docs: drop em dashes from llms.md, model-providers/{index,authoring}.md

Sweep of leftover em dashes from PR-1/PR-2 docs that slipped past
the no-em-dashes-in-user-facing-copy rule. Same substitutions as
the prompts.md cleanup (colons, semicolons, parens, or sentence
restructuring).

Author: chris-colinsky

docs/concepts/llms.md

@@ -196,7 +196,7 @@ response post-receive against the supplied schema; strict is a
 wire-level optimization, not a correctness requirement.
 
 `strict_mode_supported(schema)` (exported from `openarmature.llm`)
-performs the deep recursive check. The heuristic is conservative —
+performs the deep recursive check. The heuristic is conservative:
 anything not on the list below trips to `strict: false`:
 
 - Top-level schema is `type: "object"`.
@@ -240,7 +240,7 @@ A text block is the array-form equivalent of a text-string message:
 text block is normatively equivalent to one with `content="describe
 this"`.
 
-An image block carries one source — URL or inline base64 — plus an
+An image block carries one source (URL or inline base64) plus an
 optional `detail` hint:
 
 ```python
@@ -302,7 +302,7 @@ fidelity: `"auto"`, `"low"`, or `"high"`. The class default is `None`,
 which **omits the field from the wire** and lets the provider apply
 its own default (conceptually `"auto"`). Setting `detail="auto"`
 explicitly on the spec block forces the wire to carry an explicit
-`"auto"` — usually unnecessary, since the provider's default is the
+`"auto"`, usually unnecessary since the provider's default is the
 same value.
 
 ### When the model can't handle the block
@@ -324,12 +324,12 @@ provider on this category) compose cleanly against it.
 "audio", "video") and `reason` (the provider's human-readable
 message) when those are recoverable from the rejection.
 
-`OpenAIProvider` detects content rejection via the response body —
+`OpenAIProvider` detects content rejection via the response body:
 HTTP 400 with an error code like `image_content_not_supported` or a
 message like "does not support image inputs." Pre-send capability
 checks (failing fast before the wire trip when you know the model
 doesn't support images) live above the provider as userland
-middleware — the provider doesn't ship a static model-capability
+middleware; the provider doesn't ship a static model-capability
 catalog.
 
 ## Routing on parsed fields

docs/model-providers/authoring.md

@@ -69,7 +69,7 @@ class MyProvider:
         response_schema: dict[str, Any] | type[BaseModel] | None = None,
     ) -> Response:
         # response_schema is part of the Protocol; a skeleton provider
-        # MUST NOT silently ignore it — callers expect either
+        # MUST NOT silently ignore it: callers expect either
         # Response.parsed populated or a StructuredOutputInvalid raise.
         # Until the wire path is implemented, raise
         # ProviderInvalidRequest when response_schema is set. A
@@ -206,8 +206,8 @@ of:
   `ImageSourceInline`) are stable across providers; only the wire
   shape differs. Provider authors targeting non-multimodal models
   MUST surface `ProviderUnsupportedContentBlock` when the request
-  carries blocks the bound model can't serve — pre-send or
-  post-receive per §7.
+  carries blocks the bound model can't serve (pre-send or
+  post-receive per §7).
 - **Structured output.** Threading `response_schema` through the
   request body (native `response_format` if the underlying wire
   supports it; prompt-augmentation fallback otherwise) and validating

docs/model-providers/index.md

@@ -89,7 +89,7 @@ in the LLMs concept page for the multimodal contract; see
 
 `OpenAIProvider` detects unsupported-content-block rejections via
 the response body (HTTP 400 with an error code or message indicating
-content rejection) — a post-receive mapping rather than a static
+content rejection): a post-receive mapping rather than a static
 pre-send capability check. Pre-send protection is a userland
 middleware pattern when callers know the bound model's capabilities
 up front.