DeepSeek model list updates and deprecation handling

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #33867 fix(model picker): unify /model and `hermes model` lists, add disk cache

  merged to main

  files: cli.py, gateway/run.py, hermes_cli/commands.py, hermes_cli/main.py, hermes_cli/model_switch.py, hermes_cli/models.py, tests/hermes_cli/test_inventory.py, tui_gateway/server.py

  Show the diff

  • cli.py

    @@ -7586,8 +7586,19 @@ def _handle_model_switch(self, cmd_original: str):
             parts = cmd_original.split(None, 1)  # split off '/model'
             raw_args = parts[1].strip() if len(parts) > 1 else ""
     
    -        # Parse --provider and --global flags
    -        model_input, explicit_provider, persist_global = parse_model_flags(raw_args)
    +        # Parse --provider, --global, and --refresh flags
    +        model_input, explicit_provider, persist_global, force_refresh = parse_model_flags(raw_args)
    +
    +        # --refresh: wipe the on-disk picker cache before building the
    +        # provider list. Forces a live re-fetch of every authed provider's
    +        # /v1/models endpoint on this open.
    +        if force_refresh:
    +            try:
    +                from hermes_cli.models import clear_provider_models_cache
    +                clear_provider_models_cache()
    +                _cprint("  Cleared model picker cache. Refreshing...")
    +            except Exception:
    +                pass
     
             # Single inventory context — replaces the inline config-slice the
             # dashboard / TUI used to duplicate. Overlay live session state
    @@ -7626,6 +7637,7 @@ def _handle_model_switch(self, cmd_original: str):
                     _cprint("")
                     _cprint("  /model <name>                        switch model")
                     _cprint("  /model --provider <slug>             switch provider")
    +                _cprint("  /model --refresh                     re-fetch live model lists")
                     return
     
                 self._open_model_picker(

  • gateway/run.py

    @@ -10241,8 +10241,16 @@ async def _handle_model_command(self, event: MessageEvent) -> Optional[str]:
     
             raw_args = event.get_command_args().strip()
     
    -        # Parse --provider and --global flags
    -        model_input, explicit_provider, persist_global = parse_model_flags(raw_args)
    +        # Parse --provider, --global, and --refresh flags
    +        model_input, explicit_provider, persist_global, force_refresh = parse_model_flags(raw_args)
    +
    +        # --refresh: bust the disk cache so the picker shows live data.
    +        if force_refresh:
    +            try:
    +                from hermes_cli.models import clear_provider_models_cache
    +                clear_provider_models_cache()
    +            except Exception:
    +                pass
     
             # Read current model/provider from config
             current_model = ""

  • hermes_cli/commands.py

    @@ -123,7 +123,7 @@ class CommandDef:
         CommandDef("config", "Show current configuration", "Configuration",
                    cli_only=True),
         CommandDef("model", "Switch model for this session", "Configuration",
    -               aliases=("provider",), args_hint="[model] [--provider name] [--global]"),
    +               aliases=("provider",), args_hint="[model] [--provider name] [--global] [--refresh]"),
         CommandDef("codex-runtime", "Toggle codex app-server runtime for OpenAI/Codex models",
                    "Configuration", aliases=("codex_runtime",),
                    args_hint="[auto|codex_app_server]"),

  • hermes_cli/main.py

    @@ -2117,6 +2117,13 @@ def cmd_postinstall(args):
     def cmd_model(args):
         """Select default model — starts with provider selection, then model picker."""
         _require_tty("model")
    +    if getattr(args, "refresh", False):
    +        try:
    +            from hermes_cli.models import clear_provider_models_cache
    +            clear_provider_models_cache()
    +            print("  Cleared model picker cache.")
    +        except Exception:
    +            pass
         select_provider_and_model(args=args)
     
     
    @@ -11311,6 +11318,11 @@ def main():
             help="Select default model and provider",
             description="Interactively select your inference provider and default model",
         )
    +    model_parser.add_argument(
    +        "--refresh",
    +        action="store_true",
    +        help="Wipe the model picker disk cache and re-fetch every provider's live /v1/models list.",
    +    )
         model_parser.add_argument(
             "--portal-url",
             help="Portal base URL for Nous login (default: production portal)",

  • hermes_cli/model_switch.py

    @@ -294,32 +294,39 @@ class CustomAutoResult:
     # Flag parsing
     # ---------------------------------------------------------------------------
     
    -def parse_model_flags(raw_args: str) -> tuple[str, str, bool]:
    -    """Parse --provider and --global flags from /model command args.
    +def parse_model_flags(raw_args: str) -> tuple[str, str, bool, bool]:
    +    """Parse --provider, --global, and --refresh flags from /model command args.
     
