diff --git a/src/ucode/agents/__init__.py b/src/ucode/agents/__init__.py
index 27b0458..065220d 100644
--- a/src/ucode/agents/__init__.py
+++ b/src/ucode/agents/__init__.py
@@ -363,6 +363,7 @@ def check_gateway_endpoint(state: dict, tool: str) -> bool:
             bool(state.get("claude_models"))
             or bool(state.get("codex_models"))
             or bool(state.get("gemini_models"))
+            or bool(state.get("oss_models"))
         )
     return False
 
@@ -373,7 +374,7 @@ def check_gateway_endpoint(state: dict, tool: str) -> bool:
     "codex": ("codex",),
     "gemini": ("gemini",),
     "copilot": ("claude", "codex"),
-    "pi": ("claude", "codex", "gemini"),
+    "pi": ("claude", "codex", "gemini", "oss"),
 }
 
 
diff --git a/src/ucode/agents/claude.py b/src/ucode/agents/claude.py
index 4ac91e3..2528bfa 100644
--- a/src/ucode/agents/claude.py
+++ b/src/ucode/agents/claude.py
@@ -27,6 +27,7 @@
 from ucode.databricks import (
     build_auth_shell_command,
     build_tool_base_url,
+    claude_model_supports_1m,
     get_databricks_token,
 )
 from ucode.launcher import exec_or_spawn
@@ -69,11 +70,6 @@ def _resolve_web_search_model(state: dict) -> str | None:
 
 
 WEB_SEARCH_MCP_NAME = "web_search"
-# Matches both the AI Gateway form (`databricks-claude-opus-4-8`) and the UC
-# model-services form (`system.ai.claude-opus-4-8`).
-_CLAUDE_MODEL_RE = re.compile(
-    r"^(?:system\.ai\.)?(?:databricks-)?claude-(opus|sonnet)-(\d+)-(\d+)(.*)$"
-)
 
 # Env keys the MLflow Stop hook reads to route traces. Written into the
 # settings `env` block alongside the hook itself.
@@ -333,19 +329,9 @@ def render_overlay(
 
 
 def _maybe_add_1m_suffix(model: str) -> str:
-    if model.endswith("[1m]"):
-        return model
-    match = _CLAUDE_MODEL_RE.match(model)
-    if not match:
+    if model.endswith("[1m]") or not claude_model_supports_1m(model):
         return model
-
-    family, major_raw, minor_raw, _ = match.groups()
-    major = int(major_raw)
-    minor = int(minor_raw)
-    should_suffix = (family == "opus" and (major, minor) >= (4, 6)) or (
-        family == "sonnet" and (major, minor) >= (4, 6)
-    )
-    return f"{model}[1m]" if should_suffix else model
+    return f"{model}[1m]"
 
 
 def _register_web_search_mcp(workspace: str, search_model: str, profile: str | None = None) -> bool:
diff --git a/src/ucode/agents/pi.py b/src/ucode/agents/pi.py
index e7c1760..806c26f 100644
--- a/src/ucode/agents/pi.py
+++ b/src/ucode/agents/pi.py
@@ -1,12 +1,13 @@
 """Pi coding agent: writes ~/.pi/agent/models.json with Databricks-backed providers.
 
-Pi (https://pi.dev) is a multi-provider coding agent. We register three
+Pi (https://pi.dev) is a multi-provider coding agent. We register four
 providers in its `models.json`, each speaking the API dialect best suited to
 that family's gateway path:
 
 - `databricks-claude`  (api: anthropic-messages)       → /ai-gateway/anthropic
 - `databricks-openai`  (api: openai-responses)         → /ai-gateway/codex/v1
 - `databricks-gemini`  (api: google-generative-ai)     → /ai-gateway/gemini/v1beta
+- `databricks-mlflow`  (api: openai-completions)       → /ai-gateway/mlflow/v1
 
 Per-provider `compat` flags work around fields the gateway translators reject:
 
@@ -15,11 +16,17 @@
   pi uses for every request. With this flag pi omits the per-tool field and
   sends the legacy `anthropic-beta: fine-grained-tool-streaming-...` header
   instead, which the gateway accepts.
-
-OSS / Databricks-foundation models (Llama, Qwen, etc.) are not exposed via
-pi today — they live behind /ai-gateway/mlflow/v1 with per-model
-`max_tokens` caps that pi has no global way to honor without per-model
-config we don't currently maintain.
+- mlflow: `supportsStore: false` and `supportsStrictMode: false` — the MLflow
+  chat-completions gateway rejects OpenAI's `store` field and
+  `tools[].function.strict`.
+
+The `databricks-mlflow` provider carries the validated OSS coding models
+(GLM and Kimi) discovered upstream. Per model it sets
+`contextWindow`/`maxTokens` from `databricks.model_token_limits` and
+`reasoning` from `databricks.model_is_reasoning` (so Pi renders the gateway's
+streamed reasoning_content as thinking). Inkling is intentionally not offered
+until the gateway emits a terminal `finish_reason` on natural completion
+(issue #215).
 
 The bearer token is baked into the file and refreshed by a background thread
 while the session runs (same pattern as OpenCode/Copilot).
@@ -44,7 +51,12 @@
 from ucode.databricks import (
     TOKEN_REFRESH_INTERVAL_SECONDS,
     build_pi_base_urls,
+    claude_model_capabilities,
     get_databricks_token,
+    gpt_model_token_limits,
+    model_is_reasoning,
+    model_token_limits,
+    preferred_gpt_model,
 )
 from ucode.state import mark_tool_managed, save_state
 from ucode.telemetry import agent_version, ucode_version
@@ -68,6 +80,7 @@
     "databricks-claude",
     "databricks-openai",
     "databricks-gemini",
+    "databricks-mlflow",
 )
 
 PROVIDER_KEYS: list[list[str]] = [["providers", name] for name in PROVIDER_NAMES]
@@ -86,6 +99,7 @@ def _resolve_model_selector(
     claude_models: dict[str, str],
     codex_models: list[str],
     gemini_models: list[str],
+    oss_models: list[str],
 ) -> str:
     """Return a Pi model selector in `<provider>/<model>` form when possible."""
     for name in PROVIDER_NAMES:
@@ -97,9 +111,65 @@ def _resolve_model_selector(
         return f"databricks-openai/{model}"
     if model in gemini_models:
         return f"databricks-gemini/{model}"
+    if model in oss_models:
+        return f"databricks-mlflow/{model}"
     return model
 
