step 2: provider finalises
+        extra_body = dict(extra_params)
+        OpenAIChatCompletionsProvider._apply_thinking_mode(extra_body, caps)
+
+        assert extra_body == {
+            "chat_template_kwargs": {
+                "reasoning_effort": "medium",
+                "enable_thinking": True,
+            },
+            "skip_special_tokens": False,
+        }
+
+    def test_granite_thinking_key(self) -> None:
+        """Granite uses 'thinking' instead of 'enable_thinking'."""
+        caps = ModelCapabilities(thinking_mode="manual", thinking_param="thinking")
+        extra_params = merge_server_compat({"reasoning_effort": "low"}, {})
+        extra_body = dict(extra_params)
+        OpenAIChatCompletionsProvider._apply_thinking_mode(extra_body, caps)
+
+        assert extra_body["chat_template_kwargs"]["thinking"] is True
+        assert "enable_thinking" not in extra_body["chat_template_kwargs"]
+
+    def test_non_thinking_model_no_injection(self) -> None:
+        """Non-thinking model gets no thinking params."""
+        caps = ModelCapabilities()  # thinking_mode="none"
+        extra_params = merge_server_compat({"reasoning_effort": "medium"}, {})
+        extra_body = dict(extra_params)
+        OpenAIChatCompletionsProvider._apply_thinking_mode(extra_body, caps)
+
+        assert extra_body == {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+
+
+# ---------------------------------------------------------------------------
+# Probe integration: suggest_profile called from _detect_openai_compat
+# ---------------------------------------------------------------------------
+
+
+class TestProbeIntegration:
+    def test_detect_vllm_gemma_suggests_profile(self) -> None:
+        """_detect_openai_compat returns suggested_capabilities and suggested_server_compat."""
+        from turnstone.core.model_registry import _detect_openai_compat
+
+        result: dict[str, Any] = {
+            "reachable": True,
+            "model_found": True,
+            "available_models": ["google/gemma-4-31B-it"],
+            "context_window": None,
+            "server_type": None,
+            "error": None,
+        }
+        model_obj = MagicMock()
+        model_obj.model_dump.return_value = {"owned_by": "vllm"}
+
+        _detect_openai_compat(
+            result, model_obj, "google/gemma-4-31B-it", "http://localhost:8000/v1"
+        )
+
+        assert result["server_type"] == "vllm"
+        assert result["suggested_capabilities"]["thinking_mode"] == "manual"
+        assert result["suggested_capabilities"]["thinking_param"] == "enable_thinking"
+        assert result["suggested_server_compat"]["extra_body"]["skip_special_tokens"] is False
+
+    def test_detect_non_thinking_no_suggested_capabilities(self) -> None:
+        """Non-thinking vLLM model gets server_compat but no capabilities suggestion."""
+        from turnstone.core.model_registry import _detect_openai_compat
+
+        result: dict[str, Any] = {
+            "reachable": True,
+            "model_found": True,
+            "available_models": ["meta-llama/Llama-3-70B"],
+            "context_window": None,
+            "server_type": None,
+            "error": None,
+        }
+        model_obj = MagicMock()
+        model_obj.model_dump.return_value = {"owned_by": "vllm"}
+
+        _detect_openai_compat(
+            result, model_obj, "meta-llama/Llama-3-70B", "http://localhost:8000/v1"
+        )
+
+        assert result["server_type"] == "vllm"
+        assert "suggested_capabilities" not in result
+        assert result["suggested_server_compat"]["server_type"] == "vllm"

tests/test_session.py

@@ -1080,3 +1080,85 @@ class TestProviderExtraParams:
         openai_prov = create_provider("openai")
         result = session._provider_extra_params(provider=openai_prov)
         assert result is None
+
+    def test_server_compat_extra_body_merged(self, tmp_db):
+        """server_compat.extra_body workarounds are merged into extra_params."""
+        from turnstone.core.model_registry import ModelConfig, ModelRegistry
+
+        session = self._session_with_provider("openai-compatible", tmp_db)
+        cfg = ModelConfig(
+            alias="test",
+            base_url="http://localhost:8000/v1",
+            api_key="none",
+            model="google/gemma-4-31B-it",
+            server_compat={
+                "extra_body": {"skip_special_tokens": False},
+            },
+        )
+        session._registry = ModelRegistry(models={"test": cfg}, default="test")
+        session._model_alias = "test"
+        result = session._provider_extra_params()
+        assert result is not None
+        assert result["chat_template_kwargs"]["reasoning_effort"] == "medium"
+        assert result["skip_special_tokens"] is False
+
+    def test_empty_server_compat_backwards_compatible(self, tmp_db):
+        """Empty server_compat produces same output as before."""
+        session = self._session_with_provider("openai-compatible", tmp_db)
+        result = session._provider_extra_params()
+        assert result == {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+
+    def test_server_compat_with_reasoning_effort_override(self, tmp_db):
+        """reasoning_effort override works alongside server_compat."""
+        from turnstone.core.model_registry import ModelConfig, ModelRegistry
+
+        session = self._session_with_provider("openai-compatible", tmp_db)
+        cfg = ModelConfig(
+            alias="test",
+            base_url="http://localhost:8000/v1",
+            api_key="none",
+            model="google/gemma-4-31B-it",
+            server_compat={"extra_body": {"skip_special_tokens": False}},
+        )
+        session._registry = ModelRegistry(models={"test": cfg}, default="test")
+        session._model_alias = "test"
+        result = session._provider_extra_params(reasoning_effort="high")
+        assert result is not None
+        assert result["chat_template_kwargs"]["reasoning_effort"] == "high"
+        assert result["skip_special_tokens"] is False
+
+    def test_model_alias_resolves_target_compat(self, tmp_db):
+        """model_alias parameter selects compat from the target, not the primary."""
+        from turnstone.core.model_registry import ModelConfig, ModelRegistry
+
+        session = self._session_with_provider("openai-compatible", tmp_db)
+        primary = ModelConfig(
+            alias="primary",
+            base_url="http://localhost:8000/v1",
+            api_key="none",
+            model="google/gemma-4-31B-it",
+            server_compat={"extra_body": {"skip_special_tokens": False}},
+        )
+        fallback = ModelConfig(
+            alias="fallback",
+            base_url="http://localhost:9000/v1",
+            api_key="none",
+            model="meta-llama/Llama-3-70B",
+        )
+        reg = ModelRegistry(
+            models={"primary": primary, "fallback": fallback},
+            default="primary",
+            fallback=["fallback"],
+        )
+        session._registry = reg
+        session._model_alias = "primary"
+
+        # Primary alias → gets Gemma workaround
+        result_primary = session._provider_extra_params()
+        assert result_primary is not None
+        assert result_primary["skip_special_tokens"] is False
+
+        # Fallback alias → no compat, just base kwargs
+        result_fallback = session._provider_extra_params(model_alias="fallback")
+        assert result_fallback == {"chat_template_kwargs": {"reasoning_effort": "medium"}}
+        assert "skip_special_tokens" not in result_fallback

tests/test_settings_registry.py

@@ -69,7 +69,7 @@ class TestValidateValueCoercion:
             validate_value("tools.timeout", None)
 
     def test_str(self):
-        assert validate_value("model.name", "gpt-5") == "gpt-5"
+        assert validate_value("model.default_alias", "gpt5-prod") == "gpt5-prod"
         assert validate_value("session.instructions", "be nice") == "be nice"
 
 
@@ -143,10 +143,10 @@ class TestSerializeDeserialize:
 
     def test_str_round_trip(self):
         v = "hello world"
-        assert deserialize_value("model.name", serialize_value(v)) == v
+        assert deserialize_value("model.default_alias", serialize_value(v)) == v
 
     def test_str_round_trip_empty(self):
-        assert deserialize_value("model.name", serialize_value("")) == ""
+        assert deserialize_value("model.default_alias", serialize_value("")) == ""
 
 
 # ---------------------------------------------------------------------------

turnstone/__init__.py

@@ -1,3 +1,3 @@
 """turnstone - Multi-node AI orchestration platform with tool use, agent routing, and cluster simulation."""
 
-__version__ = "1.3.0a3"
+__version__ = "1.4.0a2"

turnstone/api/console_schemas.py

@@ -812,6 +812,9 @@ class ModelDefinitionInfo(BaseModel):
     context_window: int = 32768
     capabilities: str = "{}"
     enabled: bool = True
+    temperature: float | None = None
+    max_tokens: int | None = None
+    reasoning_effort: str | None = None
     source: str = ""
     created_by: str = ""
     created: str = ""
@@ -827,6 +830,9 @@ class CreateModelDefinitionRequest(BaseModel):
     context_window: int = 32768
     capabilities: dict[str, Any] = Field(default_factory=dict)
     enabled: bool = True
+    temperature: float | None = None
+    max_tokens: int | None = None
+    reasoning_effort: str | None = None
 
 
 class UpdateModelDefinitionRequest(BaseModel):
@@ -838,6 +844,9 @@ class UpdateModelDefinitionRequest(BaseModel):
     context_window: int | None = None
     capabilities: dict[str, Any] | None = None
     enabled: bool | None = None
+    temperature: float | None = None
+    max_tokens: int | None = None
+    reasoning_effort: str | None = None
 
 
 class ListModelDefinitionsResponse(BaseModel):

turnstone/bootstrap.py

@@ -76,8 +76,9 @@ For commercial providers (OpenAI, Anthropic-via-proxy), use the real key.
 - `TAVILY_API_KEY` — Web search API key (optional)
 