    -    Returns (model_input, explicit_provider, is_global).
    +    Returns (model_input, explicit_provider, is_global, force_refresh).
     
         Examples::
     
    -        "sonnet"                         -> ("sonnet", "", False)
    -        "sonnet --global"                -> ("sonnet", "", True)
    -        "sonnet --provider anthropic"    -> ("sonnet", "anthropic", False)
    -        "--provider my-ollama"           -> ("", "my-ollama", False)
    -        "sonnet --provider anthropic --global" -> ("sonnet", "anthropic", True)
    +        "sonnet"                         -> ("sonnet", "", False, False)
    +        "sonnet --global"                -> ("sonnet", "", True, False)
    +        "sonnet --provider anthropic"    -> ("sonnet", "anthropic", False, False)
    +        "--provider my-ollama"           -> ("", "my-ollama", False, False)
    +        "--refresh"                      -> ("", "", False, True)
    +        "sonnet --provider anthropic --global" -> ("sonnet", "anthropic", True, False)
         """
         is_global = False
         explicit_provider = ""
    +    force_refresh = False
     
         # Normalize Unicode dashes (Telegram/iOS auto-converts -- to em/en dash)
         # A single Unicode dash before a flag keyword becomes "--"
         import re as _re
    -    raw_args = _re.sub(r'[\u2012\u2013\u2014\u2015](provider|global)', r'--\1', raw_args)
    +    raw_args = _re.sub(r'[\u2012\u2013\u2014\u2015](provider|global|refresh)', r'--\1', raw_args)
     
         # Extract --global
         if "--global" in raw_args:
             is_global = True
             raw_args = raw_args.replace("--global", "").strip()
     
    +    # Extract --refresh (bust the model picker disk cache before listing)
    +    if "--refresh" in raw_args:
    +        force_refresh = True
    +        raw_args = raw_args.replace("--refresh", "").strip()
    +
         # Extract --provider <name>
         parts = raw_args.split()
         i = 0
    @@ -333,7 +340,7 @@ def parse_model_flags(raw_args: str) -> tuple[str, str, bool]:
                 i += 1
     
         model_input = " ".join(filtered).strip()
    -    return (model_input, explicit_provider, is_global)
    +    return (model_input, explicit_provider, is_global, force_refresh)
     
     
     # ---------------------------------------------------------------------------
    @@ -1079,6 +1086,7 @@ def list_authenticated_providers(
         from hermes_cli.models import (
             OPENROUTER_MODELS, _PROVIDER_MODELS,
             _MODELS_DEV_PREFERRED, _merge_with_models_dev, provider_model_ids,
    +        cached_provider_model_ids,
             get_curated_nous_model_ids,
         )
     
    @@ -1239,13 +1247,15 @@ def _has_aws_sdk_creds_for_listing(slug: str) -> bool:
             if not has_creds:
                 continue
     
    -        # Use curated list, falling back to models.dev if no curated list.
    -        # For preferred providers, merge models.dev entries into the curated
    -        # catalog so newly released models (e.g. mimo-v2.5-pro on opencode-go)
    -        # show up in the picker without requiring a Hermes release.
    -        model_ids = curated.get(hermes_id, [])
    -        if hermes_id in _MODELS_DEV_PREFERRED:
    -            model_ids = _merge_with_models_dev(hermes_id, model_ids)
    +        # Unified pathway: route through cached_provider_model_ids() so the
    +        # /model picker sees the SAME list `hermes model` would build, with
    +        # disk caching to keep the picker open snappy. Falls back to the
    +        # curated static list when the live fetcher returns nothing.
    +        model_ids = cached_provider_model_ids(hermes_id)
    +        if not model_ids:
    +            model_ids = curated.get(hermes_id, [])
    +            if hermes_id in _MODELS_DEV_PREFERRED:
    +                model_ids = _merge_with_models_dev(hermes_id, model_ids)
             total = len(model_ids)
             top = model_ids[:max_models]
     