 
+def _pi_claude_model_entry(model_id: str) -> dict:
+    """Build a Claude entry with explicit limits.
+
+    Databricks model ids do not match Pi's built-in Anthropic ids, so a bare
+    custom entry silently gets Pi's 128k context / 4k output defaults.
+    """
+    capabilities = claude_model_capabilities(model_id)
+    entry: dict = {
+        "id": model_id,
+        "reasoning": True,
+        "input": ["text", "image"],
+        "contextWindow": capabilities.context,
+        "maxTokens": capabilities.output,
+    }
+    if capabilities.force_adaptive_thinking:
+        entry["compat"] = {"forceAdaptiveThinking": True}
+    return entry
+
+
+def _pi_oss_model_entry(model_id: str) -> dict:
+    """Build a Pi mlflow model entry enriched from the shared limits/reasoning
+    tables: `reasoning:true` for reasoning models (Pi renders their streamed
+    reasoning_content as thinking), and `contextWindow`/`maxTokens` from
+    `model_token_limits`. Fields are omitted when unknown so Pi keeps its
+    default."""
+    entry: dict = {"id": model_id}
+    if model_is_reasoning(model_id):
+        entry["reasoning"] = True
+    limits = model_token_limits(model_id)
+    if limits:
+        if limits.get("context"):
+            entry["contextWindow"] = limits["context"]
+        if limits.get("output"):
+            entry["maxTokens"] = limits["output"]
+    return entry
+
+
+def _pi_gpt_model_entry(model_id: str) -> dict:
+    """Build a Pi openai (codex) model entry with `contextWindow`/`maxTokens`
+    from `databricks.gpt_model_token_limits`. GPT ids aren't in Pi's built-in
+    catalog, so without an explicit window Pi falls back to a small default and
+    truncates long sessions."""
+    limits = gpt_model_token_limits(model_id)
+    entry: dict = {
+        "id": model_id,
+        "contextWindow": limits["context"],
+        "maxTokens": limits["output"],
+    }
+    if "gpt-5" in model_id.lower().replace(".", "-"):
+        entry["reasoning"] = True
+        entry["input"] = ["text", "image"]
+    return entry
+
+
 def render_overlay(
     model: str,
     token: str,
@@ -107,6 +177,7 @@ def render_overlay(
     claude_models: dict[str, str],
     codex_models: list[str],
     gemini_models: list[str],
+    oss_models: list[str],
 ) -> tuple[dict, list[list[str]]]:
     """Return (overlay, managed_key_paths) for ~/.pi/agent/models.json."""
     providers: dict = {}
@@ -127,7 +198,7 @@ def render_overlay(
             # the legacy beta header instead when this is false.
             "compat": {"supportsEagerToolInputStreaming": False},
             "headers": ua_headers,
-            "models": [{"id": m} for m in claude_ids],
+            "models": [_pi_claude_model_entry(m) for m in claude_ids],
         }
         keys.append(["providers", "databricks-claude"])
     if codex_models:
@@ -137,7 +208,7 @@ def render_overlay(
             "apiKey": token,
             "authHeader": True,
             "headers": ua_headers,
-            "models": [{"id": m} for m in codex_models],
+            "models": [_pi_gpt_model_entry(m) for m in codex_models],
         }
         keys.append(["providers", "databricks-openai"])
     if gemini_models:
@@ -150,8 +221,23 @@ def render_overlay(
             "models": [{"id": m} for m in gemini_models],
         }
         keys.append(["providers", "databricks-gemini"])
+    if oss_models:
+        providers["databricks-mlflow"] = {
+            "baseUrl": pi_base_urls["oss"],
+            "api": "openai-completions",
+            "apiKey": token,
+            "authHeader": True,
+            # MLflow chat-completions gateway rejects OpenAI's `store` field
+            # and per-tool `strict`. Pi omits both when these are false.
+            "compat": {"supportsStore": False, "supportsStrictMode": False},
+            "headers": ua_headers,
+            "models": [_pi_oss_model_entry(m) for m in oss_models],
+        }
+        keys.append(["providers", "databricks-mlflow"])
     overlay: dict = {
-        "model": _resolve_model_selector(model, claude_models, codex_models, gemini_models),
+        "model": _resolve_model_selector(
+            model, claude_models, codex_models, gemini_models, oss_models
+        ),
     }
     if providers:
         overlay["providers"] = providers
@@ -178,6 +264,7 @@ def write_tool_config(
         state.get("claude_models") or {},
         state.get("codex_models") or [],
         state.get("gemini_models") or [],
+        state.get("oss_models") or [],
     )
     existing = read_json_safe(PI_CONFIG_PATH)
     providers = existing.get("providers")
@@ -206,16 +293,19 @@ def _write_settings(model_selector: str) -> None:
 
 
 def default_model(state: dict) -> str | None:
-    """Prefer Claude opus → sonnet → haiku; fall back to codex, gemini."""
+    """Prefer Claude opus → sonnet → haiku; fall back to codex, Gemini, then OSS."""
     claude_models = state.get("claude_models") or {}
     for family in ("opus", "sonnet", "haiku"):
         if claude_models.get(family):
             return claude_models[family]
-    codex_models = state.get("codex_models") or []
-    if codex_models:
-        return codex_models[0]
+    codex_model = preferred_gpt_model(state.get("codex_models") or [])
+    if codex_model:
+        return codex_model
     gemini_models = state.get("gemini_models") or []
-    return gemini_models[0] if gemini_models else None
+    if gemini_models:
+        return gemini_models[0]
+    oss_models = state.get("oss_models") or []
+    return oss_models[0] if oss_models else None
 
 
 def _refresh_token_once(state: dict, *, force_refresh: bool = False) -> str:
diff --git a/src/ucode/cli.py b/src/ucode/cli.py
index 1b42b4b..6037d4c 100644
--- a/src/ucode/cli.py
+++ b/src/ucode/cli.py
@@ -97,7 +97,7 @@
     "claude": ("claude", "opencode", "copilot", "pi"),
     "codex": ("codex", "copilot", "pi"),
     "gemini": ("gemini", "opencode", "pi"),
-    "oss": ("opencode",),
+    "oss": ("opencode", "pi"),
 }
 
 
@@ -371,7 +371,7 @@ def configure_shared_state(
     )
     want_gemini = fetch_all or "gemini" in tools or "opencode" in tools or "pi" in tools
     want_codex = fetch_all or "codex" in tools or "copilot" in tools or "pi" in tools
-    want_oss = fetch_all or "opencode" in tools
+    want_oss = fetch_all or "opencode" in tools or "pi" in tools
 
     claude_reason: str | None = None
     gemini_reason: str | None = None
diff --git a/src/ucode/databricks.py b/src/ucode/databricks.py
index 1d32f31..4417ff9 100644
--- a/src/ucode/databricks.py
+++ b/src/ucode/databricks.py
@@ -23,6 +23,7 @@
 from concurrent.futures import (
     TimeoutError as FutureTimeoutError,
 )
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Literal, cast, overload
 from urllib import error as urllib_error
@@ -1194,10 +1195,24 @@ def build_auth_shell_command(
 # Databricks-managed foundation models under `system.ai`.
 _MODEL_SERVICE_REQUIRED_PREFIX = "system.ai."
 