 ### Database
-- `DB_BACKEND` — `sqlite` (default) or `postgresql`
-- `DATABASE_URL` — PostgreSQL connection string (production only)
+- `TURNSTONE_DB_BACKEND` — `sqlite` (default) or `postgresql`
+- `TURNSTONE_DB_URL` — PostgreSQL connection URL (production only), \
+e.g. `postgresql+psycopg://turnstone:<password>@postgres:5432/turnstone`
 - `POSTGRES_USER` — PostgreSQL username (default: turnstone)
 - `POSTGRES_PASSWORD` — PostgreSQL password (required for production)
 
@@ -184,7 +185,7 @@ exact commands to run next (e.g., `docker compose --profile production up -d` th
 - If `compose.yaml` is missing, call `write_compose` before anything else. \
 The compose file uses pre-built images from ghcr.io — no local Docker build is needed.
 - If an existing .env is detected, summarize what's configured and ask what to change.
-- The `DATABASE_URL` for docker compose internal networking uses the hostname `postgres` \
+- The `TURNSTONE_DB_URL` for docker compose internal networking uses the hostname `postgres` \
 (e.g., `postgresql+psycopg://turnstone:<password>@postgres:5432/turnstone`).
 - For local LLM backends (vLLM, llama.cpp, Ollama, etc.), set `OPENAI_API_KEY=dummy` in the \
 .env file — local servers typically don't require authentication. The `LLM_BASE_URL` should \

turnstone/console/server.py

@@ -1318,8 +1318,11 @@ async def _lifespan(app: Starlette) -> AsyncGenerator[None, None]:
         try:
             if not tls_mgr.ca_initialized:
                 await tls_mgr.init_ca()
-            hostname = socket.getfqdn()
+            hostname = socket.gethostname()
+            fqdn = socket.getfqdn()
             cert_hostnames = [hostname, "localhost", "127.0.0.1"]
+            if fqdn != hostname:
+                cert_hostnames.append(fqdn)
             extra_sans = os.environ.get("TURNSTONE_TLS_SANS", "")
             if extra_sans:
                 cert_hostnames.extend(s.strip() for s in extra_sans.split(",") if s.strip())
@@ -5232,6 +5235,9 @@ async def admin_import_mcp_config(request: Request) -> JSONResponse:
 
 _MODEL_ALIAS_RE = re.compile(r"^[a-zA-Z0-9._-]+$")
 _MODEL_PROVIDERS = frozenset({"openai", "anthropic", "openai-compatible", "google"})
+_REASONING_EFFORT_CHOICES = frozenset(
+    {"", "none", "minimal", "low", "medium", "high", "xhigh", "max"}
+)
 # Keep in sync with turnstone.core.providers._google.GOOGLE_DEFAULT_BASE_URL
 _PROVIDER_DEFAULT_URLS: dict[str, str] = {
     "openai": "https://api.openai.com/v1",
@@ -5344,12 +5350,18 @@ async def admin_list_model_definitions(request: Request) -> JSONResponse:
         model_name = ""
         provider = "openai"
         context_window = 0
+        cfg_temperature = None
+        cfg_max_tokens = None
+        cfg_reasoning_effort = None
         for node_models in node_statuses.values():
             nm = node_models.get(alias)
             if nm:
                 model_name = nm.get("model", "")
                 provider = nm.get("provider", "openai")
                 context_window = nm.get("context_window", 0)
+                cfg_temperature = nm.get("temperature")
+                cfg_max_tokens = nm.get("max_tokens")
+                cfg_reasoning_effort = nm.get("reasoning_effort")
                 break
         result.append(
             {
@@ -5362,6 +5374,9 @@ async def admin_list_model_definitions(request: Request) -> JSONResponse:
                 "context_window": context_window,
                 "capabilities": "{}",
                 "enabled": True,
+                "temperature": cfg_temperature,
+                "max_tokens": cfg_max_tokens,
+                "reasoning_effort": cfg_reasoning_effort,
                 "source": "config",
                 "created_by": "",
                 "created": "",
@@ -5451,6 +5466,36 @@ async def admin_create_model_definition(request: Request) -> JSONResponse:
     capabilities = json.dumps(caps) if isinstance(caps, dict) else "{}"
     enabled = bool(body.get("enabled", True))
 
+    # Per-model sampling overrides (None = use global default)
+    temperature: float | None = None
+    if body.get("temperature") is not None:
+        try:
+            temperature = float(body["temperature"])
+        except (ValueError, TypeError):
+            return JSONResponse({"error": "temperature must be a number"}, status_code=400)
+        if not 0.0 <= temperature <= 2.0:
+            return JSONResponse(
+                {"error": "temperature must be between 0.0 and 2.0"}, status_code=400
+            )
+    max_tokens: int | None = None
+    if body.get("max_tokens") is not None:
+        try:
+            max_tokens = int(body["max_tokens"])
+        except (ValueError, TypeError):
+            return JSONResponse({"error": "max_tokens must be an integer"}, status_code=400)
+        if max_tokens < 1:
+            return JSONResponse({"error": "max_tokens must be >= 1"}, status_code=400)
+    reasoning_effort: str | None = None
+    if body.get("reasoning_effort") is not None:
+        reasoning_effort = str(body["reasoning_effort"]).strip()
+        if reasoning_effort and reasoning_effort not in _REASONING_EFFORT_CHOICES:
+            return JSONResponse(
+                {"error": f"Invalid reasoning_effort: {reasoning_effort!r}"},
+                status_code=400,
+            )
+        if not reasoning_effort:
+            reasoning_effort = None
+
     storage.create_model_definition(
         definition_id=definition_id,
         alias=alias,
@@ -5462,6 +5507,9 @@ async def admin_create_model_definition(request: Request) -> JSONResponse:
         capabilities=capabilities,
         enabled=enabled,
         created_by=audit_uid,
+        temperature=temperature,
+        max_tokens=max_tokens,
+        reasoning_effort=reasoning_effort,
     )
 
     record_audit(
@@ -5570,6 +5618,50 @@ async def admin_update_model_definition(request: Request) -> JSONResponse:
     if "enabled" in body:
         updates["enabled"] = bool(body["enabled"])
 
+    # Per-model sampling overrides — explicit null clears to "use global default"
+    if "temperature" in body:
+        raw_temp = body["temperature"]
+        if raw_temp is None:
+            updates["temperature"] = None
+        else:
+            try:
+                temp_val = float(raw_temp)
+            except (ValueError, TypeError):
+                return JSONResponse({"error": "temperature must be a number"}, status_code=400)
+            if not 0.0 <= temp_val <= 2.0:
+                return JSONResponse(
+                    {"error": "temperature must be between 0.0 and 2.0"},
+                    status_code=400,
+                )
+            updates["temperature"] = temp_val
+    if "max_tokens" in body:
+        raw_mt = body["max_tokens"]
+        if raw_mt is None:
+            updates["max_tokens"] = None
+        else:
+            try:
+                mt_val = int(raw_mt)
+            except (ValueError, TypeError):
+                return JSONResponse({"error": "max_tokens must be an integer"}, status_code=400)
+            if mt_val < 1:
+                return JSONResponse({"error": "max_tokens must be >= 1"}, status_code=400)
+            updates["max_tokens"] = mt_val
+    if "reasoning_effort" in body:
+        raw_re = body["reasoning_effort"]
+        if raw_re is None:
+            updates["reasoning_effort"] = None
+        else:
+            re_val = str(raw_re).strip()
+            if not re_val:
+                updates["reasoning_effort"] = None
+            elif re_val not in _REASONING_EFFORT_CHOICES:
+                return JSONResponse(
+                    {"error": f"Invalid reasoning_effort: {re_val!r}"},
+                    status_code=400,
+                )
+            else:
+                updates["reasoning_effort"] = re_val
+
     if updates:
         storage.update_model_definition(definition_id, **updates)
 
@@ -7933,7 +8025,7 @@ def main() -> None:
     else:
         _advertise_host = args.host
         if _advertise_host in ("0.0.0.0", "::", ""):
-            _advertise_host = _socket.getfqdn()
+            _advertise_host = _socket.gethostname()
         console_url = f"http://{_advertise_host}:{args.port}"
     if auth_storage:
         try:

turnstone/console/static/admin.js

@@ -4447,6 +4447,24 @@ function _renderModels(items) {
       colAlias.appendChild(document.createTextNode(" "));
       colAlias.appendChild(defBadge);
     }
+    // Per-model sampling override indicators
+    var overrides = [];
+    if (m.temperature != null) overrides.push("temp=" + m.temperature);
+    if (m.max_tokens != null) overrides.push("max_tok=" + m.max_tokens);
+    if (m.reasoning_effort != null)
+      overrides.push("effort=" + m.reasoning_effort);
+    if (overrides.length) {
+      var ovrSpan = document.createElement("span");
+      ovrSpan.className = "model-overrides-hint";
+      ovrSpan.textContent = overrides.join(", ");
+      ovrSpan.title = "Per-model overrides (override global defaults)";
+      ovrSpan.setAttribute(
+        "aria-label",
+        "Per-model overrides: " + overrides.join(", "),
+      );
+      colAlias.appendChild(document.createElement("br"));
+      colAlias.appendChild(ovrSpan);
+    }
     row.appendChild(colAlias);
 
