Make UC model discovery the default; remove --enable-uc

ucode configure only found the opus Claude model on workspaces where the
legacy /ai-gateway/anthropic/v1/models listing dropped sonnet/haiku once
system.ai endpoints existed. UC model-services discovery found all three but
was hidden behind --enable-uc (and had no fallback).

Now discovery is UC-first and best-effort: try model-services first, fall back
to the legacy per-family listing per family when UC returns nothing. The
--enable-uc flag, UCODE_ENABLE_UC env var, and uc_enabled helper are removed,
and curated system.ai.* MCP services are surfaced by default. The
model-services endpoint still 499s without a bounded page_size, so pagination
(page_size=100, follow next_page_token, light per-page retry) is retained.

Co-authored-by: Isaac

Author: AarushiShah-db

src/ucode/cli.py

@@ -46,7 +46,6 @@
     normalize_workspace_url,
     resolve_pat_token,
     run_databricks_login,
-    uc_enabled,
 )
 from ucode.mcp import (
     MCP_CLIENTS,
@@ -195,8 +194,6 @@ def configure_shared_state(
     profile: str | None = None,
     tools: list[str] | None = None,
     force_login: bool = False,
-    enable_uc: bool | None = None,
-    reset_uc: bool = False,
     use_pat: bool | None = None,
 ) -> dict:
     """Log into Databricks, enforce AI Gateway v2, fetch model lists, persist state.
@@ -211,28 +208,10 @@ def configure_shared_state(
     ``--profile`` to every CLI invocation so ambiguous `~/.databrickscfg`
     entries (e.g. DEFAULT and a named profile both pointing at the same host)
     don't error out. If ``None``, we resolve it from the host after login.
-    ``enable_uc`` is the resolved CLI flag (`--enable-uc`): when not None
-    it overrides both the env var and the persisted state.
-    ``reset_uc`` is True only on the explicit ``ucode configure`` flow.
     """
     workspace = normalize_workspace_url(workspace)
     prior_state = load_state()
     previous_workspace = prior_state.get("workspace")
-    # Precedence: explicit CLI flag > env var > (configure: reset to False;
-    # launch: target workspace's persisted state). Use *target* state on the
-    # launch path so the flag is sticky per-workspace and doesn't leak
-    # across workspace switches.
-    # TODO: when this flips uc_enabled True->False, prune any
-    # `system.ai.*` MCP services from state["mcp_servers"] (and their
-    # cross-tool registrations). Today they linger as orphans pointing at
-    # /ai-gateway/mcp-services/* until the user re-runs `configure mcp`
-    # or switches workspaces.
-    if enable_uc is None:
-        if reset_uc:
-            enable_uc = uc_enabled(default=False)
-        else:
-            target_ws_state = load_full_state().get("workspaces", {}).get(workspace) or {}
-            enable_uc = uc_enabled(default=bool(target_ws_state.get("uc_enabled")))
     if use_pat is None:
         use_pat = bool(prior_state.get("use_pat")) and previous_workspace == workspace
     fetch_all = tools is None
@@ -278,25 +257,23 @@ def configure_shared_state(
     claude_models = {}
     gemini_models = []
     codex_models = []
-    if enable_uc:
-        # Opt-in: one UC model-services call yields all families as
-        # `system.ai.<model-name>` ids, bucketed by name. The single reason is
-        # shared across the families that were requested.
-        with spinner("Fetching available models (model services)..."):
-            ms_claude, ms_codex, ms_gemini, ms_reason = discover_model_services(workspace, token)
+    # UC-first, best-effort: one UC model-services call yields all families as
+    # `system.ai.<model-name>` ids, bucketed by name. If a family comes back
+    # empty (workspace without UC model-services, or the listing failed), fall
+    # back to the per-family AI Gateway listing for that family only.
+    with spinner("Fetching available models..."):
+        ms_claude, ms_codex, ms_gemini, ms_reason = discover_model_services(workspace, token)
         if want_claude:
             claude_models, claude_reason = ms_claude, ms_reason
+            if not claude_models:
+                claude_models, claude_reason = discover_claude_models(workspace, token)
         if want_gemini:
             gemini_models, gemini_reason = ms_gemini, ms_reason
+            if not gemini_models:
+                gemini_models, gemini_reason = discover_gemini_models(workspace, token)
         if want_codex:
             codex_models, codex_reason = ms_codex, ms_reason
-    else:
-        with spinner("Fetching available models..."):
-            if want_claude:
-                claude_models, claude_reason = discover_claude_models(workspace, token)
-            if want_gemini:
-                gemini_models, gemini_reason = discover_gemini_models(workspace, token)
-            if want_codex:
+            if not codex_models:
                 codex_models, codex_reason = discover_codex_models(workspace, token)
     opencode_models: dict[str, list[str]] = {}
     if claude_models:
@@ -311,9 +288,8 @@ def configure_shared_state(
         state["profile"] = profile
     else:
         state.pop("profile", None)
-    # Persist the resolved flag so subsequent launches stay on the same
-    # discovery path without the env var or CLI flag being re-passed.