-# Supported OSS chat families, matched by name substring. Add an entry to
-# support a new family.
+# OSS families validated as coding models in ucode, matched by name substring.
+# Keep this as an explicit product allowlist rather than exposing every model on
+# the chat-completions route. Inkling remains excluded until gateway issue #215
+# is fixed; other families require coding-harness validation before inclusion.
 _OSS_MODEL_FAMILIES = ("kimi-", "glm-")
 
+# Non-chat services must never be offered to a chat agent if a future supported
+# family also uses one of these substrings.
+_OSS_NON_CHAT_SUBSTRINGS = ("embedding", "embed", "rerank")
+
+
+def _is_oss_chat_model(model_id: str) -> bool:
+    """True if the id matches an OSS chat family and isn't a non-chat service."""
+    if any(bad in model_id for bad in _OSS_NON_CHAT_SUBSTRINGS):
+        return False
+    return any(family in model_id for family in _OSS_MODEL_FAMILIES)
+
+
 # Claude model families ucode buckets, newest tier first. Each maps to a
 # Claude Code family alias (ANTHROPIC_DEFAULT_<FAMILY>_MODEL). Add an entry to
 # support a new family in both discovery paths (`claude-<family>-*` via the
@@ -1211,24 +1226,179 @@ def build_auth_shell_command(
 # config dialect. Both fields are provided because agents like OpenCode require
 # context and output together. Keyed by family substring; add an entry to bound
 # a new model.
+#
+# Output caps probed from the gateway 2026-07-16 (it 400s with "max_tokens (N)
+# cannot exceed <cap>"); context windows from each model's docs/description
+# (conservative when unstated). If the gateway raises a cap or ships a new
+# model, update this table.
 _MODEL_TOKEN_LIMITS: dict[str, dict[str, int]] = {
-    # GLM-4.6: 200k context, but the gateway caps output well below the model's
-    # native 128k — pin 25k so requests aren't rejected.
+    # Keep the version-specific entry before the family fallback: GLM 5.2 has
+    # materially higher probed gateway limits than earlier/unknown variants.
+    "glm-5-2": {"context": 1_000_000, "output": 65_536},
     "glm": {"context": 200_000, "output": 25_000},
+    "kimi": {"context": 128_000, "output": 65_536},
 }
 
+# Conservative fallback for a future variant that matches a validated family
+# but has no specific entry. Pinning a low output ceiling risks truncation, not
+# a gateway 400, so it is the safe failure direction.
+_OSS_FALLBACK_LIMITS = {"context": 128_000, "output": 8_192}
+
+# Validated families that emit reasoning. Pi renders their streamed
+# reasoning_content as thinking when the model entry sets reasoning:true.
+_OSS_REASONING_FAMILIES = ("glm", "kimi")
+
+
+def model_is_reasoning(model_id: str) -> bool:
+    """True if the OSS model reports reasoning output (family-matched)."""
+    return any(family in model_id for family in _OSS_REASONING_FAMILIES)
+
 
 def model_token_limits(model_id: str) -> dict[str, int] | None:
     """Return ``{"context": ..., "output": ...}`` limits for ``model_id``, or None.
 
-    Matches by family substring (e.g. any ``*glm*`` id). None means the model
-    has no known limits and the agent should not pin any."""
+    Prefers a specific `_MODEL_TOKEN_LIMITS` family entry (e.g. any ``*glm*``
+    id). Any other OSS chat model falls back to a conservative floor so it is
+    never offered uncapped (which would 400). None only for non-OSS ids, where
+    the agent should not pin any limit."""
     for family, limits in _MODEL_TOKEN_LIMITS.items():
         if family in model_id:
             return dict(limits)
+    if _is_oss_chat_model(model_id):
+        return dict(_OSS_FALLBACK_LIMITS)
     return None
 