     // Model ID
@@ -4578,6 +4596,19 @@ function _renderModels(items) {
   });
 }
 
+function _isPlainObject(v) {
+  return v !== null && typeof v === "object" && !Array.isArray(v);
+}
+
+function _toggleThinkingParam() {
+  var mode = document.getElementById("model-thinking-mode").value;
+  var row = document.getElementById("model-thinking-param-row");
+  row.style.display = mode ? "" : "none";
+  // Set default when first enabling
+  var paramEl = document.getElementById("model-thinking-param");
+  if (mode && !paramEl.value) paramEl.value = "enable_thinking";
+}
+
 function showCreateModelModal() {
   _modelCreateTrigger = document.activeElement;
   var ov = document.getElementById("model-create-overlay");
@@ -4593,7 +4624,21 @@ function showCreateModelModal() {
   document.getElementById("model-api-key").value = "";
   document.getElementById("model-api-key").placeholder = "sk-...";
   document.getElementById("model-ctx-window").value = "0";
+  document.getElementById("model-temperature").value = "";
+  document.getElementById("model-max-tokens").value = "";
+  document.getElementById("model-reasoning-effort").value = "";
+  document.getElementById("model-server-type").value = "";
+  document.getElementById("model-thinking-mode").value = "";
+  document.getElementById("model-thinking-param").value = "";
+  document.getElementById("model-thinking-param-row").style.display = "none";
+  document.getElementById("model-extra-body").value = "";
   document.getElementById("model-capabilities").value = "";
+  // Clear validation error styling from prior submit attempts
+  ["model-extra-body", "model-capabilities"].forEach(function (id) {
+    var el = document.getElementById(id);
+    el.removeAttribute("aria-invalid");
+    el.style.borderColor = "";
+  });
   document.getElementById("model-enabled").checked = true;
   document.getElementById("model-detect-result").style.display = "none";
   document.getElementById("model-detect-btn").disabled = false;
@@ -4626,15 +4671,55 @@ function showEditModelModal(definitionId) {
         "\u2022\u2022\u2022 (leave blank to keep existing)";
       document.getElementById("model-ctx-window").value =
         m.context_window != null ? m.context_window : 0;
-      // Parse capabilities JSON for display
-      var caps = m.capabilities || "{}";
+      document.getElementById("model-temperature").value =
+        m.temperature != null ? m.temperature : "";
+      document.getElementById("model-max-tokens").value =
+        m.max_tokens != null ? m.max_tokens : "";
+      document.getElementById("model-reasoning-effort").value =
+        m.reasoning_effort != null ? m.reasoning_effort : "";
+      // Parse capabilities JSON and extract server_compat for structured fields
+      var capsObj = {};
       try {
-        caps = JSON.stringify(JSON.parse(caps), null, 2);
+        capsObj = JSON.parse(m.capabilities || "{}");
       } catch (e) {
-        /* keep raw */
+        /* keep empty */
       }
-      if (caps === "{}") caps = "";
-      document.getElementById("model-capabilities").value = caps;
+      // Defend against null/array/primitive values in the DB
+      if (!_isPlainObject(capsObj)) capsObj = {};
+      var sc = _isPlainObject(capsObj.server_compat)
+        ? capsObj.server_compat
+        : {};
+      // Only extract thinking_mode into the dropdown when the UI can
+      // represent it ("manual" or "").  Values like "adaptive" (Anthropic-
+      // only) stay in the raw capabilities JSON so they aren't silently
+      // lost on save.
+      var tmVal = capsObj.thinking_mode || "";
+      var tmRepresentable = tmVal === "" || tmVal === "manual";
+      if (tmRepresentable) {
+        document.getElementById("model-thinking-mode").value = tmVal;
+        document.getElementById("model-thinking-param").value =
+          capsObj.thinking_param || "";
+      } else {
+        document.getElementById("model-thinking-mode").value = "";
+        document.getElementById("model-thinking-param").value = "";
+      }
+      _toggleThinkingParam();
+      // Server compat: server_type and extra_body workarounds
+      document.getElementById("model-server-type").value = sc.server_type || "";
+      var eb = sc.extra_body || {};
+      var ebText = JSON.stringify(eb, null, 2);
+      document.getElementById("model-extra-body").value =
+        ebText === "{}" ? "" : ebText;
+      // Remove structured fields from capabilities display — only delete
+      // thinking_mode/thinking_param when the UI successfully captured them.
+      delete capsObj.server_compat;
+      if (tmRepresentable) {
+        delete capsObj.thinking_mode;
+        delete capsObj.thinking_param;
+      }
+      var capsText = JSON.stringify(capsObj, null, 2);
+      document.getElementById("model-capabilities").value =
+        capsText === "{}" ? "" : capsText;
       document.getElementById("model-enabled").checked = m.enabled !== false;
       _applyProviderDefaults();
     })
@@ -4667,15 +4752,65 @@ function submitCreateModel() {
     return;
   }
 
-  var capsText = document.getElementById("model-capabilities").value.trim();
+  var capsEl = document.getElementById("model-capabilities");
+  var capsText = capsEl.value.trim();
   var caps = {};
+  capsEl.removeAttribute("aria-invalid");
+  capsEl.style.borderColor = "";
   if (capsText) {
     try {
       caps = JSON.parse(capsText);
     } catch (e) {
+      capsEl.setAttribute("aria-invalid", "true");
+      capsEl.style.borderColor = "var(--red)";
       _showModelError("Invalid JSON in capabilities");
       return;
     }
+    if (!_isPlainObject(caps)) {
+      capsEl.setAttribute("aria-invalid", "true");
+      capsEl.style.borderColor = "var(--red)";
+      _showModelError(
+        "Capabilities must be a JSON object (not array or primitive)",
+      );
+      return;
+    }
+  }
+
+  // Thinking mode → capabilities (provider uses this to inject
+  // the correct chat_template_kwargs param automatically).
+  var thinkingMode = document.getElementById("model-thinking-mode").value;
+  if (thinkingMode) {
+    caps.thinking_mode = thinkingMode;
+    // Preserve thinking_param so Granite/DeepSeek "thinking" key
+    // isn't silently reverted to the default "enable_thinking".
+    var savedParam = document.getElementById("model-thinking-param").value;
+    if (savedParam) caps.thinking_param = savedParam;
+  }
+
+  // Build server_compat from structured fields
+  var serverCompat = {};
+  var serverType = document.getElementById("model-server-type").value;
+  if (serverType) serverCompat.server_type = serverType;
+  var ebEl = document.getElementById("model-extra-body");
+  var ebText = ebEl.value.trim();
+  ebEl.removeAttribute("aria-invalid");
+  ebEl.style.borderColor = "";
+  if (ebText) {
+    try {
+      var ebParsed = JSON.parse(ebText);
+      if (!_isPlainObject(ebParsed)) {
+        throw new Error("not an object");
+      }
+      serverCompat.extra_body = ebParsed;
+    } catch (e) {
+      ebEl.setAttribute("aria-invalid", "true");
+      ebEl.style.borderColor = "var(--red)";
+      _showModelError("Extra body params must be a JSON object");
+      return;
+    }
+  }
+  if (Object.keys(serverCompat).length > 0) {
+    caps.server_compat = serverCompat;
   }
 
   var form = {
@@ -4689,6 +4824,36 @@ function submitCreateModel() {
     enabled: document.getElementById("model-enabled").checked,
   };
 
+  // Per-model sampling overrides — null when empty (use global default)
+  var tempVal = document.getElementById("model-temperature").value.trim();
+  if (tempVal !== "") {
+    var t = parseFloat(tempVal);
+    if (isNaN(t) || t < 0 || t > 2) {
+      _showModelError("Temperature must be between 0 and 2");
+      return;
+    }
+    form.temperature = t;
+  } else {
+    form.temperature = null;
+  }
+  var mtVal = document.getElementById("model-max-tokens").value.trim();
+  if (mtVal !== "") {
+    var mt = parseInt(mtVal, 10);
+    if (isNaN(mt) || mt < 1) {
+      _showModelError("Max tokens must be at least 1");
+      return;
+    }
+    form.max_tokens = mt;
+  } else {
+    form.max_tokens = null;
+  }
+  var reVal = document.getElementById("model-reasoning-effort").value;
+  if (reVal !== "") {
+    form.reasoning_effort = reVal;
+  } else {
+    form.reasoning_effort = null;
+  }
+
   var apiKey = document.getElementById("model-api-key").value;
   if (apiKey) form.api_key = apiKey;
 
@@ -4838,6 +5003,52 @@ function detectModel() {
         resultDiv.appendChild(
           _detectResultLine("Server type: " + d.server_type),
         );
+        // Auto-fill server type if not already set and value is a known option
+        var stEl = document.getElementById("model-server-type");
+        var stOpts = Array.from(stEl.options).map(function (o) {
+          return o.value;
+        });
+        if (!stEl.value && stOpts.indexOf(d.server_type) !== -1)
+          stEl.value = d.server_type;
+      }
+      // Auto-fill capabilities from suggested profile
+      if (d.suggested_capabilities) {
+        var sc2 = d.suggested_capabilities;
+        var tmEl = document.getElementById("model-thinking-mode");
+        if (!tmEl.value && sc2.thinking_mode) {
+          tmEl.value = sc2.thinking_mode;
+        }
+        if (sc2.thinking_param) {
+          var tpEl = document.getElementById("model-thinking-param");
+          if (!tpEl.value) tpEl.value = sc2.thinking_param;
+        }
+        _toggleThinkingParam();
+      }
+      // Auto-fill server compat from suggested profile
+      if (d.suggested_server_compat) {
+        var ssc = d.suggested_server_compat;
+        var stEl2 = document.getElementById("model-server-type");
+        var stOpts2 = Array.from(stEl2.options).map(function (o) {
+          return o.value;
+        });
+        if (
+          !stEl2.value &&
+          ssc.server_type &&
+          stOpts2.indexOf(ssc.server_type) !== -1
+        )
+          stEl2.value = ssc.server_type;
+        if (ssc.extra_body) {
+          var ebEl2 = document.getElementById("model-extra-body");
+          if (!ebEl2.value.trim()) {
+            var ebJson = JSON.stringify(ssc.extra_body, null, 2);
+            if (ebJson !== "{}") ebEl2.value = ebJson;
+          }
+        }
+      }
+      if (d.suggested_capabilities || d.suggested_server_compat) {
+        resultDiv.appendChild(
+          _detectResultLine("\u2713 Compatibility profile suggested", "green"),
+        );
       }
       resultDiv.style.borderColor = "var(--green)";
     })
@@ -4931,6 +5142,11 @@ function _applyProviderDefaults() {
   if (!def) return;
   document.getElementById("model-base-url").placeholder = def.urlPlaceholder;
   document.getElementById("model-name").placeholder = def.modelPlaceholder;
+  // Server compat section only applies to local model servers
+  var scSection = document.getElementById("model-server-compat-section");
+  if (scSection) {
+    scSection.style.display = provider === "openai-compatible" ? "" : "none";
+  }
 }
 