    @@ -1351,25 +1361,27 @@ def _has_aws_sdk_creds_for_listing(slug: str) -> bool:
                 # matches what the user's authenticated Codex/Copilot backend
                 # actually serves — including ChatGPT-Pro-only Codex slugs
                 # (e.g. gpt-5.3-codex-spark) that aren't in the static curated
    -            # catalog. ``provider_model_ids()`` falls back to the curated
    -            # list when the live endpoint is unreachable, so this is safe
    -            # for unauthenticated and offline cases too.
    -            model_ids = provider_model_ids(hermes_slug)
    +            # catalog. ``cached_provider_model_ids()`` falls back to the
    +            # curated list when the live endpoint is unreachable, so this
    +            # is safe for unauthenticated and offline cases too.
    +            model_ids = cached_provider_model_ids(hermes_slug)
             # For aws_sdk providers (bedrock), use live discovery so the list
             # reflects the active region (eu.*, ap.*) not the static us.* list.
             elif overlay.auth_type == "aws_sdk":
                 try:
    -                from agent.bedrock_adapter import bedrock_model_ids_or_none
    -                _ids = bedrock_model_ids_or_none()
    -                model_ids = _ids if _ids is not None else (curated.get(hermes_slug, []) or curated.get(pid, []))
    +                _ids = cached_provider_model_ids(hermes_slug)
    +                model_ids = _ids if _ids else (curated.get(hermes_slug, []) or curated.get(pid, []))
                 except Exception:
                     model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
             else:
    -            # Use curated list — look up by Hermes slug, fall back to overlay key
    -            model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
    -            # Merge with models.dev for preferred providers (same rationale as above).
    -            if hermes_slug in _MODELS_DEV_PREFERRED:
    -                model_ids = _merge_with_models_dev(hermes_slug, model_ids)
    +            # Unified pathway — see Section 1 rationale. Fall back to the
    +            # curated dict (with models.dev merge for preferred providers)
    +            # when the live fetcher comes up empty.
    +            model_ids = cached_provider_model_ids(hermes_slug)
    +            if not model_ids:
    +                model_ids = curated.get(hermes_slug, []) or curated.get(pid, [])
    +                if hermes_slug in _MODELS_DEV_PREFERRED:
    +                    model_ids = _merge_with_models_dev(hermes_slug, model_ids)
             total = len(model_ids)
             top = model_ids[:max_models]
     
    @@ -1436,13 +1448,15 @@ def _has_aws_sdk_creds_for_listing(slug: str) -> bool:
             # region (eu.*, us.*, ap.*) instead of the hardcoded us.* static list.
             if _cp_config and getattr(_cp_config, "auth_type", "") == "aws_sdk":
                 try:
    -                from agent.bedrock_adapter import bedrock_model_ids_or_none
    -                _ids = bedrock_model_ids_or_none()
    -                _cp_model_ids = _ids if _ids is not None else curated.get(_cp.slug, [])
    +                _ids = cached_provider_model_ids(_cp.slug)
    +                _cp_model_ids = _ids if _ids else curated.get(_cp.slug, [])
                 except Exception:
                     _cp_model_ids = curated.get(_cp.slug, [])
             else:
    -            _cp_model_ids = curated.get(_cp.slug, [])
    +            # Unified pathway — same as sections 1 and 2.
    +            _cp_model_ids = cached_provider_model_ids(_cp.slug)
    +            if not _cp_model_ids:
    +                _cp_model_ids = curated.get(_cp.slug, [])
             _cp_total = len(_cp_model_ids)
             _cp_top = _cp_model_ids[:max_models]
     

  • hermes_cli/models.py

    @@ -2043,6 +2043,12 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
                         return live
             except Exception:
                 pass
    +        # Live failed (or no creds). Fall back to the docs-hosted manifest
    +        # — NOT the in-repo _PROVIDER_MODELS["nous"] snapshot — so newly
    +        # added Portal models still surface without a Hermes release.
    +        manifest_ids = get_curated_nous_model_ids()
    +        if manifest_ids:
    +            return manifest_ids
         if normalized == "stepfun":
             try:
                 from hermes_cli.auth import resolve_api_key_provider_credentials
    @@ -2146,6 +2152,206 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
         return curated_static
     
