rdm upd

README.md

@@ -46,7 +46,7 @@ bantam.hpp   all shared declarations (structs, prototypes, native Json type)
 util.cpp     string building, UTF-8, prompt-injection filter, color, IDs, MD5
 config.cpp   config file parsing, env precedence, /models discovery
 json.cpp     native RFC 8259 JSON engine, request building + response parsing
-llm.cpp      libcurl HTTP client, OpenCode headers, backoff, SSE streaming
+llm.cpp      libcurl HTTP client, custom headers, backoff, SSE streaming
 tools.cpp    bash/read/write tools, oversized-result offloading
 session.cpp  message copy, session save/load, compaction
 render.cpp   terminal markdown renderer (native, box-drawing tables)
@@ -326,13 +326,16 @@ that left an empty assistant message in the session), Bantam strips the last
 
 ### Custom request headers
 
-All endpoints receive custom request headers mimicking OpenCode:
-`User-Agent: opencode/1.18.31 ai-sdk/provider-utils/4.0.23 runtime/bun/1.3.14`,
-`x-opencode-client: cli`, `x-opencode-project: global`,
-`x-opencode-session: <ses_...>`, and a fresh `x-opencode-request: <msg_...>`
-per call (the 12-hex timestamp prefix in `x-opencode-request` is the bitwise
-inverse of `x-opencode-session`). The `Authorization: Bearer <api_key>` header
-is added whenever `api_key` is set and not `-`.
+All requests to the `/chat/completions` and `/models` endpoints are sent with a
+minimal, dependency-free header set (see `apply_llm_headers` / `http_get` in
+`llm.cpp`):
+
+- `Content-Type: application/json`
+- `Expect:` (empty) — suppresses the `Expect: 100-continue` round-trip so large
+  POST bodies are sent immediately and do not hang behind some proxies.
+- `User-Agent: Mozilla/5.0 Bantam/nightly-cpp`
+- `Authorization: Bearer <api_key>` — added only when `api_key` is set and is
+  not `-` (a real key, not the placeholder).
 
 ### Prompt-injection defense