 /* Populate the model name datalist with known model prefixes for the

turnstone/console/static/index.html

@@ -1551,6 +1551,42 @@ window.TURNSTONE_KB_SHORTCUTS = [
     <input type="password" id="model-api-key" placeholder="sk-..." autocomplete="off">
     <label for="model-ctx-window">Context Window <span style="font-weight:400;text-transform:none">(0 = auto-detect from model)</span></label>
     <input type="number" id="model-ctx-window" value="0" min="0">
+    <div class="modal-section-divider" role="separator">Sampling Defaults</div>
+    <label for="model-temperature">Temperature <span style="font-weight:400;text-transform:none">(empty = use global default)</span></label>
+    <input type="number" id="model-temperature" placeholder="Global default" step="0.1" min="0" max="2">
+    <label for="model-max-tokens">Max Tokens <span style="font-weight:400;text-transform:none">(empty = use global default)</span></label>
+    <input type="number" id="model-max-tokens" placeholder="Global default" min="1">
+    <label for="model-reasoning-effort">Reasoning Effort <span style="font-weight:400;text-transform:none">(empty = use global default)</span></label>
+    <select id="model-reasoning-effort">
+      <option value="">Global default</option>
+      <option value="none">none</option>
+      <option value="minimal">minimal</option>
+      <option value="low">low</option>
+      <option value="medium">medium</option>
+      <option value="high">high</option>
+      <option value="xhigh">xhigh</option>
+      <option value="max">max</option>
+    </select>
+    <div id="model-server-compat-section" style="display:none">
+    <div class="modal-section-divider" role="separator">Server Compatibility</div>
+    <label for="model-server-type">Server Type <span style="font-weight:400;text-transform:none">(auto-detected or manual)</span></label>
+    <select id="model-server-type">
+      <option value="">Auto / Unknown</option>
+      <option value="vllm">vLLM</option>
+      <option value="llama.cpp">llama.cpp</option>
+      <option value="openai-compatible">Other OpenAI-compatible</option>
+    </select>
+    <label for="model-thinking-mode">Thinking Mode <span style="font-weight:400;text-transform:none">(reasoning / chain-of-thought)</span></label>
+    <select id="model-thinking-mode" onchange="_toggleThinkingParam()">
+      <option value="">None</option>
+      <option value="manual">Enabled</option>
+    </select>
+    <div id="model-thinking-param-row" style="display:none">
+      <label for="model-thinking-param" style="font-size:11px">Template param name <span style="font-weight:400;text-transform:none">(Granite/DeepSeek use "thinking")</span></label>
+      <input type="text" id="model-thinking-param" value="enable_thinking" placeholder="enable_thinking" style="font-family:var(--font-mono);font-size:11px"></div>
+    <label for="model-extra-body">Extra body params <span style="font-weight:400;text-transform:none">(JSON, merged into every request)</span></label>
+    <textarea id="model-extra-body" rows="2" placeholder='{"skip_special_tokens": false}' style="font-family:var(--font-mono);font-size:11px"></textarea>
+    </div>
     <label for="model-capabilities">Capabilities <span style="font-weight:400;text-transform:none">(JSON)</span></label>
     <textarea id="model-capabilities" rows="3" placeholder='{"supports_vision": true}' style="font-family:var(--font-mono);font-size:11px"></textarea>
     <div style="display:flex;gap:20px;margin-top:14px">

turnstone/console/static/style.css

@@ -2471,6 +2471,12 @@ h3.skill-spec-heading { font-size: inherit; margin-block: 0; }
 .model-provider-google{color:var(--green);border-color:rgba(52,211,153,.2)}
 .model-provider-compat{color:var(--fg-dim);border-color:var(--border-strong)}
 
+/* Per-model override hints */
+.model-overrides-hint{font-size:10px;color:var(--fg-dim);font-family:var(--font-mono);letter-spacing:.02em}
+
+/* Modal section divider for field groups */
+.modal-section-divider{font-family:var(--font-display);font-size:9px;font-weight:600;text-transform:uppercase;letter-spacing:.1em;color:var(--fg-dim);margin:16px 0 4px;padding-top:12px;border-top:1px solid var(--border)}
+
 /* Model source badge */
 .scope-db{color:var(--blue);border-color:rgba(56,189,248,.2)}
 

turnstone/core/config.py

@@ -266,3 +266,21 @@ def warn_migrated_settings() -> None:
                 config_key,
                 key,
             )
+
+    # Warn about removed settings whose config.toml keys are now ignored.
+    # model.name → use model definitions (Models tab); model.context_window
+    # → set per-model in the Models tab (context_window column).
+    removed_settings: dict[str, str] = {
+        "model.name": "Use model definitions in the Models tab instead.",
+        "model.context_window": "Set per-model in the Models tab instead.",
+    }
+    for key, guidance in removed_settings.items():
+        section, config_key = key.split(".", 1)
+        section_data = cfg.get(section, {})
+        if isinstance(section_data, dict) and config_key in section_data:
+            log.warning(
+                "config.toml [%s] %s has been removed and will be ignored. %s",
+                section,
+                config_key,
+                guidance,
+            )

turnstone/core/env.py

@@ -73,7 +73,7 @@ _EXPLICIT_SCRUB: frozenset[str] = frozenset(
         "AZURE_CLIENT_SECRET",
         "GCP_SERVICE_ACCOUNT_KEY",
         "GOOGLE_APPLICATION_CREDENTIALS",
-        "DATABASE_URL",
+        "DATABASE_URL",  # conventional name (Heroku, Railway, etc.) — kept for defence-in-depth
         "TURNSTONE_DB_URL",
     }
 )

turnstone/core/model_registry.py

@@ -35,6 +35,13 @@ class ModelConfig:
     provider: str = "openai"
     capabilities: dict[str, Any] = field(default_factory=dict)
     source: str = ""  # "config", "db", or "" (CLI default)
+    # Per-model sampling overrides (None = use global default from ConfigStore)
+    temperature: float | None = None
+    max_tokens: int | None = None
+    reasoning_effort: str | None = None
+    # Server compatibility settings for openai-compatible backends.
+    # Populated from capabilities["server_compat"] during load.
+    server_compat: dict[str, Any] = field(default_factory=dict)
 
 
 # ---------------------------------------------------------------------------
@@ -262,12 +269,20 @@ def load_model_registry(
                             caps = parsed
                     except (_json.JSONDecodeError, TypeError):
                         pass  # falls back to empty capabilities
+                # Extract server_compat from capabilities (namespaced key)
+                row_server_compat = caps.pop("server_compat", {})
+                if not isinstance(row_server_compat, dict):
+                    row_server_compat = {}
                 row_base_url = _resolve_env_vars(row.get("base_url", ""))
                 row_provider = _resolve_openai_provider(row.get("provider", "openai"), row_base_url)
                 row_model = row["model"]
                 # 0 = auto-detect: inherit CLI-detected context_window,
                 # same fallback chain as config.toml models
                 row_ctx = row.get("context_window", 0) or context_window
+                # Per-model sampling overrides (None = use global default)
+                row_temperature = row.get("temperature")
+                row_max_tokens = row.get("max_tokens")
+                row_reasoning_effort = row.get("reasoning_effort")
                 configs[alias] = ModelConfig(
                     alias=alias,
                     base_url=row_base_url,
@@ -277,6 +292,12 @@ def load_model_registry(
                     provider=row_provider,
                     capabilities=caps,
                     source="db",
+                    temperature=float(row_temperature) if row_temperature is not None else None,
+                    max_tokens=int(row_max_tokens) if row_max_tokens is not None else None,
+                    reasoning_effort=row_reasoning_effort
+                    if row_reasoning_effort is not None
+                    else None,
+                    server_compat=row_server_compat,
                 )
         except Exception:
             log.warning("Failed to load model definitions from storage", exc_info=True)
@@ -290,6 +311,44 @@ def load_model_registry(
             log.warning("Model entry '%s' has no model name, skipping", alias)
             continue
         entry_base_url = _resolve_env_vars(entry.get("base_url", base_url))
+        # Per-model sampling overrides from config.toml — invalid values
+        # are logged and treated as None (inherit global default).
+        entry_temp: float | None = None
+        entry_max_tokens: int | None = None
+        entry_effort: str | None = None
+        raw_temp = entry.get("temperature")
+        if raw_temp is not None:
+            try:
+                entry_temp = float(raw_temp)
+                if not 0.0 <= entry_temp <= 2.0:
+                    log.warning(
+                        "Model '%s' temperature %.2f out of range [0, 2], ignoring",
+                        alias,
+                        entry_temp,
+                    )
+                    entry_temp = None
+            except (ValueError, TypeError):
+                log.warning("Model '%s' has invalid temperature %r, ignoring", alias, raw_temp)
+        raw_mt = entry.get("max_tokens")
+        if raw_mt is not None:
+            try:
+                entry_max_tokens = int(raw_mt)
+                if entry_max_tokens < 1:
+                    log.warning("Model '%s' max_tokens %d < 1, ignoring", alias, entry_max_tokens)
+                    entry_max_tokens = None
+            except (ValueError, TypeError):
+                log.warning("Model '%s' has invalid max_tokens %r, ignoring", alias, raw_mt)
+        raw_effort = entry.get("reasoning_effort")
+        if raw_effort is not None:
+            entry_effort = str(raw_effort)
+        entry_caps = (
+            dict(entry.get("capabilities", {}))
+            if isinstance(entry.get("capabilities"), dict)
+            else {}
+        )
+        entry_server_compat = entry_caps.pop("server_compat", {})
+        if not isinstance(entry_server_compat, dict):
+            entry_server_compat = {}
         configs[alias] = ModelConfig(
             alias=alias,
             base_url=entry_base_url,
@@ -297,10 +356,12 @@ def load_model_registry(
             model=model_name,
             context_window=entry.get("context_window", context_window),
             provider=_resolve_openai_provider(entry.get("provider", "openai"), entry_base_url),
-            capabilities=entry.get("capabilities", {})
-            if isinstance(entry.get("capabilities"), dict)
-            else {},
+            capabilities=entry_caps,
             source="config",
+            temperature=entry_temp,
+            max_tokens=entry_max_tokens,
+            reasoning_effort=entry_effort,
+            server_compat=entry_server_compat,
         )
 