 
+# Pi treats every custom model without explicit metadata as 128k context / 4k
+# output. Gateway ids are custom ids (not Pi's built-ins), so preserve the
+# upstream windows explicitly. Entries are ordered most-specific first after
+# normalizing dotted OpenAI ids and hyphenated Databricks ids to one form.
+# GPT-5.6 Sol/Terra/Luna support the opt-in 1.05M window; 272k is merely Pi's
+# built-in short-context pricing default, not the model's hard context limit.
+_GPT_TOKEN_LIMITS: tuple[tuple[str, dict[str, int]], ...] = (
+    ("gpt-5-6-sol", {"context": 1_050_000, "output": 128_000}),
+    ("gpt-5-6-terra", {"context": 1_050_000, "output": 128_000}),
+    ("gpt-5-6-luna", {"context": 1_050_000, "output": 128_000}),
+    ("gpt-5-5-pro", {"context": 1_050_000, "output": 128_000}),
+    ("gpt-5-4-pro", {"context": 1_050_000, "output": 128_000}),
+    ("gpt-5-5", {"context": 272_000, "output": 128_000}),
+    ("gpt-5-4-mini", {"context": 400_000, "output": 128_000}),
+    ("gpt-5-4-nano", {"context": 400_000, "output": 128_000}),
+    ("gpt-5-4", {"context": 272_000, "output": 128_000}),
+    ("gpt-5", {"context": 400_000, "output": 128_000}),
+    ("gpt-4-1", {"context": 1_047_576, "output": 32_768}),
+    ("gpt-4o", {"context": 128_000, "output": 16_384}),
+    ("gpt-4-turbo", {"context": 128_000, "output": 4_096}),
+    ("gpt-4", {"context": 8_192, "output": 8_192}),
+)
+_GPT_FALLBACK_LIMITS = {"context": 128_000, "output": 16_384}
+
+
+def _normalized_foundation_model_id(model_id: str) -> str:
+    """Strip route prefixes case-insensitively and normalize dotted versions."""
+    tail = model_id.split("/")[-1].lower()
+    if tail.startswith("system.ai."):
+        tail = tail[len("system.ai.") :]
+    if tail.startswith("databricks-"):
+        tail = tail[len("databricks-") :]
+    return tail.replace(".", "-")
+
+
+def gpt_model_token_limits(model_id: str) -> dict[str, int]:
+    """Return Pi metadata limits for a GPT (codex/openai) gateway model."""
+    tail = _normalized_foundation_model_id(model_id)
+    for family, limits in _GPT_TOKEN_LIMITS:
+        if tail == family or tail.startswith(f"{family}-"):
+            return dict(limits)
+    return dict(_GPT_FALLBACK_LIMITS)
+
+
+def preferred_gpt_model(model_ids: list[str]) -> str | None:
+    """Prefer the newest numeric GPT id, then any other Responses endpoint.
+
+    ``gpt-oss`` is chat-completions-only and must never be selected for the
+    Responses route, even if stale state supplies it here.
+    """
+    eligible = [
+        model_id
+        for model_id in model_ids
+        if not _normalized_foundation_model_id(model_id).startswith("gpt-oss")
+    ]
+    numeric_gpt = [
+        model_id
+        for model_id in eligible
+        if re.match(r"^gpt-\d(?:-|$)", _normalized_foundation_model_id(model_id))
+    ]
+    if numeric_gpt:
+        return min(
+            numeric_gpt,
+            key=lambda model_id: model_version_sort_key(_normalized_foundation_model_id(model_id)),
+        )
+    return eligible[0] if eligible else None
+
+
+@dataclass(frozen=True)
+class ClaudeModelCapabilities:
+    context: int
+    output: int
+    supports_1m: bool = False
+    force_adaptive_thinking: bool = False
+
+
+_CLAUDE_FALLBACK_CAPABILITIES = ClaudeModelCapabilities(context=200_000, output=64_000)
+_CLAUDE_MODEL_RE = re.compile(r"^claude-(fable|opus|sonnet|haiku)-(\d+)(?:-(\d+))?")
+
+
+def claude_model_capabilities(model_id: str) -> ClaudeModelCapabilities:
+    """Return the shared Claude capability policy for every agent.
+
+    Opus gained the opt-in 1M window in 4.6; Sonnet gained it in 4.5.
+    Sonnet's verified 1M tiers retain a conservative 64k output cap. Fable 5
+    is 1M by default (so it needs no ``[1m]`` suffix) with a 128k output cap.
+    Opus 4.5, Haiku, and unrecognized ids use the conservative 200k fallback.
+    """
+    tail = _normalized_foundation_model_id(model_id)
+    match = _CLAUDE_MODEL_RE.match(tail)
+    if not match:
+        return _CLAUDE_FALLBACK_CAPABILITIES
+    family, major_raw, minor_raw = match.groups()
+    version = (int(major_raw), int(minor_raw or 0))
+    if family == "opus" and version >= (4, 6):
+        return ClaudeModelCapabilities(
+            context=1_000_000,
+            output=128_000,
+            supports_1m=True,
+            force_adaptive_thinking=True,
+        )
+    if family == "sonnet" and version >= (4, 6):
+        return ClaudeModelCapabilities(
+            context=1_000_000,
+            output=64_000,
+            supports_1m=True,
+            force_adaptive_thinking=True,
+        )
+    if family == "sonnet" and version >= (4, 5):
+        return ClaudeModelCapabilities(context=1_000_000, output=64_000, supports_1m=True)
+    if family == "fable" and version >= (5, 0):
+        return ClaudeModelCapabilities(
+            context=1_000_000,
+            output=128_000,
+            force_adaptive_thinking=True,
+        )
+    return _CLAUDE_FALLBACK_CAPABILITIES
+
+
+def claude_model_supports_1m(model_id: str) -> bool:
+    """Whether Claude Code should request the model's opt-in ``[1m]`` tier."""
+    return claude_model_capabilities(model_id).supports_1m
+
+
+def claude_model_token_limits(model_id: str) -> dict[str, int]:
+    """Return Pi metadata limits from the shared Claude capability policy."""
+    capabilities = claude_model_capabilities(model_id)
+    return {"context": capabilities.context, "output": capabilities.output}
+
+
 def _model_service_id(service: dict) -> str | None:
     """Extract the `system.ai.<model-name>` id from one model-service entry.
 
@@ -1354,10 +1524,13 @@ def discover_model_services(
         if candidates:
             claude_models[family] = candidates[0]
 
-    codex_models = [m for m in ids if "gpt-" in m]
+    # `gpt-oss-*` also contains "gpt-" but is a chat-completions-only OSS model
+    # (served via /ai-gateway/mlflow/v1), NOT an openai-responses codex model —
+    # exclude it here so it isn't offered under the codex provider (which 400s).
+    codex_models = [m for m in ids if "gpt-" in m and "gpt-oss" not in m]
     gemini_models = sorted([m for m in ids if "gemini-" in m], key=model_version_sort_key)
 
-    oss_models = [m for m in ids if any(family in m for family in _OSS_MODEL_FAMILIES)]
+    oss_models = [m for m in ids if _is_oss_chat_model(m)]
 
     if not (claude_models or codex_models or gemini_models or oss_models):
         sample = ", ".join(ids[:5])
@@ -2391,6 +2564,7 @@ def build_pi_base_urls(workspace: str) -> dict[str, str]:
         "claude": build_tool_base_url("claude", workspace),
         "openai": build_tool_base_url("codex", workspace),
         "gemini": build_tool_base_url("gemini", workspace) + "/v1beta",
+        "oss": f"{workspace}/ai-gateway/mlflow/v1",
     }
 
 
diff --git a/tests/test_agent_claude.py b/tests/test_agent_claude.py
index 60b4a6a..ed18ae0 100644
--- a/tests/test_agent_claude.py
+++ b/tests/test_agent_claude.py
@@ -48,6 +48,30 @@ def test_adds_1m_suffix_for_sonnet_4_6_and_later(self):
             overlay["env"]["ANTHROPIC_DEFAULT_SONNET_MODEL"] == "databricks-claude-sonnet-4-7[1m]"
         )
 
+    def test_adds_1m_suffix_for_sonnet_4_5(self):
+        # Sonnet 4.5 supports the 1M context window (its 1M beta shipped before
+        # Opus's), so it must get the [1m] suffix even though it predates the
+        # Opus 4.6 floor.
+        overlay, _ = claude.render_overlay(
+            WS, "s4", claude_models={"sonnet": "databricks-claude-sonnet-4-5"}
+        )
+        assert (
+            overlay["env"]["ANTHROPIC_DEFAULT_SONNET_MODEL"] == "databricks-claude-sonnet-4-5[1m]"
+        )
+
+    def test_does_not_add_1m_suffix_for_sonnet_4_4(self):
+        overlay, _ = claude.render_overlay(
+            WS, "s4", claude_models={"sonnet": "databricks-claude-sonnet-4-4"}
+        )
+        assert overlay["env"]["ANTHROPIC_DEFAULT_SONNET_MODEL"] == "databricks-claude-sonnet-4-4"
+
+    def test_does_not_add_1m_suffix_for_opus_4_5(self):
+        # Opus's 1M window starts at 4.6, so 4.5 stays on the default context.
+        overlay, _ = claude.render_overlay(
+            WS, "s4", claude_models={"opus": "databricks-claude-opus-4-5"}
+        )
+        assert overlay["env"]["ANTHROPIC_DEFAULT_OPUS_MODEL"] == "databricks-claude-opus-4-5"
+
     def test_does_not_add_1m_suffix_for_haiku(self):
         overlay, _ = claude.render_overlay(
             WS, "s4", claude_models={"haiku": "databricks-claude-haiku-4-6"}
@@ -72,6 +96,19 @@ def test_no_1m_suffix_for_model_services_haiku(self):
         )
         assert overlay["env"]["ANTHROPIC_DEFAULT_HAIKU_MODEL"] == "system.ai.claude-haiku-4-6"
 
