feat(ai): send a per-entry reasoning effort to Local and gateway providers

Reasoning models on Ollama and similar servers think by default and can
spend the whole max_tokens budget before the visible answer starts, so
the call comes back empty or times out. The Local and OpenAI-compatible
chain entries now carry an optional reasoning setting: Default sends
nothing, Off sends reasoning_effort "none", Low / Medium / High send
their own value. It is stored on the entry in aiProviderChain, so a
chain can mix a thinking model with one that does not know the field.

- Every exported resolver binds the entry's value onto the client, the
  connection test included, keyed on the instance type so the operator
  provider, OpenAI, Anthropic and Codex never carry it.
- PATCH /api/user/ai-provider accepts localReasoningEffort and
  compatReasoningEffort and GET reports them. A provider absent from
  the chain holds its value on a disabled entry; restating Default on a
  chain that was never customised writes nothing.
- PUT /api/insights/provider-chain accepts reasoningEffort on local and
  openai-compatible entries, refuses it on any other, and keeps the
  stored value when the body leaves it out. Its schema is now shared
  with the OpenAPI registry.
- A Default request body is byte-identical to the one sent before.

Refs #1126

docs/api/openapi.yaml

@@ -25855,6 +25855,28 @@ components:
               minimum: 10
               maximum: 600
             - type: "null"
+        localReasoningEffort:
+          description: Reasoning setting of the Local provider entry, stored on that entry of the provider chain. `none` = Off,
+            `null` = Default (nothing sent). Omitted leaves it untouched.
+          anyOf:
+            - type: string
+              enum:
+                - none
+                - low
+                - medium
+                - high
+            - type: "null"
+        compatReasoningEffort:
+          description: Reasoning setting of the OpenAI-compatible gateway entry, stored on that entry of the provider chain.
+            `none` = Off, `null` = Default (nothing sent). Omitted leaves it untouched.
+          anyOf:
+            - type: string
+              enum:
+                - none
+                - low
+                - medium
+                - high
+            - type: "null"
       description: "Partial update of the calling user's AI-provider configuration. An omitted key is left untouched; `null`
         (or an empty string, on the string fields) clears the column. At least one recognised key must be present, or
         the write is refused. Key material is write-only: it is encrypted on the way in and never returned. Unknown keys
@@ -27071,6 +27093,7 @@ components:
       properties:
         chain:
           minItems: 1
+          maxItems: 7
           type: array
           items:
             type: object
@@ -27096,15 +27119,30 @@ components:
                 maximum: 9007199254740991
               enabled:
                 type: boolean
+              reasoningEffort:
+                description: Only on a `local` or `openai-compatible` entry; refused on any other. Omitted keeps the value already
+                  stored for that provider, `null` restores Default, `none` / `low` / `medium` / `high` are sent as
+                  `reasoning_effort`.
+                anyOf:
+                  - type: string
+                    enum:
+                      - none
+                      - low
+                      - medium
+                      - high
+                  - type: "null"
             required:
               - providerType
               - enabled
+            additionalProperties: false
           description: The whole chain, in the order it should be walked. At least one entry and at most one per known provider
             type; a repeated type is refused.
       required:
         - chain
+      additionalProperties: false
       description: Replaces the account's provider chain wholesale. No credential is written or read here — only which
-        provider types exist, in what order, and which are enabled.
+        provider types exist, in what order, which are enabled, and the reasoning setting of the Local and
+        OpenAI-compatible entries.
     InsightsFeedbackRequest:
       type: object
       properties:
@@ -48543,6 +48581,27 @@ components:
             - type: "null"
           description: v1.22 (#89) — per-user response timeout for AI generation, in seconds (10–600). Null = the built-in
             comprehensive-briefing default (~120 s). Mainly for slow local/self-hosted backends.
+        localReasoningEffort:
+          anyOf:
+            - type: string
+              enum:
+                - none
+                - low
+                - medium
+                - high
+            - type: "null"
+          description: "#1126 — reasoning setting of the Local provider entry, sent as `reasoning_effort` (`none` = Off). Null =
+            Default: the key is not sent."
+        compatReasoningEffort:
+          anyOf:
+            - type: string
+              enum:
+                - none
+                - low
+                - medium
+                - high
+            - type: "null"
+          description: "#1126 — the same for the OpenAI-compatible gateway entry."
         serverProviderHealth:
           type: string
           enum:
@@ -48587,6 +48646,8 @@ components:
         - compatModel
         - hasCompatKey
         - responseTimeoutSeconds
+        - localReasoningEffort
+        - compatReasoningEffort
         - serverProviderHealth
         - serverProviderOffer
         - serverProviderConsent