     # 3. Ensure a "default" entry from CLI args (only if not already defined
@@ -596,3 +657,12 @@ def _detect_openai_compat(
         result["server_type"] = "vllm"
     else:
         result["server_type"] = "openai-compatible"
+
+    # Suggest capabilities and server compat based on detected server_type
+    from turnstone.core.server_compat import suggest_profile
+
+    suggested = suggest_profile(result.get("server_type", ""), model_id)
+    if suggested.get("capabilities"):
+        result["suggested_capabilities"] = suggested["capabilities"]
+    if suggested.get("server_compat"):
+        result["suggested_server_compat"] = suggested["server_compat"]

turnstone/core/providers/_anthropic.py

@@ -568,9 +568,10 @@ class AnthropicProvider:
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
         cancel_ref: list[Any] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> Iterator[StreamChunk]:
         _ensure_anthropic()
-        caps = self.get_capabilities(model)
+        caps = capabilities or self.get_capabilities(model)
         system_prompt, converted_msgs = self._convert_messages(messages)
         kwargs = self._build_thinking_and_kwargs(
             caps,
@@ -771,9 +772,10 @@ class AnthropicProvider:
         reasoning_effort: str = "medium",
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> CompletionResult:
         _ensure_anthropic()
-        caps = self.get_capabilities(model)
+        caps = capabilities or self.get_capabilities(model)
         system_prompt, converted_msgs = self._convert_messages(messages)
         kwargs = self._build_thinking_and_kwargs(
             caps,

turnstone/core/providers/_openai_chat.py

@@ -108,6 +108,52 @@ class OpenAIChatCompletionsProvider:
         kwargs["web_search_options"] = {}
         return tools
 
+    # -- thinking mode -------------------------------------------------------
+
+    @staticmethod
+    def _apply_thinking_mode(
+        extra_body: dict[str, Any],
+        caps: ModelCapabilities,
+    ) -> None:
+        """Inject thinking-mode params into *extra_body* based on capabilities.
+
+        When ``caps.thinking_mode`` is ``"manual"`` or ``"adaptive"``, sets
+        the model-family-specific key (``caps.thinking_param``, e.g.
+        ``"enable_thinking"`` or ``"thinking"``) to ``True`` inside
+        ``extra_body["chat_template_kwargs"]``.
+
+        Does nothing when thinking mode is ``"none"`` or the key is already
+        present (operator override via ``extra_body`` takes precedence).
+        """
+        if caps.thinking_mode == "none":
+            return
+        ctk = extra_body.get("chat_template_kwargs")
+        if not isinstance(ctk, dict):
+            ctk = {}
+            extra_body["chat_template_kwargs"] = ctk
+        if caps.thinking_param not in ctk:
+            ctk[caps.thinking_param] = True
+
+    def _finalize_extra_body(
+        self,
+        extra_params: dict[str, Any] | None,
+        caps: ModelCapabilities,
+    ) -> dict[str, Any] | None:
+        """Build the final ``extra_body``, injecting thinking params if needed.
+
+        Returns ``None`` when the result would be empty (no extra_body needed).
+        Shallow-copies *extra_params* and its ``chat_template_kwargs`` so the
+        caller's dict is never mutated.
+        """
+        eb: dict[str, Any] = {}
+        if extra_params:
+            eb = dict(extra_params)
+            ctk = eb.get("chat_template_kwargs")
+            if isinstance(ctk, dict):
+                eb["chat_template_kwargs"] = dict(ctk)
+        self._apply_thinking_mode(eb, caps)
+        return eb or None
+
     # -- streaming -----------------------------------------------------------
 
     def create_streaming(
@@ -123,8 +169,9 @@ class OpenAIChatCompletionsProvider:
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
         cancel_ref: list[Any] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> Iterator[StreamChunk]:
-        caps = self.get_capabilities(model)
+        caps = capabilities or self.get_capabilities(model)
         messages = self._prepare_messages(messages)
         kwargs: dict[str, Any] = {
             "model": model,
@@ -139,8 +186,9 @@ class OpenAIChatCompletionsProvider:
         tools = apply_tool_search(caps, tools, deferred_names)
         if tools:
             kwargs["tools"] = tools
-        if extra_params:
-            kwargs["extra_body"] = extra_params
+        extra_body = self._finalize_extra_body(extra_params, caps)
+        if extra_body:
+            kwargs["extra_body"] = extra_body
 
         log.debug(
             "openai.chat.request",
@@ -250,8 +298,9 @@ class OpenAIChatCompletionsProvider:
         reasoning_effort: str = "medium",
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> CompletionResult:
-        caps = self.get_capabilities(model)
+        caps = capabilities or self.get_capabilities(model)
         messages = self._prepare_messages(messages)
         kwargs: dict[str, Any] = {
             "model": model,
@@ -265,8 +314,9 @@ class OpenAIChatCompletionsProvider:
         tools = apply_tool_search(caps, tools, deferred_names)
         if tools:
             kwargs["tools"] = tools
-        if extra_params:
-            kwargs["extra_body"] = extra_params
+        extra_body = self._finalize_extra_body(extra_params, caps)
+        if extra_body:
+            kwargs["extra_body"] = extra_body
 
         log.debug(
             "openai.chat.request",

turnstone/core/providers/_openai_responses.py

@@ -223,9 +223,10 @@ class OpenAIResponsesProvider:
         temperature: float,
         reasoning_effort: str,
         deferred_names: frozenset[str] | None,
+        capabilities: ModelCapabilities | None = None,
     ) -> dict[str, Any]:
         """Build the kwargs dict for ``client.responses.create/stream``."""
-        caps = self.get_capabilities(model)
+        caps = capabilities or self.get_capabilities(model)
 
         instructions, input_items = self._convert_messages(messages)
         tools = apply_tool_search(caps, tools, deferred_names)
@@ -276,6 +277,7 @@ class OpenAIResponsesProvider:
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
         cancel_ref: list[Any] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> Iterator[StreamChunk]:
         if extra_params:
             log.debug("openai.responses: extra_params ignored (not supported by Responses API)")
@@ -287,6 +289,7 @@ class OpenAIResponsesProvider:
             temperature,
             reasoning_effort,
             deferred_names,
+            capabilities=capabilities,
         )
         kwargs["stream"] = True
 
@@ -455,6 +458,7 @@ class OpenAIResponsesProvider:
         reasoning_effort: str = "medium",
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> CompletionResult:
         if extra_params:
             log.debug("openai.responses: extra_params ignored (not supported by Responses API)")
@@ -466,6 +470,7 @@ class OpenAIResponsesProvider:
             temperature,
             reasoning_effort,
             deferred_names,
+            capabilities=capabilities,
         )
 
         log.debug(

turnstone/core/providers/_protocol.py

@@ -74,6 +74,11 @@ class ModelCapabilities:
     supports_tools: bool = True
     token_param: str = "max_completion_tokens"
     thinking_mode: str = "none"  # "none" | "manual" | "adaptive"
+    # For openai-compatible servers: the chat_template_kwargs key that
+    # toggles thinking (e.g. "enable_thinking" for Gemma/Qwen,
+    # "thinking" for Granite/DeepSeek).  Ignored when thinking_mode is
+    # "none" or by providers that handle thinking natively (Anthropic).
+    thinking_param: str = "enable_thinking"
     supports_effort: bool = False
     effort_levels: tuple[str, ...] = ()
     reasoning_effort_values: tuple[str, ...] = ()
@@ -127,9 +132,16 @@ class LLMProvider(Protocol):
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
         cancel_ref: list[Any] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> Iterator[StreamChunk]:
         """Create a streaming request, yielding normalized StreamChunks.
 