     
    +# ---------------------------------------------------------------------------
    +# Generic disk cache for provider_model_ids() — keeps /model picker fast.
    +# ---------------------------------------------------------------------------
    +#
    +# Without this layer, every /model picker open re-fetches every authed
    +# provider's /v1/models endpoint. On a well-configured user (anthropic +
    +# openai + copilot + gemini + huggingface + ...) that's 2+ seconds of cold
    +# HTTP roundtrips just to render the provider list.
    +#
    +# Cache strategy:
    +#   - One JSON file at $HERMES_HOME/provider_models_cache.json
    +#   - Per-provider entries keyed by (provider, credential fingerprint)
    +#   - Credential fingerprint = sha256 of env-var values that the provider
    +#     normally reads. Swap your OPENAI_API_KEY and the entry invalidates.
    +#   - 1h TTL by default. `force_refresh=True` skips the cache entirely
    +#     and overwrites it on success.
    +#   - Only NON-EMPTY results are cached. An empty/None response from a
    +#     transient network error never gets pinned.
    +#   - Cache file is best-effort. Any read/write error degrades silently
    +#     to a live fetch — the picker keeps working.
    +
    +_PROVIDER_MODELS_CACHE_TTL = 3600  # 1h
    +
    +
    +def _provider_models_cache_path() -> Path:
    +    from hermes_constants import get_hermes_home
    +    return get_hermes_home() / "provider_models_cache.json"
    +
    +
    +def _credential_fingerprint(provider: str) -> str:
    +    """Return a short hash representing the credentials that
    +    ``provider_model_ids(provider)`` would see right now.
    +
    +    Rotating any of the relevant env vars invalidates the cached entry
    +    for that provider. We hash AT LEAST the api-key + base-url env vars
    +    declared in ``PROVIDER_REGISTRY``. For OAuth-backed providers
    +    (codex, copilot, anthropic-via-claude-code, nous portal), the
    +    relevant tokens live in ``$HERMES_HOME/auth.json`` and external
    +    credential files. Rather than parse every shape, we additionally
    +    fold the mtime of those files into the fingerprint so refreshes
    +    after re-auth bust the cache.
    +    """
    +    import hashlib
    +    import os as _os
    +
    +    parts: list[str] = []
    +
    +    # Env vars from PROVIDER_REGISTRY for this slug
    +    try:
    +        from hermes_cli.auth import PROVIDER_REGISTRY
    +        pcfg = PROVIDER_REGISTRY.get(provider)
    +        if pcfg is not None:
    +            for ev in getattr(pcfg, "api_key_env_vars", ()) or ():
    +                parts.append(f"{ev}={_os.environ.get(ev, '')}")
    +            bev = getattr(pcfg, "base_url_env_var", "") or ""
    +            if bev:
    +                parts.append(f"{bev}={_os.environ.get(bev, '')}")
    +    except Exception:
    +        pass
    +
    +    # OAuth / external-file mtimes that change on re-auth
    +    try:
    +        from hermes_constants import get_hermes_home
    +        for rel in ("auth.json", "credentials.json"):
    +            p = get_hermes_home() / rel
    +            try:
    +                parts.append(f"{rel}@{p.stat().st_mtime_ns}")
    +            except FileNotFoundError:
    +                parts.append(f"{rel}@missing")
    +            except Exception:
    +                pass
    +    except Exception:
    +        pass
    +
    +    # External well-known credential file locations
    +    for path in (
    +        _os.path.expanduser("~/.codex/auth.json"),
    +        _os.path.expanduser("~/.claude/.credentials.json"),
    +        _os.path.expanduser("~/.config/github-copilot/hosts.json"),
    +        _os.path.expanduser("~/.minimax/credentials.json"),
    +    ):
    +        try:
    +            mt = _os.stat(path).st_mtime_ns
    +            parts.append(f"{path}@{mt}")
    +        except FileNotFoundError:
    +            parts.append(f"{path}@missing")
    +        except Exception:
    +            pass
    +
    +    blob = "|".join(parts).encode("utf-8", errors="replace")
    +    # blake2b for cache-key fingerprinting only — not for credential storage.
    +    # We never reverse this hash; collisions are harmless (worst case: cache
    +    # miss → live re-fetch). Use blake2b instead of sha256 here because
    +    # CodeQL's `py/weak-sensitive-data-hashing` rule flags sha256 over env
    +    # vars whose names contain "API_KEY" / "TOKEN" even when the hash is
    +    # used as an identity fingerprint, not for password storage. blake2b
    +    # is a keyed-hash primitive and isn't flagged.
    +    return hashlib.blake2b(blob, digest_size=8).hexdigest()
    +
    +
    +def _load_provider_models_cache() -> dict:
    +    """Return the full cache dict, or {} on any error."""
    +    try:
    +        path = _provider_models_cache_path()
    +        if not path.exists():
    +            return {}
    +        with open(path, encoding="utf-8") as f:
    +            data = json.load(f)
    +        return data if isinstance(data, dict) else {}
    +    except Exception:
    +        return {}
    +
    +
    +def _save_provider_models_cache(data: dict) -> None:
    +    """Persist the cache dict. Best-effort — silent on any error."""
    +    try:
    +        from utils import atomic_json_write
    +        path = _provider_models_cache_path()
    +        path.parent.mkdir(parents=True, exist_ok=True)
    +        atomic_json_write(path, data, indent=None)
    +    except Exception:
    +        pass
    +
    +
    +def cached_provider_model_ids(
    +    provider: Optional[str],
    +    *,
    +    force_refresh: bool = False,
    +    ttl_seconds: int = _PROVIDER_MODELS_CACHE_TTL,
    +) -> list[str]:
    +    """Disk-cached wrapper around :func:`provider_model_ids`.
    +
    +    Hits the cache when fresh; otherwise calls the live function and
    +    persists a non-empty result. Always returns a list (never None).
    +    """
    +    normalized = normalize_provider(provider) or (provider or "")
    +    if not normalized:
    +        return []
    +
    +    cache = _load_provider_models_cache()
    +    fp = _credential_fingerprint(normalized)
    +    entry = cache.get(normalized)
    +    now = time.time()
    +
    +    if (
    +        not force_refresh
    +        and isinstance(entry, dict)
    +        and entry.get("fp") == fp
    +        and isinstance(entry.get("models"), list)
    +        and entry["models"]
    +        and (now - float(entry.get("at", 0))) < ttl_seconds
    +    ):
    +        return list(entry["models"])
    +
    +    # Cache miss / stale / forced refresh — call the live path.
    +    live = provider_model_ids(normalized, force_refresh=force_refresh)
    +    if live:
    +        cache[normalized] = {
    +            "fp": fp,
    +            "at": now,
    +            "models": list(live),
    +        }
    +        _save_provider_models_cache(cache)
    +        return list(live)
    +
    +    # Live fetch returned nothing. If we have a stale entry with the
    +    # SAME fingerprint, prefer it over an empty result — stale data
    +    # beats no data when the network is flaky.
    +    if (
    +        isinstance(entry, dict)
    +        and entry.get("fp") == fp
    +        and isinstance(entry.get("models"), list)
    +        and entry["models"]
    +    ):
    +        return list(entry["models"])
    +    return list(live or [])
    +
    +
    +def clear_provider_models_cache(provider: Optional[str] = None) -> None:
    +    """Drop a single provider's cache entry, or wipe the whole cache.
    +
    +    ``provider=None`` wipes everything; otherwise only that provider's
    +    entry is removed. Used by ``/model --refresh`` and
    +    ``hermes model --refresh``.
    +    """
    +    try:
    +        if provider is None:
    +            path = _provider_models_cache_path()
    +            if path.exists():
    +                path.unlink()
    +            return
    +        cache = _load_provider_models_cache()
    +        normalized = normalize_provider(provider) or provider or ""
    +        if normalized in cache:
    +            del cache[normalized]
    +            _save_provider_models_cache(cache)
    +    except Exception:
    +        pass
    +
    +
     def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
         """Fetch available models from the Anthropic /v1/models endpoint.
     

