docs: update hephaestus default model references from gpt-5.3-codex to gpt-5.4

Updated across README (all locales), docs/guide/, docs/reference/,
docs/examples/, AGENTS.md files, and test expectations/snapshots.

The deep category and multimodal-looker still use gpt-5.3-codex as
those are separate from the hephaestus agent.

docs/examples/coding-focused.jsonc

@@ -14,7 +14,7 @@
 
     // Heavy lifter: maximum autonomy for coding tasks
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "You are the primary implementation agent. Own the codebase. Explore, decide, execute. Use LSP and AST-grep aggressively.",
       "permission": { "edit": "allow", "bash": { "git": "allow", "test": "allow" } },
     },

docs/examples/default.jsonc

@@ -13,7 +13,7 @@
 
     // Deep autonomous worker: end-to-end implementation
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "Explore thoroughly, then implement. Prefer small, testable changes.",
     },
 

docs/examples/planning-focused.jsonc

@@ -14,7 +14,7 @@
 
     // Implementation: uses planning outputs
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "Follow established plans precisely. Ask for clarification when plans are ambiguous.",
     },