+    @pytest.mark.parametrize(
+        ("model_id", "expected"),
+        [
+            ("system.ai.claude-opus-5", "system.ai.claude-opus-5[1m]"),
+            ("databricks-claude-sonnet-5", "databricks-claude-sonnet-5[1m]"),
+            ("system.ai.claude-opus-4-5", "system.ai.claude-opus-4-5"),
+            ("system.ai.claude-fable-5", "system.ai.claude-fable-5"),
+            ("not-a-claude-model", "not-a-claude-model"),
+        ],
+    )
+    def test_suffix_uses_shared_capability_policy(self, model_id, expected):
+        assert claude._maybe_add_1m_suffix(model_id) == expected
+
     def test_sets_anthropic_base_url(self):
         overlay, _ = claude.render_overlay(WS, "s4")
         assert overlay["env"]["ANTHROPIC_BASE_URL"] == f"{WS}/ai-gateway/anthropic"
diff --git a/tests/test_agent_opencode.py b/tests/test_agent_opencode.py
index 71ca2bc..f63d078 100644
--- a/tests/test_agent_opencode.py
+++ b/tests/test_agent_opencode.py
@@ -98,15 +98,24 @@ def test_glm_gets_token_limits(self):
         overlay, _ = opencode.render_overlay("system.ai.glm-5-2", "tok", _base_urls(), models)
         glm = overlay["provider"]["databricks-oss"]["models"]["system.ai.glm-5-2"]
         # OpenCode's schema requires both context and output on `limit`.
-        assert glm["limit"] == {"context": 200000, "output": 25000}
+        # Probed 2026-07-16: glm-5-2 is 1M context / 65536 output.
+        assert glm["limit"] == {"context": 1_000_000, "output": 65_536}
 
-    def test_non_glm_oss_model_has_no_output_cap(self):
+    def test_kimi_gets_token_limits(self):
+        # kimi is now a capped OSS family (128k context / 65536 output).
         models = {"oss": ["system.ai.kimi-k2-7-code"]}
         overlay, _ = opencode.render_overlay(
             "system.ai.kimi-k2-7-code", "tok", _base_urls(), models
         )
         kimi = overlay["provider"]["databricks-oss"]["models"]["system.ai.kimi-k2-7-code"]
-        assert "limit" not in kimi
+        assert kimi["limit"] == {"context": 128_000, "output": 65_536}
+
+    def test_uncapped_oss_model_has_no_limit(self):
+        # A model outside the limits table gets no `limit` (client default).
+        models = {"oss": ["system.ai.mystery-7b"]}
+        overlay, _ = opencode.render_overlay("system.ai.mystery-7b", "tok", _base_urls(), models)
+        entry = overlay["provider"]["databricks-oss"]["models"]["system.ai.mystery-7b"]
+        assert "limit" not in entry
 
     def test_token_in_api_key(self):
         models = {"anthropic": ["claude-sonnet"]}
diff --git a/tests/test_agent_pi.py b/tests/test_agent_pi.py
index 0afc5fb..b0711ee 100644
--- a/tests/test_agent_pi.py
+++ b/tests/test_agent_pi.py
@@ -17,6 +17,7 @@ def _base_urls() -> dict[str, str]:
         "claude": f"{WS}/ai-gateway/anthropic",
         "openai": f"{WS}/ai-gateway/codex/v1",
         "gemini": f"{WS}/ai-gateway/gemini/v1beta",
+        "oss": f"{WS}/ai-gateway/mlflow/v1",
     }
 
 
@@ -26,6 +27,7 @@ def _empty() -> dict:
         "claude_models": {},
         "codex_models": [],
         "gemini_models": [],
+        "oss_models": [],
     }
 
 
@@ -39,6 +41,7 @@ def _overlay(model: str, token: str = "tok", **kwargs):
         bundle["claude_models"],
         bundle["codex_models"],
         bundle["gemini_models"],
+        bundle["oss_models"],
     )
 
 
@@ -75,23 +78,117 @@ def test_openai_provider_uses_openai_responses(self):
         assert provider["api"] == "openai-responses"
         assert provider["baseUrl"] == f"{WS}/ai-gateway/codex/v1"
 
+    def test_gpt56_sol_model_entry_pins_1m_context(self):
+        # Gateway ids are custom to Pi, so explicit metadata is required to
+        # avoid its 128k custom-model default.
+        overlay, _ = _overlay("gpt-5-6-sol", codex_models=["gpt-5-6-sol"])
+        entry = overlay["providers"]["databricks-openai"]["models"][0]
+        assert entry["id"] == "gpt-5-6-sol"
+        assert entry["contextWindow"] == 1_050_000
+        assert entry["maxTokens"] == 128_000
+        assert entry["reasoning"] is True
+        assert entry["input"] == ["text", "image"]
+
+    def test_gpt_model_entries_use_model_specific_windows(self):
+        overlay, _ = _overlay(
+            "system.ai.gpt-5-2",
+            codex_models=[
+                "system.ai.gpt-5-2",
+                "databricks-gpt-5-4-nano",
+                "databricks-gpt-5-6-sol",
+            ],
+        )
+        windows = {
+            m["id"]: m["contextWindow"] for m in overlay["providers"]["databricks-openai"]["models"]
+        }
+        assert windows == {
+            "system.ai.gpt-5-2": 400_000,
+            "databricks-gpt-5-4-nano": 400_000,
+            "databricks-gpt-5-6-sol": 1_050_000,
+        }
+
+    def test_claude_entries_pin_limits_and_capabilities(self):
+        overlay, _ = _overlay(
+            "databricks-claude-opus-4-8",
+            claude_models={
+                "opus": "databricks-claude-opus-4-8",
+                "sonnet": "system.ai.claude-sonnet-4-5",
+                "haiku": "databricks-claude-haiku-4-5",
+                "fable": "system.ai.claude-fable-5",
+            },
+        )
+        entries = {m["id"]: m for m in overlay["providers"]["databricks-claude"]["models"]}
+        opus = entries["databricks-claude-opus-4-8"]
+        assert opus["contextWindow"] == 1_000_000
+        assert opus["maxTokens"] == 128_000
+        assert opus["reasoning"] is True
+        assert opus["input"] == ["text", "image"]
+        assert opus["compat"] == {"forceAdaptiveThinking": True}
+        assert entries["system.ai.claude-sonnet-4-5"]["contextWindow"] == 1_000_000
+        assert entries["system.ai.claude-sonnet-4-5"]["maxTokens"] == 64_000
+        assert entries["databricks-claude-haiku-4-5"]["contextWindow"] == 200_000
+        fable = entries["system.ai.claude-fable-5"]
+        assert fable["contextWindow"] == 1_000_000
+        assert fable["maxTokens"] == 128_000
+        assert fable["compat"] == {"forceAdaptiveThinking": True}
+
     def test_gemini_provider_uses_google_generative_ai(self):
         overlay, _ = _overlay("gemini-2", gemini_models=["gemini-2"])
         provider = overlay["providers"]["databricks-gemini"]
         assert provider["api"] == "google-generative-ai"
         assert provider["baseUrl"] == f"{WS}/ai-gateway/gemini/v1beta"
 