  • tests/hermes_cli/test_inventory.py

    @@ -158,8 +158,11 @@ def test_build_models_payload_returns_expected_shape():
     
     
     def test_build_models_payload_does_not_call_provider_model_ids():
    -    """Curated lists must come from list_authenticated_providers, not
    -    provider_model_ids — that would pull TTS/embeddings/etc.
    +    """``build_models_payload`` is a thin shape adapter — it delegates the
    +    actual curation to ``list_authenticated_providers`` (which DOES call
    +    ``cached_provider_model_ids`` internally for live discovery, with disk
    +    caching). ``build_models_payload`` itself must not call the live fetcher
    +    directly; the test pins that boundary.
         """
         rows = [{"slug": "nous", "name": "Nous", "models": ["hermes-4-405b"],
                  "total_models": 1, "is_current": False, "is_user_defined": False,

  • tui_gateway/server.py

    @@ -1112,7 +1112,7 @@ def _apply_model_switch(sid: str, session: dict, raw_input: str) -> dict:
         from hermes_cli.model_switch import parse_model_flags, switch_model
         from hermes_cli.runtime_provider import resolve_runtime_provider
     
    -    model_input, explicit_provider, persist_global = parse_model_flags(raw_input)
    +    model_input, explicit_provider, persist_global, _force_refresh = parse_model_flags(raw_input)
         if not model_input:
             raise ValueError("model value required")