From f67514d145c34af1373361b77a005ec3971d0336 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sat, 16 May 2026 14:00:39 +0000 Subject: [PATCH] Studio: drop redundant issue refs from inheritance comments --- studio/backend/core/inference/llama_cpp.py | 4 ++-- studio/backend/core/inference/llama_server_args.py | 6 +++--- studio/backend/routes/inference.py | 10 ++++------ 3 files changed, 9 insertions(+), 11 deletions(-) diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py index e8009a3fa1..96babd9be6 100644 --- a/studio/backend/core/inference/llama_cpp.py +++ b/studio/backend/core/inference/llama_cpp.py @@ -2688,7 +2688,7 @@ class LlamaCppBackend: # failed startup can't poison the next inheritance check. # None keeps prior, [] clears, list sets. Source records # the caller's hf_variant (None for local files) so the - # route's same_source check stays symmetric (#5401). + # route's same_source check stays symmetric. if extra_args is not None: self._extra_args = list(extra_args) self._extra_args_source = (model_identifier, hf_variant) @@ -2740,7 +2740,7 @@ class LlamaCppBackend: return False # Direct-file loads pass hf_variant=None while the backend # stores an extracted filename label; compare paths instead - # to keep the guard symmetric (#5401). + # to keep the guard symmetric. if gguf_path is not None and self._gguf_path: try: if Path(self._gguf_path).resolve() != Path(gguf_path).resolve(): diff --git a/studio/backend/core/inference/llama_server_args.py b/studio/backend/core/inference/llama_server_args.py index f2d74fd490..f7fe8604c2 100644 --- a/studio/backend/core/inference/llama_server_args.py +++ b/studio/backend/core/inference/llama_server_args.py @@ -124,7 +124,7 @@ def is_managed_flag(flag: str) -> bool: # (max_seq_length, cache_type_kv, speculative_type, # chat_template_override). Stripped from inherited extras so they # can't last-wins-override an Apply that re-sets the same first-class -# field (#5401). +# field. _CONTEXT_FLAGS: frozenset[str] = frozenset({"-c", "--ctx-size"}) _CACHE_FLAGS: frozenset[str] = frozenset( {"-ctk", "--cache-type-k", "-ctv", "--cache-type-v"} @@ -155,7 +155,7 @@ _SHADOWING_FLAGS: frozenset[str] = ( # Boolean flags inside _SHADOWING_FLAGS that take no value. The # value-consuming heuristic in strip_shadowing_flags must skip just the -# flag for these, never the following token (#5401). +# flag for these, never the following token. _BOOLEAN_SHADOWING_FLAGS: frozenset[str] = frozenset( {"--spec-default", "--jinja", "--no-jinja"} ) @@ -178,7 +178,7 @@ def strip_shadowing_flags( group; the route only strips groups whose corresponding first-class field was actually supplied by the caller, so an inherited ``--chat-template-file`` survives an Apply that omits both - ``llama_extra_args`` and ``chat_template_override`` (#5401). + ``llama_extra_args`` and ``chat_template_override``. """ shadowing: set[str] = set() if strip_context: diff --git a/studio/backend/routes/inference.py b/studio/backend/routes/inference.py index a455ce086c..0c86c8ec57 100644 --- a/studio/backend/routes/inference.py +++ b/studio/backend/routes/inference.py @@ -452,7 +452,7 @@ def _request_matches_loaded_settings( # llama_extra_args=None means "inherit"; only an explicit list that # differs forces a reload. On the inherit path, refuse to match if # stored extras contain any shadow flag, so the reload path can - # strip them instead of leaving a stale override in effect (#5401). + # strip them instead of leaving a stale override in effect. backend_extra = list(llama_backend.extra_args) if llama_backend.extra_args else [] if request.llama_extra_args is None: if backend_extra and strip_shadowing_flags(backend_extra) != backend_extra: @@ -519,8 +519,7 @@ async def load_model( except ValueError as exc: raise HTTPException(status_code = 400, detail = str(exc)) # Re-narrow []-from-None back to None so the inheritance path - # below can tell "caller omitted" from "caller explicit []" - # (#5401). + # below can tell "caller omitted" from "caller explicit []". extra_llama_args: Optional[list[str]] = ( None if request.llama_extra_args is None else extra_llama_args ) @@ -685,8 +684,7 @@ async def load_model( # Inheritance is gated on (model_identifier, hf_variant) # to refuse cross-model pickup, and shadowing flags are # stripped so an inherited override can't win the last-wins - # CLI parse against a freshly-supplied first-class field - # (#5401). + # CLI parse against a freshly-supplied first-class field. if request.llama_extra_args is None and llama_backend.extra_args: source = llama_backend.extra_args_source same_source = bool( @@ -710,7 +708,7 @@ async def load_model( # Strip only the groups whose first-class field # was actually set by the caller, so an inherited # --chat-template-file survives an Apply that omits - # chat_template_override (#5401). + # chat_template_override. fields_set = getattr(request, "model_fields_set", set()) stripped = strip_shadowing_flags( llama_backend.extra_args,