-    def test_all_three_providers_when_all_present(self):
+    def test_mlflow_provider_uses_openai_completions(self):
+        overlay, _ = _overlay("system.ai.glm-5-2", oss_models=["system.ai.glm-5-2"])
+        provider = overlay["providers"]["databricks-mlflow"]
+        assert provider["api"] == "openai-completions"
+        assert provider["baseUrl"] == f"{WS}/ai-gateway/mlflow/v1"
+        assert provider["compat"] == {"supportsStore": False, "supportsStrictMode": False}
+
+    def test_no_mlflow_provider_when_no_oss_models(self):
+        overlay, _ = _overlay("gpt-5", codex_models=["gpt-5"])
+        assert "databricks-mlflow" not in overlay.get("providers", {})
+
+    def test_all_four_providers_when_all_present(self):
         overlay, _ = _overlay(
             "claude-sonnet",
             claude_models={"sonnet": "claude-sonnet"},
             codex_models=["gpt-5"],
             gemini_models=["gemini-2"],
+            oss_models=["system.ai.glm-5-2"],
         )
         assert set(overlay["providers"].keys()) == {
             "databricks-claude",
             "databricks-openai",
             "databricks-gemini",
+            "databricks-mlflow",
+        }
+
+
+class TestRenderOverlayOssEnrichment:
+    """OSS mlflow model entries carry reasoning + contextWindow + maxTokens
+    from the shared databricks.model_token_limits / model_is_reasoning tables."""
+
+    def test_reasoning_model_enriched(self):
+        overlay, _ = _overlay("system.ai.glm-5-2", oss_models=["system.ai.glm-5-2"])
+        entry = overlay["providers"]["databricks-mlflow"]["models"][0]
+        assert entry["id"] == "system.ai.glm-5-2"
+        assert entry["reasoning"] is True
+        assert entry["contextWindow"] == 1_000_000
+        assert entry["maxTokens"] == 65_536
+
+    def test_unvalidated_model_has_no_inferred_metadata(self):
+        # Discovery does not offer this model; even if supplied directly, Pi
+        # must not infer capabilities for an unvalidated coding model.
+        overlay, _ = _overlay("system.ai.inkling", oss_models=["system.ai.inkling"])
+        entry = overlay["providers"]["databricks-mlflow"]["models"][0]
+        assert entry == {"id": "system.ai.inkling"}
+
+    def test_unknown_oss_model_bare(self):
+        # No limits/reasoning table entry -> only id, client keeps defaults.
+        overlay, _ = _overlay("system.ai.mystery-7b", oss_models=["system.ai.mystery-7b"])
+        assert overlay["providers"]["databricks-mlflow"]["models"][0] == {
+            "id": "system.ai.mystery-7b"
         }
 
 
@@ -193,6 +290,10 @@ def test_prefixes_gemini_model(self):
         overlay, _ = _overlay("gemini-2", gemini_models=["gemini-2"])
         assert overlay["model"] == "databricks-gemini/gemini-2"
 
+    def test_prefixes_oss_model(self):
+        overlay, _ = _overlay("system.ai.glm-5-2", oss_models=["system.ai.glm-5-2"])
+        assert overlay["model"] == "databricks-mlflow/system.ai.glm-5-2"
+
     def test_preserves_already_prefixed_model(self):
         overlay, _ = _overlay(
             "databricks-claude/claude-sonnet",
@@ -220,14 +321,38 @@ def test_falls_back_to_haiku(self):
         state = {"claude_models": {"haiku": "h4"}}
         assert pi.default_model(state) == "h4"
 
-    def test_falls_back_to_codex(self):
-        state = {"claude_models": {}, "codex_models": ["gpt-5"]}
-        assert pi.default_model(state) == "gpt-5"
+    def test_falls_back_to_newest_codex_model(self):
+        state = {
+            "claude_models": {},
+            "codex_models": ["databricks-gpt-5", "system.ai.gpt-5-6-sol", "gpt-5-5"],
+        }
+        assert pi.default_model(state) == "system.ai.gpt-5-6-sol"
+
+    def test_falls_back_to_generic_responses_endpoint(self):
+        state = {"claude_models": {}, "codex_models": ["c1"]}
+        assert pi.default_model(state) == "c1"
+
+    def test_does_not_route_gpt_oss_to_responses(self):
+        state = {
+            "claude_models": {},
+            "codex_models": ["gpt-oss-120b"],
+            "gemini_models": ["gemini-2"],
+        }
+        assert pi.default_model(state) == "gemini-2"
 
     def test_falls_back_to_gemini(self):
         state = {"claude_models": {}, "codex_models": [], "gemini_models": ["gemini-2"]}
         assert pi.default_model(state) == "gemini-2"
 
+    def test_falls_back_to_oss_last(self):
+        state = {
+            "claude_models": {},
+            "codex_models": [],
+            "gemini_models": [],
+            "oss_models": ["system.ai.glm-5-2"],
+        }
+        assert pi.default_model(state) == "system.ai.glm-5-2"
+
     def test_returns_none_when_empty(self):
         assert pi.default_model({}) is None
         assert (
@@ -296,6 +421,7 @@ def test_stale_managed_providers_removed_before_merge(self, tmp_path, monkeypatc
                 "databricks-claude": {"old": True},
                 "databricks-openai": {"old": True},
                 "databricks-gemini": {"old": True},
+                "databricks-mlflow": {"old": True},
                 "user-provider": {"keep": True},
             }
         }
@@ -311,6 +437,7 @@ def test_stale_managed_providers_removed_before_merge(self, tmp_path, monkeypatc
         providers = written.get("providers", {})
         assert providers.get("databricks-claude") != {"old": True}
         assert "old" not in providers.get("databricks-claude", {})
+        assert "databricks-mlflow" not in providers
         assert providers.get("user-provider") == {"keep": True}
 
     def test_legacy_providers_removed_on_upgrade(self, tmp_path, monkeypatch):
diff --git a/tests/test_agents_init.py b/tests/test_agents_init.py
index 97acf30..91c3202 100644
--- a/tests/test_agents_init.py
+++ b/tests/test_agents_init.py
@@ -189,6 +189,14 @@ def test_pi_available_with_codex(self):
     def test_pi_available_with_gemini(self):
         assert check_gateway_endpoint({"gemini_models": ["gemini-2"]}, "pi") is True
 