+        If *capabilities* is provided the provider uses it instead of
+        calling ``get_capabilities(model)`` internally.  This lets the
+        session pass config-merged capabilities so that overrides from
+        the model registry (e.g. ``thinking_mode``, ``token_param``)
+        are respected.
+
         If *cancel_ref* is provided the provider appends the underlying SDK
         stream object (which has a ``.close()`` method) before yielding the
         first chunk.  The caller can then close it from another thread to
@@ -149,6 +161,7 @@ class LLMProvider(Protocol):
         reasoning_effort: str = "medium",
         extra_params: dict[str, Any] | None = None,
         deferred_names: frozenset[str] | None = None,
+        capabilities: ModelCapabilities | None = None,
     ) -> CompletionResult:
         """Create a non-streaming request, returning a normalized result."""
         ...

turnstone/core/server_compat.py

@@ -0,0 +1,207 @@
+"""Server compatibility profiles for OpenAI-compatible backends.
+
+Different local model servers (vLLM, llama.cpp, SGLang) need different
+request shaping.  This module separates two concerns:
+
+1. **Model capabilities** — ``thinking_mode`` and ``thinking_param`` are
+   properties of the *model* (Gemma thinks, Llama doesn't).  These go
+   into the ``capabilities`` dict and flow through ``ModelCapabilities``
+   so the provider can act on them (just like Anthropic's thinking mode).
+
+2. **Server workarounds** — ``extra_body`` overrides like
+   ``skip_special_tokens=false`` are properties of the *server* (vLLM
+   bug workaround).  These stay in ``server_compat`` and get merged
+   into the request's ``extra_body`` at call time.
+
+Profiles are *suggestions* only.  The admin UI auto-fills them on
+Detect; the operator has final say, and the stored DB config is what
+actually gets used at request time.
+"""
+
+from __future__ import annotations
+
+import copy
+from typing import Any
+
+# ---------------------------------------------------------------------------
+# Profile suggestions
+# ---------------------------------------------------------------------------
+
+# Each profile has two optional parts:
+#   "capabilities" — merged into the model's capabilities dict (thinking_mode etc.)
+#   "server_compat" — stored as server_compat (extra_body workarounds)
+
+_PROFILES: dict[str, dict[str, Any]] = {
+    "vllm-gemma-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "enable_thinking",
+        },
+        "server_compat": {
+            "server_type": "vllm",
+            # Workaround: vLLM strips special tokens before the Gemma4
+            # reasoning parser sees them.  skip_special_tokens=false
+            # preserves <|channel> / <channel|> markers so reasoning
+            # content is extracted correctly.
+            "extra_body": {"skip_special_tokens": False},
+        },
+    },
+    "vllm-qwen-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "enable_thinking",
+        },
+        "server_compat": {
+            "server_type": "vllm",
+        },
+    },
+    "vllm-granite-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "thinking",
+        },
+        "server_compat": {
+            "server_type": "vllm",
+        },
+    },
+    "vllm-deepseek-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "thinking",
+        },
+        "server_compat": {
+            "server_type": "vllm",
+        },
+    },
+    "vllm-holo-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "enable_thinking",
+        },
+        "server_compat": {
+            "server_type": "vllm",
+        },
+    },
+    "vllm": {
+        "server_compat": {
+            "server_type": "vllm",
+        },
+    },
+    "llama.cpp": {
+        "server_compat": {
+            "server_type": "llama.cpp",
+        },
+    },
+    "llama.cpp-thinking": {
+        "capabilities": {
+            "thinking_mode": "manual",
+            "thinking_param": "enable_thinking",
+        },
+        "server_compat": {
+            "server_type": "llama.cpp",
+            # llama.cpp uses reasoning_format (top-level request param) to
+            # extract thinking into the reasoning_content response field.
+            # "auto" lets the server decide based on the model's template;
+            # "deepseek" forces extraction for all thinking models.
+            "extra_body": {"reasoning_format": "auto"},
+        },
+    },
+    "sglang": {
+        "server_compat": {
+            "server_type": "sglang",
+        },
+    },
+}
+
+# Model-family → profile key mapping.  Checked in order; first match wins.
+_VLLM_MODEL_PROFILES: list[tuple[str, str]] = [
+    ("gemma-4", "vllm-gemma-thinking"),
+    ("gemma-3", "vllm-gemma-thinking"),
+    ("gemma4", "vllm-gemma-thinking"),
+    ("gemma3", "vllm-gemma-thinking"),
+    ("qwen3", "vllm-qwen-thinking"),
+    ("qwq", "vllm-qwen-thinking"),
+    ("granite-3", "vllm-granite-thinking"),
+    ("granite3", "vllm-granite-thinking"),
+    ("deepseek-r1", "vllm-deepseek-thinking"),
+    ("holo2", "vllm-holo-thinking"),
+]
+
+# llama.cpp model-family → profile key mapping.
+_LLAMA_CPP_MODEL_PROFILES: list[tuple[str, str]] = [
+    ("gemma-4", "llama.cpp-thinking"),
+    ("gemma-3", "llama.cpp-thinking"),
+    ("gemma4", "llama.cpp-thinking"),
+    ("gemma3", "llama.cpp-thinking"),
+    ("qwen3", "llama.cpp-thinking"),
+    ("qwq", "llama.cpp-thinking"),
+    ("deepseek-r1", "llama.cpp-thinking"),
+]
+
+
+# ---------------------------------------------------------------------------
+# Public API
+# ---------------------------------------------------------------------------
+
+
+def suggest_profile(server_type: str, model_id: str) -> dict[str, Any]:
+    """Suggest capabilities and server compat based on server type and model.
+
+    Returns a dict with optional ``"capabilities"`` and ``"server_compat"``
+    keys.  Empty dict when no special settings are needed.
+    """
+    profile_key: str | None = None
+    model_lower = (model_id or "").lower()
+    if server_type == "vllm":
+        for substring, key in _VLLM_MODEL_PROFILES:
+            if substring in model_lower:
+                profile_key = key
+                break
+        if profile_key is None:
+            profile_key = "vllm"
+    elif server_type == "llama.cpp":
+        for substring, key in _LLAMA_CPP_MODEL_PROFILES:
+            if substring in model_lower:
+                profile_key = key
+                break
+        if profile_key is None:
+            profile_key = "llama.cpp"
+    elif server_type in _PROFILES:
+        profile_key = server_type
+
+    if profile_key is None:
+        return {}
+    return copy.deepcopy(_PROFILES[profile_key])
+
+
+def merge_server_compat(
+    base_chat_template_kwargs: dict[str, Any],
+    server_compat: dict[str, Any],
+) -> dict[str, Any]:
+    """Build the ``extra_body`` dict by merging server compat into base kwargs.
+
+    *base_chat_template_kwargs* always contains at least ``reasoning_effort``.
+    *server_compat* comes from ``ModelConfig.server_compat``.
+
+    Note: thinking-mode params (``enable_thinking``, ``thinking``) are **not**
+    merged here — the provider handles those via ``ModelCapabilities``.
+    This function only merges server workarounds from ``extra_body``.
+
+    Returns the complete dict to pass as ``extra_body`` to the OpenAI client.
+    """
+    extra: dict[str, Any] = {"chat_template_kwargs": dict(base_chat_template_kwargs)}
+
+    # Merge top-level extra_body overrides (skip_special_tokens, etc.)
+    compat_eb = server_compat.get("extra_body")
+    if isinstance(compat_eb, dict):
+        for key, value in compat_eb.items():
+            if key == "chat_template_kwargs":
+                # Deep-merge: operator values in extra_body win over the
+                # base dict (which has reasoning_effort).  This lets
+                # operators intentionally extend chat_template_kwargs.
+                if isinstance(value, dict):
+                    extra["chat_template_kwargs"].update(value)
+                continue
+            extra[key] = value
+
+    return extra

turnstone/core/session.py

@@ -1448,21 +1448,50 @@ class ChatSession:
         self,
         reasoning_effort: str | None = None,
         provider: LLMProvider | None = None,
+        model_alias: str | None = None,
     ) -> dict[str, Any] | None:
         """Build provider-specific extra parameters.
 
