fix(settings): don't require vision endpoint/model when OCR is active

Enabling the analysis worker ran the vision validators: the SSRF gate
rejected the default `localhost` endpoint and a model id was required.
With the OCR backend active those fields are never used, and the
OCR-only settings UI no longer exposes them — so an operator could not
turn the worker on (a 422 with no fixable field).

Gate both checks on `base.backend == Vision`. The basic malformed-URL
sanity check stays unconditional. Existing vision-validation tests now
use a Vision base; a new test pins that enabling on the OCR backend with
the default localhost endpoint and an empty model validates cleanly.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/src/settings.rs

@@ -25,7 +25,7 @@ use serde::{Deserialize, Serialize};
 use crate::analysis::prompt::{
     GROUNDING_PROMPT_DEFAULT, OCR_PROMPT_DEFAULT, SYSTEM_PROMPT_DEFAULT,
 };
-use crate::config::{AnalysisConfig, CrawlerConfig, ResponseFormat};
+use crate::config::{AnalysisBackend, AnalysisConfig, CrawlerConfig, ResponseFormat};
 use crate::crawler::safety::DownloadAllowlist;
 
 /// `app_settings.key` for the crawler group.
@@ -355,6 +355,15 @@ impl AnalysisSettings {
         if self.workers < 1 {
             errs.push("workers", "must be at least 1");
         }
+        // The endpoint/model are vision-only knobs — the OCR backend never
+        // dials a URL or sends a model id. While vision is dormant
+        // (`base.backend == Ocr`), skip the live-worker SSRF gate and the
+        // model-required check so an OCR operator can enable the worker
+        // without a vision endpoint/model (the OCR settings UI doesn't even
+        // expose them). The basic malformed-URL sanity check below stays
+        // unconditional. Re-enabling vision restores the full gate via the
+        // `base.backend == Vision` predicate.
+        let vision_active = base.backend == AnalysisBackend::Vision;
         let trimmed_endpoint = self.endpoint.trim();
         if trimmed_endpoint.is_empty() {
             errs.push("endpoint", "must be a valid absolute URL");
@@ -362,7 +371,7 @@ impl AnalysisSettings {
             // Always reject obviously-malformed URLs (matches prior behaviour).
             let _ = e;
             errs.push("endpoint", "must be a valid absolute URL");
-        } else if self.enabled {
+        } else if self.enabled && vision_active {
             // SSRF + API-key exfiltration defence — only enforced when the
             // worker is actually live. Worker attaches an env-managed bearer
             // token to every call; without this check, an admin (or one
@@ -379,7 +388,7 @@ impl AnalysisSettings {
                 errs.push("endpoint", url_safety_message(&e));
             }
         }
-        if self.enabled && self.model.trim().is_empty() {
+        if self.enabled && vision_active && self.model.trim().is_empty() {
             errs.push("model", "required when analysis is enabled");
         }
         if self.max_tokens < 1 {
@@ -701,7 +710,8 @@ mod tests {
         // a hostile/CSRF-able admin must NOT be able to point endpoint at
         // cloud metadata, loopback services, or RFC1918 hosts — when the
         // worker is enabled (toggling enabled=true later re-runs this gate).
-        let base = AnalysisConfig::default();
+        let mut base = AnalysisConfig::default();
+        base.backend = AnalysisBackend::Vision;
         for url in [
             "http://169.254.169.254/v1/chat/completions",
             "http://127.0.0.1:5432/",
@@ -725,7 +735,8 @@ mod tests {
         // The documented default — docker DNS name resolving to a private IP
         // at runtime — must still validate, because the bearer recipient
         // identity is the operator-chosen hostname, not the underlying IP.
-        let base = AnalysisConfig::default();
+        let mut base = AnalysisConfig::default();
+        base.backend = AnalysisBackend::Vision;
         for url in [
             "http://mangalord-vision:8000/v1/chat/completions",
             "https://api.openai.com/v1/chat/completions",
@@ -756,7 +767,10 @@ mod tests {
 
     #[test]
     fn analysis_requires_model_only_when_enabled() {
-        let base = AnalysisConfig::default();
+        // Vision base: the model id is required only when the vision worker
+        // is actually live (see the OCR carve-out below).
+        let mut base = AnalysisConfig::default();
+        base.backend = AnalysisBackend::Vision;
         let disabled = AnalysisSettings {
             enabled: false,
             model: "".to_string(),
@@ -772,6 +786,28 @@ mod tests {
         assert!(errs.errors.iter().any(|e| e.field == "model"));
     }
 
+    #[test]
+    fn analysis_ocr_backend_enable_skips_vision_endpoint_and_model_validation() {
+        // With the OCR backend active the worker never dials the vision
+        // endpoint nor sends a model id, so enabling analysis must NOT
+        // validate those vision-only fields. The default base carries the
+        // dev-localhost endpoint (which the SSRF gate would otherwise reject)
+        // and an empty model — under OCR, enabling is still valid. Without
+        // this carve-out an OCR operator can't turn the worker on, since the
+        // OCR settings UI doesn't expose endpoint/model to fix.
+        let base = AnalysisConfig::default(); // backend = Ocr
+        let dto = AnalysisSettings {
+            enabled: true,
+            endpoint: "http://localhost:8000/v1/chat/completions".to_string(),
+            model: "".to_string(),
+            ..AnalysisSettings::from_config(&base)
+        };
+        assert!(
+            dto.to_config(&base).is_ok(),
+            "OCR-enabled config must not fail on vision endpoint/model"
+        );
+    }
+
     #[test]
     fn dtos_serialize_to_json_and_back() {
         let c = CrawlerSettings::default();