+    def test_pi_available_with_oss(self):
+        assert check_gateway_endpoint({"oss_models": ["system.ai.glm-5-2"]}, "pi") is True
+
+    def test_pi_oss_discovery_reason_is_reported(self):
+        state = {"_discovery_reasons": {"oss": "no validated OSS models"}}
+        detail = agents_mod._availability_failure_detail("pi", state)
+        assert detail == " (oss discovery: no validated OSS models)"
+
     def test_pi_unavailable_when_no_models(self):
         assert check_gateway_endpoint({}, "pi") is False
 
@@ -243,6 +251,15 @@ def test_pi_falls_back_to_gemini(self):
         state = {"claude_models": {}, "codex_models": [], "gemini_models": ["gemini-2"]}
         assert default_model_for_tool("pi", state) == "gemini-2"
 
+    def test_pi_falls_back_to_oss(self):
+        state = {
+            "claude_models": {},
+            "codex_models": [],
+            "gemini_models": [],
+            "oss_models": ["system.ai.glm-5-2"],
+        }
+        assert default_model_for_tool("pi", state) == "system.ai.glm-5-2"
+
     def test_pi_returns_none_when_no_models(self):
         assert default_model_for_tool("pi", {}) is None
 
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 83ed6df..2c600d0 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -27,6 +27,17 @@ def _strip_ansi(text: str) -> str:
 TOOLS = ["codex", "claude", "gemini", "opencode"]
 
 
+def test_oss_discovery_diagnostic_names_all_consumers(monkeypatch):
+    import ucode.cli as cli_mod
+
+    notes = []
+    monkeypatch.setattr(cli_mod, "print_note", notes.append)
+
+    cli_mod._print_discovery_diagnostics({"_discovery_reasons": {"oss": "not found"}})
+
+    assert notes[0] == "OSS models (needed for: opencode, pi): not found"
+
+
 @pytest.fixture(autouse=True)
 def no_state_writes():
     """Prevent any test from writing to the real state file on disk."""
diff --git a/tests/test_databricks.py b/tests/test_databricks.py
index 7e1a73a..45d03ad 100644
--- a/tests/test_databricks.py
+++ b/tests/test_databricks.py
@@ -173,19 +173,154 @@ def _model_service(model_id: str) -> dict:
 
 class TestModelTokenLimits:
     def test_glm_is_capped(self):
+        # Probed 2026-07-16: glm-5-2 accepts 1M context / 65536 output.
         assert db_mod.model_token_limits("system.ai.glm-5-2") == {
-            "context": 200_000,
-            "output": 25_000,
+            "context": 1_000_000,
+            "output": 65_536,
         }
 
-    def test_glm_matches_any_version(self):
-        assert db_mod.model_token_limits("system.ai.glm-4-6-flash") == {
+    @pytest.mark.parametrize(
+        "model_id",
+        ["system.ai.glm-4-6-flash", "system.ai.glm-future"],
+    )
+    def test_other_glm_versions_keep_conservative_limits(self, model_id):
+        assert db_mod.model_token_limits(model_id) == {
             "context": 200_000,
             "output": 25_000,
         }
 
-    def test_uncapped_model_returns_none(self):
-        assert db_mod.model_token_limits("system.ai.kimi-k2-7-code") is None
+    def test_kimi_is_capped(self):
+        assert db_mod.model_token_limits("system.ai.kimi-k2-7-code") == {
+            "context": 128_000,
+            "output": 65_536,
+        }
+
+    def test_unvalidated_families_return_none(self):
+        for model_id in (
+            "system.ai.inkling",
+            "system.ai.gpt-oss-120b",
+            "system.ai.llama-4-maverick",
+            "system.ai.qwen35-122b-a10b",
+            "system.ai.gemma-3-12b",
+            "system.ai.deepseek-v3",
+        ):
+            assert db_mod.model_token_limits(model_id) is None
+
+    def test_embedding_model_returns_none_not_fallback(self):
+        assert db_mod.model_token_limits("system.ai.qwen3-embedding-0-6b") is None
+
+
+class TestGptModelTokenLimits:
+    def test_gpt56_sol_serves_1m_context_across_id_forms(self):
+        for model_id in (
+            "gpt-5.6-sol",
+            "system.ai.gpt-5-6-sol",
+            "databricks-gpt-5-6-sol",
+            "databricks-openai/gpt-5.6-sol",
+        ):
+            assert db_mod.gpt_model_token_limits(model_id) == {
+                "context": 1_050_000,
+                "output": 128_000,
+            }
+
+    def test_gpt5_windows_are_model_specific(self):
+        assert db_mod.gpt_model_token_limits("system.ai.gpt-5-2")["context"] == 400_000
+        assert db_mod.gpt_model_token_limits("databricks-gpt-5-4")["context"] == 272_000
+        assert db_mod.gpt_model_token_limits("databricks-gpt-5-4-nano")["context"] == 400_000
+        assert db_mod.gpt_model_token_limits("gpt-5.5-pro")["context"] == 1_050_000
+
+    def test_gpt41_window(self):
+        assert db_mod.gpt_model_token_limits("databricks-gpt-4-1") == {
+            "context": 1_047_576,
+            "output": 32_768,
+        }
+
+    @pytest.mark.parametrize(
+        "model_id",
+        ["gpt-5.40", "gpt-4.10", "gpt-6-turbo"],
+    )
+    def test_unknown_specific_gpt_uses_family_or_conservative_fallback(self, model_id):
+        expected = (
+            {"context": 400_000, "output": 128_000}
+            if model_id == "gpt-5.40"
+            else {"context": 8_192, "output": 8_192}
+            if model_id == "gpt-4.10"
+            else {"context": 128_000, "output": 16_384}
+        )
+        assert db_mod.gpt_model_token_limits(model_id) == expected
+
+    def test_route_prefixes_are_stripped_case_insensitively(self):
+        assert db_mod.gpt_model_token_limits("SYSTEM.AI.GPT-5-6-SOL") == {
+            "context": 1_050_000,
+            "output": 128_000,
+        }
+        assert db_mod.gpt_model_token_limits("DATABRICKS-GPT-4-1") == {
+            "context": 1_047_576,
+            "output": 32_768,
+        }
+
+    def test_preferred_gpt_model_uses_semantic_version_across_prefixes(self):
+        assert (
+            db_mod.preferred_gpt_model(
+                ["databricks-gpt-5", "system.ai.gpt-5-6-sol", "databricks-gpt-5-5"]
+            )
+            == "system.ai.gpt-5-6-sol"
+        )
+        assert db_mod.preferred_gpt_model(["not-gpt", "claude-opus-4-8"]) == "not-gpt"
+
+    def test_preferred_gpt_model_falls_back_to_generic_responses_endpoint(self):
+        assert db_mod.preferred_gpt_model(["c1", "custom-responses"]) == "c1"
+
+    def test_preferred_gpt_model_excludes_gpt_oss(self):
+        assert db_mod.preferred_gpt_model(["gpt-oss-120b", "c1"]) == "c1"
+        assert db_mod.preferred_gpt_model(["system.ai.gpt-oss-120b"]) is None
+
+
+class TestClaudeModelCapabilities:
+    @pytest.mark.parametrize(
+        ("model_id", "context", "output", "supports_1m", "adaptive"),
+        [
+            ("databricks-claude-opus-4-5", 200_000, 64_000, False, False),
+            ("databricks-claude-opus-4-6", 1_000_000, 128_000, True, True),
+            ("system.ai.claude-opus-5", 1_000_000, 128_000, True, True),
+            ("claude-sonnet-4-4", 200_000, 64_000, False, False),
+            ("system.ai.claude-sonnet-4-5", 1_000_000, 64_000, True, False),
+            ("claude-sonnet-4-6[1m]", 1_000_000, 64_000, True, True),
+            ("claude-sonnet-5", 1_000_000, 64_000, True, True),
+            ("claude-haiku-4-5", 200_000, 64_000, False, False),
+            ("system.ai.claude-fable-5", 1_000_000, 128_000, False, True),
+            ("claude-future", 200_000, 64_000, False, False),
+        ],
+    )
+    def test_shared_capability_policy(
+        self,
+        model_id,
+        context,
+        output,
+        supports_1m,
+        adaptive,
+    ):
+        capabilities = db_mod.claude_model_capabilities(model_id)
+        assert capabilities.context == context
+        assert capabilities.output == output
+        assert capabilities.supports_1m is supports_1m
+        assert capabilities.force_adaptive_thinking is adaptive
+        assert db_mod.claude_model_supports_1m(model_id) is supports_1m
+        assert db_mod.claude_model_token_limits(model_id) == {
+            "context": context,
+            "output": output,
+        }
+
+
+class TestModelIsReasoning:
+    def test_reasoning_families(self):
+        assert db_mod.model_is_reasoning("system.ai.glm-5-2") is True
+        assert db_mod.model_is_reasoning("system.ai.kimi-k2-7-code") is True
+
+    def test_unvalidated_families_are_not_marked_reasoning(self):
+        assert db_mod.model_is_reasoning("system.ai.inkling") is False
+        assert db_mod.model_is_reasoning("system.ai.qwen35-122b-a10b") is False
+        assert db_mod.model_is_reasoning("system.ai.gpt-oss-120b") is False
 