-    state["uc_enabled"] = enable_uc
+    # UC discovery is now always-on; drop any flag persisted by older versions.
+    state.pop("uc_enabled", None)
     # Persist the auth mode so launches rebuild the same (PAT-based) agent
     # auth command; an explicit re-configure without --use-pat clears it.
     if use_pat:
@@ -349,8 +325,6 @@ def _configure_shared_workspace_states(
     tools: list[str] | None,
     *,
     force_login: bool,
-    enable_uc: bool | None = None,
-    reset_uc: bool = False,
     use_pat: bool = False,
 ) -> list[dict]:
     if not workspaces:
@@ -363,8 +337,6 @@ def _configure_shared_workspace_states(
                 profile=profile,
                 tools=tools,
                 force_login=force_login,
-                enable_uc=enable_uc,
-                reset_uc=reset_uc,
                 use_pat=use_pat,
             )
         )
@@ -377,8 +349,6 @@ def configure_workspace_command(
     workspaces: list[tuple[str, str | None]] | None = None,
     *,
     prompt_optional_updates: bool = True,
-    enable_uc: bool | None = None,
-    reset_uc: bool = False,
     use_pat: bool = False,
     skip_validate: bool = False,
 ) -> int:
@@ -392,8 +362,6 @@ def configure_workspace_command(
             workspace_entries,
             [tool],
             force_login=True,
-            enable_uc=enable_uc,
-            reset_uc=reset_uc,
             use_pat=use_pat,
         )
         state = states[0]
@@ -429,8 +397,6 @@ def configure_workspace_command(
         workspace_entries,
         selected_tools,
         force_login=True,
-        enable_uc=enable_uc,
-        reset_uc=reset_uc,
         use_pat=use_pat,
     )
     state = states[0]
@@ -827,18 +793,6 @@ def configure(
             "'low' prints terse single-line status instead.",
         ),
     ] = "normal",
-    enable_uc: Annotated[
-        bool,
-        typer.Option(
-            "--enable-uc",
-            help="Discover models via UC `model-services` (`system.ai.<model>`) and "
-            "surface curated `system.ai.*` MCP services. Equivalent to setting "
-            "UCODE_ENABLE_UC=1 for this configure run. The value is persisted so "
-            "subsequent `ucode <agent>` launches stay on the same discovery path; "
-            "re-run `ucode configure` without the flag (and without "
-            "UCODE_ENABLE_UC=1 in the env) to turn UC discovery back off.",
-        ),
-    ] = False,
 ) -> None:
     """Configure workspace URL and AI Gateway."""
     if ctx.invoked_subcommand is not None:
@@ -849,10 +803,6 @@ def configure(
     set_dry_run(dry_run)
     set_verbosity(verbose)
     prompt_optional_updates = not skip_upgrade
-    flag_enable_uc: bool | None = True if enable_uc else None
-    # Explicit `ucode configure` is a clean slate: when the user omits both
-    # `--enable-uc` and `UCODE_ENABLE_UC`, persisted `uc_enabled=true` from
-    # a prior run is reset to false.
     try:
         install_databricks_cli()
         if agent is not None and agents is not None:
@@ -883,15 +833,11 @@ def configure(
                 prompt_optional_updates=prompt_optional_updates,
             )
             if workspace_entries is None:
-                configure_workspace_command(
-                    tool, enable_uc=flag_enable_uc, reset_uc=True, **skip_kwargs
-                )
+                configure_workspace_command(tool, **skip_kwargs)
             else:
                 configure_workspace_command(
                     tool,
                     workspaces=workspace_entries,
-                    enable_uc=flag_enable_uc,
-                    reset_uc=True,
                     **skip_kwargs,
                 )
         elif agents is not None:
@@ -900,17 +846,13 @@ def configure(
                 configure_workspace_command(
                     selected_tools=selected_tools,
                     prompt_optional_updates=prompt_optional_updates,
-                    enable_uc=flag_enable_uc,
-                    reset_uc=True,
                     **skip_kwargs,
                 )
             else:
                 configure_workspace_command(
                     selected_tools=selected_tools,
                     workspaces=workspace_entries,
                     prompt_optional_updates=prompt_optional_updates,
-                    enable_uc=flag_enable_uc,
-                    reset_uc=True,
                     **skip_kwargs,
                 )
         else:
@@ -919,16 +861,12 @@ def configure(
             if workspace_entries is None:
                 configure_workspace_command(
                     prompt_optional_updates=prompt_optional_updates,
-                    enable_uc=flag_enable_uc,
-                    reset_uc=True,
                     **skip_kwargs,
                 )
             else:
                 configure_workspace_command(
                     workspaces=workspace_entries,
                     prompt_optional_updates=prompt_optional_updates,
-                    enable_uc=flag_enable_uc,
-                    reset_uc=True,
                     **skip_kwargs,
                 )
         if tracing:

src/ucode/databricks.py

@@ -1050,27 +1050,6 @@ def build_auth_shell_command(
     )
 