         ``chat_template_kwargs`` is only meaningful for local model servers
         (``openai-compatible``).  Commercial OpenAI rejects it as an unknown
         parameter, and handles ``reasoning_effort`` natively.
+
+        Merges server workarounds (``skip_special_tokens``, etc.) from
+        ``ModelConfig.server_compat`` into the request's ``extra_body``.
+        Thinking-mode params (``enable_thinking``) are handled separately
+        by the provider based on ``ModelCapabilities.thinking_mode``.
+
+        *model_alias* controls which model config supplies server compat
+        settings.  When ``None``, defaults to the session's primary alias.
         """
+        from turnstone.core.server_compat import merge_server_compat
+
         prov = provider or self._provider
         if prov.provider_name == "openai-compatible":
-            kwargs = dict(self._chat_template_kwargs_base)
+            ctk_base = dict(self._chat_template_kwargs_base)
             if reasoning_effort:
-                kwargs["reasoning_effort"] = reasoning_effort
-            return {"chat_template_kwargs": kwargs}
+                ctk_base["reasoning_effort"] = reasoning_effort
+            return merge_server_compat(
+                ctk_base,
+                self._get_server_compat(model_alias),
+            )
         return None
 
+    def _get_server_compat(self, model_alias: str | None = None) -> dict[str, Any]:
+        """Get server compatibility settings from a model config.
+
+        *model_alias* selects the config to read.  Falls back to the
+        session's primary alias when ``None``.
+        """
+        alias = model_alias or self._model_alias
+        if self._registry and alias:
+            try:
+                cfg = self._registry.get_config(alias)
+                return dict(cfg.server_compat)
+            except (ValueError, KeyError):
+                pass
+        return {}
+
     def _utility_completion(
         self,
         messages: list[dict[str, Any]],
@@ -1488,6 +1517,7 @@ class ChatSession:
             temperature=temperature,
             reasoning_effort=reasoning_effort,
             extra_params=self._provider_extra_params(reasoning_effort=reasoning_effort),
+            capabilities=caps,
         )
 
     # -- tool search helpers --------------------------------------------------
@@ -1622,8 +1652,16 @@ class ChatSession:
         try:
             fb_client, fb_model, _ = self._registry.resolve(alias)
             fb_provider = self._registry.get_provider(alias)
+            fb_caps = self._resolve_capabilities(fb_provider, fb_model, alias)
             self.ui.on_info(f"[Primary model failed, falling back to {alias}]")
-            result = self._try_stream(fb_client, fb_model, msgs, provider=fb_provider)
+            result = self._try_stream(
+                fb_client,
+                fb_model,
+                msgs,
+                provider=fb_provider,
+                capabilities=fb_caps,
+                model_alias=alias,
+            )
             if fb_tracker:
                 fb_tracker.record_success()
             return result
@@ -1639,6 +1677,8 @@ class ChatSession:
         model: str,
         msgs: list[dict[str, Any]],
         provider: LLMProvider | None = None,
+        capabilities: ModelCapabilities | None = None,
+        model_alias: str | None = None,
     ) -> Iterator[StreamChunk]:
         """Attempt a streaming API call with retries on transient errors."""
         prov = provider or self._provider
@@ -1670,9 +1710,12 @@ class ChatSession:
                     max_tokens=self.max_tokens,
                     temperature=self.temperature,
                     reasoning_effort=self.reasoning_effort,
-                    extra_params=self._provider_extra_params(provider=prov),
+                    extra_params=self._provider_extra_params(
+                        provider=prov, model_alias=model_alias
+                    ),
                     deferred_names=self._get_deferred_names(),
                     cancel_ref=self._cancel_ref,
+                    capabilities=capabilities or self._get_capabilities(prov, model),
                 )
             except Exception as e:
                 ename = type(e).__name__
@@ -5381,10 +5424,12 @@ class ChatSession:
         if not agent_caps.supports_web_search and not self._resolve_search_client():
             tools = _without_tool(tools, "web_search")
 
-        # Build extra params for agent calls
+        # Build extra params for agent calls — resolve server compat from the
+        # agent's own model alias, not the session's primary model.
         agent_extra = self._provider_extra_params(
             reasoning_effort=reasoning_effort,
             provider=agent_provider,
+            model_alias=agent_alias,
         )
 
         def _api_call(
@@ -5403,6 +5448,7 @@ class ChatSession:
                         temperature=self.temperature,
                         reasoning_effort=reasoning_effort or self.reasoning_effort,
                         extra_params=agent_extra,
+                        capabilities=agent_caps,
                     )
                 except Exception as e:
                     ename = type(e).__name__
@@ -6924,6 +6970,25 @@ class ChatSession:
                 self.context_window = cfg.context_window
                 if not self._manual_tool_truncation:
                     self.tool_truncation = int(cfg.context_window * self._chars_per_token * 0.5)
+                # Apply per-model sampling overrides, falling back to global
+                # defaults — mirrors session_factory() resolution logic so
+                # switching away from a model with overrides doesn't leak them.
+                cs = self._config_store
+                self.temperature = (
+                    cfg.temperature
+                    if cfg.temperature is not None
+                    else (cs.get("model.temperature") if cs else self.temperature)
+                )
+                self.max_tokens = (
+                    cfg.max_tokens
+                    if cfg.max_tokens is not None
+                    else (cs.get("model.max_tokens") if cs else self.max_tokens)
+                )
+                self.reasoning_effort = (
+                    cfg.reasoning_effort
+                    if cfg.reasoning_effort is not None
+                    else (cs.get("model.reasoning_effort") if cs else self.reasoning_effort)
+                )
                 self._init_system_messages()
                 self._save_config()
                 self.ui.on_info(f"Switched to {cyan(arg)}: {model_name}")

turnstone/core/settings_registry.py

@@ -35,14 +35,6 @@ def _build_registry() -> dict[str, SettingDef]:
     """Build the settings registry from declarative definitions."""
     defs: list[SettingDef] = [
         # -- model ----------------------------------------------------------
-        SettingDef(
-            "model.name",
-            "str",
-            "",
-            "Default model name (empty = use provider default)",
-            "model",
-            help="Which AI model to use for conversations. Leave empty to use the provider's default.",
-        ),
         SettingDef(
             "model.default_alias",
             "str",
@@ -58,45 +50,38 @@ def _build_registry() -> dict[str, SettingDef]:
             "model.temperature",
             "float",
             0.5,
-            "Sampling temperature (ignored by models that don't support it, e.g. o-series)",
+            "Default sampling temperature (overridden by per-model settings)",
             "model",
             min_value=0.0,
             max_value=2.0,
-            help="Controls randomness in responses. Lower values (0.0\u20130.3) give focused, "
-            "deterministic output; higher values (0.7\u20131.5) make responses more creative and varied.",
+            help="Default sampling temperature for models without a per-model override. "
+            "Controls randomness in responses. Lower values (0.0\u20130.3) give focused, "
+            "deterministic output; higher values (0.7\u20131.5) make responses more creative "
+            "and varied. Per-model overrides can be set in the Models tab.",
             reference_url="https://arxiv.org/abs/1904.09751",
         ),
         SettingDef(
             "model.max_tokens",
             "int",
             32768,
-            "Max output tokens per response",
+            "Default max output tokens (overridden by per-model settings)",
             "model",
             min_value=1,
-            help="Upper limit on how long each response can be. One token is roughly 4 characters "
-            "of English text. Higher values allow longer responses but cost more.",
+            help="Default max output tokens for models without a per-model override. "
+            "Upper limit on how long each response can be. One token is roughly 4 characters "
+            "of English text. Per-model overrides can be set in the Models tab.",
         ),
         SettingDef(
             "model.reasoning_effort",
             "str",
             "medium",
-            "Reasoning effort level (only applies to models with reasoning support)",
+            "Default reasoning effort (overridden by per-model settings)",
             "model",
             choices=["", "none", "minimal", "low", "medium", "high", "xhigh", "max"],
-            help="How much internal \u2018thinking\u2019 the model does before responding. Higher effort "
-            "improves quality on complex tasks but is slower and uses more tokens. Not all models "
-            "support this \u2014 it is silently ignored when unsupported.",
-        ),
-        SettingDef(
-            "model.context_window",
-            "int",
-            0,
-            "Context window size in tokens (0 = auto-detect from model)",
-            "model",
-            min_value=0,
-            help="How much conversation history the model can see at once, measured in tokens "
-            "(~4 characters each). Set to 0 to auto-detect from the model. Only override this "
-            "if auto-detection fails (common with local models).",
+            help="Default reasoning effort for models without a per-model override. "
+            "Controls how much internal \u2018thinking\u2019 the model does before responding. "
+            "Higher effort improves quality on complex tasks but is slower and uses more "
+            "tokens. Per-model overrides can be set in the Models tab.",
         ),
         # -- session --------------------------------------------------------
         SettingDef(

turnstone/core/storage/_postgresql.py

@@ -3084,6 +3084,9 @@ class PostgreSQLBackend:
         capabilities: str = "{}",
         enabled: bool = True,
         created_by: str = "",
+        temperature: float | None = None,
+        max_tokens: int | None = None,
+        reasoning_effort: str | None = None,
     ) -> None:
         from sqlalchemy.dialects import postgresql
 
@@ -3101,6 +3104,9 @@ class PostgreSQLBackend:
                     context_window=context_window,
                     capabilities=capabilities,
                     enabled=1 if enabled else 0,
+                    temperature=temperature,
+                    max_tokens=max_tokens,
+                    reasoning_effort=reasoning_effort,
                     created_by=created_by,
                     created=now,
                     updated=now,

turnstone/core/storage/_protocol.py

@@ -1070,6 +1070,9 @@ class StorageBackend(Protocol):
         capabilities: str = "{}",
         enabled: bool = True,
         created_by: str = "",
+        temperature: float | None = None,
+        max_tokens: int | None = None,
+        reasoning_effort: str | None = None,
     ) -> None:
         """Create a model definition. No-op if definition_id already exists."""
         ...