 
 class TestDiscoverModelServices:
@@ -220,19 +355,20 @@ def test_buckets_families_by_name(self, monkeypatch):
         assert codex == ["system.ai.gpt-5"]
         # Gemini ordered newest-first via the shared sort key.
         assert gemini[0] == "system.ai.gemini-3-5-flash"
-        # kimi and glm are the allowlisted OSS families; llama is not.
+        # Only coding-harness-validated OSS families are offered.
         assert oss == ["system.ai.glm-5-2", "system.ai.kimi-k2-7-code"]
 
-    def test_oss_allowlist_drops_unsupported_families(self, monkeypatch):
-        # Only kimi/glm are allowlisted; other families are dropped.
+    def test_oss_allowlist_drops_unvalidated_families(self, monkeypatch):
         payload = {
             "model_services": [
                 _model_service("system.ai.glm-5-2"),
                 _model_service("system.ai.kimi-k2-7-code"),
-                _model_service("system.ai.qwen-3-coder"),
+                _model_service("system.ai.qwen35-122b-a10b"),
+                _model_service("system.ai.inkling"),
+                _model_service("system.ai.llama-4-maverick"),
+                _model_service("system.ai.gemma-3-12b"),
                 _model_service("system.ai.deepseek-v3"),
-                _model_service("system.ai.gte-large-embed"),
-                _model_service("system.ai.bge-reranker-v2"),
+                _model_service("system.ai.qwen3-embedding-0-6b"),
             ]
         }
         monkeypatch.setattr(
@@ -245,6 +381,25 @@ def test_oss_allowlist_drops_unsupported_families(self, monkeypatch):
         assert (claude, codex, gemini) == ({}, [], [])
         assert oss == ["system.ai.glm-5-2", "system.ai.kimi-k2-7-code"]
 
+    def test_gpt_oss_is_neither_selectable_oss_nor_codex(self, monkeypatch):
+        # Keep the independent codex exclusion: gpt-oss contains "gpt-" but
+        # cannot use the Responses API, even though it is not an offered model.
+        payload = {
+            "model_services": [
+                _model_service("system.ai.gpt-5"),
+                _model_service("system.ai.gpt-oss-120b"),
+            ]
+        }
+        monkeypatch.setattr(
+            db_mod, "_http_get_json", lambda url, token, timeout=10: (payload, None)
+        )
+
+        _, codex, _, oss, _ = db_mod.discover_model_services(WS, "token")
+
+        assert codex == ["system.ai.gpt-5"]
+        assert "system.ai.gpt-oss-120b" not in oss
+        assert "system.ai.gpt-oss-120b" not in codex
+
     def test_paginates_via_next_page_token(self, monkeypatch):
         pages = {
             None: {
@@ -281,7 +436,8 @@ def test_http_failure_returns_reason(self, monkeypatch):
         assert reason == "HTTP 500 Server Error"
 
     def test_no_matching_families_reports_sample(self, monkeypatch):
-        payload = {"model_services": [_model_service("system.ai.llama-4-maverick")]}
+        # deepseek is outside every claude/gpt/gemini/oss family bucket.
+        payload = {"model_services": [_model_service("system.ai.deepseek-v3")]}
         monkeypatch.setattr(
             db_mod, "_http_get_json", lambda url, token, timeout=10: (payload, None)
         )
@@ -289,7 +445,7 @@ def test_no_matching_families_reports_sample(self, monkeypatch):
         claude, codex, gemini, oss, reason = db_mod.discover_model_services(WS, "token")
 
         assert (claude, codex, gemini, oss) == ({}, [], [], [])
-        assert reason is not None and "llama-4-maverick" in reason
+        assert reason is not None and "deepseek-v3" in reason
 
     def test_ignores_non_system_ai_schemas(self, monkeypatch):
         # The metastore listing returns services from every schema; only