 
-def uc_enabled(default: bool = False) -> bool:
-    """True when the opt-in UC-securables discovery path is enabled.
-
-    Three input precedences, callers handle the highest one first:
-      1. ``ucode configure --enable-uc / --no-enable-uc`` (resolved by the
-         CLI before this function is called and passed in via ``default``,
-         since it overrides everything).
-      2. ``UCODE_ENABLE_UC=1`` (or true/yes/on) env var.
-      3. The value persisted in state (sticky, also passed via ``default``).
-
-    Enabling UC discovery makes ucode:
-      - resolve models via UC `model-services` as `system.ai.<model-name>`
-        instead of the per-family AI Gateway listings
-      - surface curated `system.ai.*` MCP services in `ucode configure mcp`
-    """
-    raw = os.environ.get("UCODE_ENABLE_UC")
-    if raw is None or not raw.strip():
-        return default
-    return raw.strip().lower() in {"1", "true", "yes", "on"}
-
-
 # A model-service's `name` is `model-services/system.ai.<model-name>`; the
 # part after the prefix is exactly the model string agents send (no
 # `databricks-` infix — that only appears on the inner destination name).
@@ -1097,11 +1076,12 @@ def _model_service_id(service: dict) -> str | None:
     return name or None
 
 
-# The model-services metastore listing is slow and flaky — large pages
-# routinely 504 with `Timeout listing model services under metastore`. A small
-# page is far more likely to come back, and each page gets a few retries before
-# we give up.
-_MODEL_SERVICES_PAGE_SIZE = 10
+# The model-services metastore listing REQUIRES a bounded `page_size`:
+# unparameterized or large-page requests (verified against
+# eng-ml-agent-platform.staging 2026-06-14) return `HTTP 499` with an empty
+# body, while pages of 10–100 come back reliably. A page can still 499
+# intermittently under load, so each gets a few retries before we give up.
+_MODEL_SERVICES_PAGE_SIZE = 100
 _MODEL_SERVICES_PAGE_RETRIES = 4
 
 
@@ -1110,9 +1090,9 @@ def _get_model_services_page(
 ) -> tuple[dict | list | None, str | None]:
     """GET one model-services page, retrying on failure.
 
-    The endpoint frequently 504s under load; a retry usually succeeds. Returns
-    the same (payload, reason) shape as ``_http_get_json`` — the last attempt's
-    result when all retries are exhausted."""
+    The endpoint intermittently 499/504s under load; a retry usually succeeds.
+    Returns the same (payload, reason) shape as ``_http_get_json`` — the last
+    attempt's result when all retries are exhausted."""
     payload: dict | list | None = None
     reason: str | None = None
     for attempt in range(retries):
@@ -1133,11 +1113,10 @@ def list_model_services(
     """List all `system.ai.*` model ids via the UC model-services API.
 
     Pages through ``/api/2.1/unity-catalog/model-services`` (metastore scope)
-    and returns the de-duplicated, sorted list of ``system.ai.<model-name>``
-    ids. Uses a small page size with per-page retries because the endpoint is
-    slow and frequently 504s. Returns (ids, reason); reason is None on success,
-    otherwise it describes why the list is empty (HTTP/network error or no
-    services).
+    with a bounded ``page_size`` (the endpoint 499s without one) and returns the
+    de-duplicated, sorted list of ``system.ai.<model-name>`` ids. Returns
+    (ids, reason); reason is None on success, otherwise it describes why the
+    list is empty (HTTP/network error or no services).
     """
     hostname = workspace_hostname(workspace)
     ids: list[str] = []

src/ucode/mcp.py

@@ -35,7 +35,6 @@
     list_databricks_connections,
     list_genie_spaces,
     list_mcp_services,
-    uc_enabled,
     workspace_hostname,
 )
 from ucode.state import load_full_state, load_state, save_state
@@ -990,17 +989,12 @@ def configure_mcp_command() -> int:
         "Databricks apps",
         lambda: discover_app_mcp_servers(workspace, profile),
     )
-    # Curated `system.ai.*` MCP services live behind a separate UC API and
-    # are gated on the same UC opt-in that enables model-services discovery
-    # (env: UCODE_ENABLE_UC, CLI: `ucode configure --enable-uc`, persisted
-    # in state on configure).
-    available_mcp_service_names = (
-        _discover_mcp_source(
-            "MCP services",
-            lambda: discover_mcp_service_names(workspace, profile),
-        )
-        if uc_enabled(default=bool(state.get("uc_enabled")))
-        else []
+    # Curated `system.ai.*` MCP services live behind a separate UC API. Like
+    # the other sources this is best-effort — `_discover_mcp_source` swallows
+    # failures and returns [] so workspaces without them just see nothing extra.
+    available_mcp_service_names = _discover_mcp_source(
+        "MCP services",
+        lambda: discover_mcp_service_names(workspace, profile),
     )
 
     original_mcp_servers: list[dict] = list(state.get("mcp_servers") or [])