turnstone/core/storage/_schema.py

@@ -587,6 +587,9 @@ model_definitions = sa.Table(
     sa.Column("context_window", sa.Integer, nullable=False, server_default="32768"),
     sa.Column("capabilities", sa.Text, nullable=False, server_default="{}"),
     sa.Column("enabled", sa.Integer, nullable=False, server_default="1"),
+    sa.Column("temperature", sa.Float, nullable=True),
+    sa.Column("max_tokens", sa.Integer, nullable=True),
+    sa.Column("reasoning_effort", sa.Text, nullable=True),
     sa.Column("created_by", sa.Text, nullable=False, server_default=""),
     sa.Column("created", sa.Text, nullable=False),
     sa.Column("updated", sa.Text, nullable=False),

turnstone/core/storage/_sqlite.py

@@ -3147,6 +3147,9 @@ class SQLiteBackend:
         capabilities: str = "{}",
         enabled: bool = True,
         created_by: str = "",
+        temperature: float | None = None,
+        max_tokens: int | None = None,
+        reasoning_effort: str | None = None,
     ) -> None:
 
         now = datetime.now(UTC).strftime("%Y-%m-%dT%H:%M:%S")
@@ -3163,6 +3166,9 @@ class SQLiteBackend:
                     "context_window": context_window,
                     "capabilities": capabilities,
                     "enabled": 1 if enabled else 0,
+                    "temperature": temperature,
+                    "max_tokens": max_tokens,
+                    "reasoning_effort": reasoning_effort,
                     "created_by": created_by,
                     "created": now,
                     "updated": now,

turnstone/core/storage/_utils.py

@@ -106,6 +106,9 @@ MODEL_DEFINITION_MUTABLE = frozenset(
         "context_window",
         "capabilities",
         "enabled",
+        "temperature",
+        "max_tokens",
+        "reasoning_effort",
     }
 )
 PROMPT_POLICY_MUTABLE = frozenset({"name", "content", "tool_gate", "priority", "enabled"})

turnstone/core/storage/migrations/versions/036_model_sampling_params.py

@@ -0,0 +1,32 @@
+"""Add per-model sampling parameters to model_definitions.
+
+Adds nullable temperature, max_tokens, and reasoning_effort columns
+so each model can override the global defaults.  NULL means "inherit
+the cluster-wide setting from system_settings".
+
+Revision ID: 036
+Revises: 035
+Create Date: 2026-04-13
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "036"
+down_revision = "035"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    with op.batch_alter_table("model_definitions") as batch:
+        batch.add_column(sa.Column("temperature", sa.Float, nullable=True))
+        batch.add_column(sa.Column("max_tokens", sa.Integer, nullable=True))
+        batch.add_column(sa.Column("reasoning_effort", sa.Text, nullable=True))
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("model_definitions") as batch:
+        batch.drop_column("reasoning_effort")
+        batch.drop_column("max_tokens")
+        batch.drop_column("temperature")

turnstone/deploy/compose.yaml

@@ -9,7 +9,7 @@
 #   Infra only:           docker compose up
 #   Single node:          docker compose --profile production up
 #   Production (PG):      docker compose --profile production up
-#                         (set DB_BACKEND, DATABASE_URL, POSTGRES_PASSWORD in .env)
+#                         (set TURNSTONE_DB_BACKEND, TURNSTONE_DB_URL, POSTGRES_PASSWORD in .env)
 #
 # Set TURNSTONE_IMAGE_TAG in .env to pin the image version (default: latest).
 # =============================================================================
@@ -94,8 +94,8 @@ services:
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
       - MODEL=${MODEL:-}
       - MCP_CONFIG=${MCP_CONFIG:-}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-sqlite}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-sqlite}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-}
       - TURNSTONE_NODE_ID=${TURNSTONE_NODE_ID:-}
       - TURNSTONE_ADVERTISE_URL=${TURNSTONE_ADVERTISE_URL:-http://server:8080}
     extra_hosts:
@@ -128,8 +128,8 @@ services:
     environment:
       # Generate with: python -c "import secrets; print(secrets.token_hex(32))"
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-sqlite}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-sqlite}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-}
       - TURNSTONE_CONSOLE_URL=http://console:8090
     networks:
       - turnstone-net
@@ -161,8 +161,8 @@ services:
       - TURNSTONE_DISCORD_GUILD=${TURNSTONE_DISCORD_GUILD:-0}
       # Generate with: python -c "import secrets; print(secrets.token_hex(32))"
       - TURNSTONE_JWT_SECRET=${TURNSTONE_JWT_SECRET:?Set TURNSTONE_JWT_SECRET in .env}
-      - TURNSTONE_DB_BACKEND=${DB_BACKEND:-postgresql}
-      - TURNSTONE_DB_URL=${DATABASE_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:-turnstone}@postgres:5432/turnstone}
+      - TURNSTONE_DB_BACKEND=${TURNSTONE_DB_BACKEND:-postgresql}
+      - TURNSTONE_DB_URL=${TURNSTONE_DB_URL:-postgresql+psycopg://${POSTGRES_USER:-turnstone}:${POSTGRES_PASSWORD:-turnstone}@postgres:5432/turnstone}
       - TURNSTONE_CHANNEL_ADVERTISE_URL=http://channel:8091
     networks:
       - turnstone-net

turnstone/server.py

@@ -2774,6 +2774,9 @@ def internal_model_status(request: Request) -> JSONResponse:
             "source": cfg.source,
             "context_window": cfg.context_window,
             "enabled": True,
+            "temperature": cfg.temperature,
+            "max_tokens": cfg.max_tokens,
+            "reasoning_effort": cfg.reasoning_effort,
         }
     return JSONResponse({"models": models})
 
@@ -3406,9 +3409,8 @@ def main() -> None:
 
     client = create_client(provider_name, base_url=base_url, api_key=api_key)
 
-    cs_model = config_store.get("model.name")
     cli_model = args.model
-    effective_model = cli_model or cs_model or None
+    effective_model = cli_model or None
     if effective_model:
         model = effective_model
         detected_ctx = None
@@ -3422,13 +3424,10 @@ def main() -> None:
             # entry and relies on DB / config.toml models instead.
             model = ""
 
-    # Use detected context window, fall back to ConfigStore override or 32768
-    cfg_ctx = config_store.get("model.context_window")
+    # Use detected context window, fall back to 32768
     if detected_ctx:
         context_window = detected_ctx
         log.info("Context window: %s (detected from backend)", f"{context_window:,}")
-    elif cfg_ctx:  # 0 = auto-detect (no override)
-        context_window = cfg_ctx
     else:
         context_window = 32768
 
@@ -3595,15 +3594,32 @@ def main() -> None:
             except Exception as e:
                 log.warning("Failed to resolve judge_model %r: %s", judge_model, e)
 
+        # Per-model sampling overrides take priority over global defaults
+        eff_temperature = (
+            r_cfg.temperature
+            if r_cfg.temperature is not None
+            else config_store.get("model.temperature")
+        )
+        eff_max_tokens = (
+            r_cfg.max_tokens
+            if r_cfg.max_tokens is not None
+            else config_store.get("model.max_tokens")
+        )
+        eff_reasoning_effort = (
+            r_cfg.reasoning_effort
+            if r_cfg.reasoning_effort is not None
+            else config_store.get("model.reasoning_effort")
+        )
+
         return ChatSession(
             client=r_client,
             model=r_model,
             ui=ui,
             instructions=config_store.get("session.instructions") or None,
-            temperature=config_store.get("model.temperature"),
-            max_tokens=config_store.get("model.max_tokens"),
+            temperature=eff_temperature,
+            max_tokens=eff_max_tokens,
             tool_timeout=config_store.get("tools.timeout"),
-            reasoning_effort=config_store.get("model.reasoning_effort"),
+            reasoning_effort=eff_reasoning_effort,
             context_window=r_cfg.context_window,
             compact_max_tokens=config_store.get("session.compact_max_tokens"),
             auto_compact_pct=config_store.get("session.auto_compact_pct"),
@@ -3715,15 +3731,15 @@ def main() -> None:
 
     cors_origins = parse_cors_origins()
 
-    # Construct advertise URL for service registration.
-    # In Docker/k8s, socket.gethostname() returns the container ID which
-    # isn't DNS-resolvable by other containers.  Priority:
-    # 1. TURNSTONE_ADVERTISE_URL env var (explicit override)
+    # Construct advertise URL for service registration.  Priority:
+    # 1. TURNSTONE_ADVERTISE_URL env var (required in Docker/k8s where
+    #    gethostname() returns a container ID that peers can't resolve)
     # 2. Explicit --host (not a wildcard bind address)
-    # 3. socket.getfqdn() (may work in k8s with proper DNS)
+    # 3. socket.gethostname() (bare-metal fallback; getfqdn() does
+    #    reverse DNS which often truncates the hostname)
     _advertise_url = os.environ.get("TURNSTONE_ADVERTISE_URL", "")
     if not _advertise_url:
-        _advertise_host = args.host if args.host not in ("0.0.0.0", "::") else socket.getfqdn()
+        _advertise_host = args.host if args.host not in ("0.0.0.0", "::") else socket.gethostname()
         _advertise_url = f"http://{_advertise_host}:{args.port}"
 
     _skip_perms = config_store.get("tools.skip_permissions")
@@ -3793,8 +3809,11 @@ def main() -> None:
 
             from turnstone.core.tls import TLSClient
 
-            hostname = socket.getfqdn()
+            hostname = socket.gethostname()
+            fqdn = socket.getfqdn()
             hostnames = [hostname, "localhost", "127.0.0.1"]
+            if fqdn != hostname:
+                hostnames.append(fqdn)
             # Only add bind host if it's a concrete address
             if args.host not in ("0.0.0.0", "::", ""):
                 hostnames.append(args.host)

turnstone/ui/static/app.js

@@ -4504,7 +4504,7 @@ function _loadHls(callback) {
   if (_hlsState === "loading") return;
   _hlsState = "loading";
   var script = document.createElement("script");
-  script.src = "/shared/hls-1.6.15/hls.min.js";
+  script.src = "/shared/hls-1.6.16/hls.min.js";
   script.onload = function () {
     _hlsState = "ready";
     var q = _hlsQueue;

uv.lock

@@ -2506,7 +2506,7 @@ wheels = [
 
 [[package]]
 name = "turnstone"
-version = "1.3.0a3"
+version = "1.4.0a2"
 source = { editable = "." }
 dependencies = [
     { name = "alembic" },