CB-508: let an opencode profile pin its own OpenAI-compatible endpoint
CI / build (push) Successful in 1m57s
CI / build (push) Successful in 1m57s
Points an opencode worker at a local vLLM (or llama.cpp / LM Studio / TGI) instead of opencode's own gateway. opencode has no ANTHROPIC_BASE_URL seam, so this could not be a config-only change: setting baseUrl on a kind: opencode profile now makes the launcher emit a custom `provider` block into the generated opencode.json, using @ai-sdk/openai-compatible. The provider id comes from the provider half of the model: selector, so one field drives both the generated declaration and the -m flag and the two cannot drift apart. A bare model name with a baseUrl set is rejected at spawn with a message saying how to fix it — silently falling back to the default gateway would leave a worker talking to the wrong LLM while looking perfectly healthy. A bare host:port gets /v1 appended (where these servers mount the API); a URL that already carries a path is used verbatim. tokenEnv, when set, becomes the provider apiKey; local servers generally ignore it but the AI SDK requires a non-empty value, so a placeholder is used otherwise. Two supporting changes: - writeConfig previously ran only when a bridge MCP url was set. A pinned endpoint needs the config file too, so it now runs when either applies, and the mcp/instructions half is emitted conditionally. - The config is now built with Jackson instead of string concatenation. The provider block is nested and interpolates operator-supplied values (URL, model id, api key), so escaping has to be real rather than a hand-rolled two-character replace. No guard entry is required even with baseUrl set. SubscriptionGuard exists to stop a worker borrowing the primary's Anthropic subscription, and an opencode process has no Anthropic credential path at all — the asymmetry with the Claude adapter reusing the same field is deliberate and documented at the call site. Also fixes a brittle assertion in the existing MCP-mount test, which matched the substring "\"type\": \"remote\"" and broke on Jackson's spacing. It now parses the generated JSON and asserts on structure; whitespace is the formatter's business, not the contract's. 318 tests (was 311): 5 new covering provider generation, /v1 normalisation, path-preserving URLs, the missing-prefix rejection, MCP+provider coexistence, and that no baseUrl still means no provider block. Verified live end to end: daemon restarted on this build, worker spawned on the opencode-local profile, generated config carries baseURL http://127.0.0.1:8000/v1, and a blocking bridge_send returned {"reply":"LOCAL-OK","replySource":"reply"} — a structured reply, not the completion fallback. The worker pane reports "Build · deepseek-v4-flash local-vllm (bridged)", confirming traffic reached the local server rather than silently falling back.
This commit is contained in:
@@ -1,5 +1,7 @@
|
||||
package dev.ltms.bridged.worker;
|
||||
|
||||
import com.fasterxml.jackson.databind.JsonNode;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import dev.ltms.bridged.config.BridgedConfig;
|
||||
import dev.ltms.bridged.herdr.AgentControl;
|
||||
import dev.ltms.bridged.herdr.FakeHerdr;
|
||||
@@ -65,10 +67,16 @@ class OpenCodeLauncherTest {
|
||||
assertNotNull(cfgPath, "OPENCODE_CONFIG points the worker at the generated config file");
|
||||
assertTrue(Path.of(cfgPath).startsWith(root), "config file is generated under the injected root");
|
||||
|
||||
String json = Files.readString(Path.of(cfgPath));
|
||||
assertTrue(json.contains("\"type\": \"remote\""), "bridge is mounted as a remote MCP server");
|
||||
assertTrue(json.contains("http://127.0.0.1:8765/mcp"), "the profile's bridge MCP url is present");
|
||||
assertTrue(json.contains("\"instructions\""), "the reply charter is mounted via instructions");
|
||||
// Assert on parsed structure, not substrings: the generated config is real JSON and its
|
||||
// whitespace is the formatter's business, not the contract's.
|
||||
JsonNode json = new ObjectMapper().readTree(Path.of(cfgPath).toFile());
|
||||
JsonNode bridge = json.path("mcp").path("bridge");
|
||||
assertEquals("remote", bridge.path("type").asText(), "bridge is mounted as a remote MCP server");
|
||||
assertEquals("http://127.0.0.1:8765/mcp", bridge.path("url").asText(),
|
||||
"the profile's bridge MCP url is present");
|
||||
assertTrue(bridge.path("enabled").asBoolean(), "the bridge server is enabled");
|
||||
assertTrue(json.path("instructions").isArray() && !json.path("instructions").isEmpty(),
|
||||
"the reply charter is mounted via instructions");
|
||||
|
||||
// The instructions entry is a real file path holding the reply charter.
|
||||
Path charter = Path.of(cfgPath).resolveSibling("reply-charter.md");
|
||||
@@ -176,4 +184,86 @@ class OpenCodeLauncherTest {
|
||||
assertNotNull(handle, "spawn returns a handle when the gate is disabled");
|
||||
assertFalse(herdr.called("agent.get"), "no polling when the gate is disabled");
|
||||
}
|
||||
|
||||
// --- CB-508: pinned OpenAI-compatible endpoint (e.g. a local vLLM) ---------------------------
|
||||
|
||||
/** A profile with a baseUrl but no model provider prefix cannot be resolved — fail loudly. */
|
||||
private static BridgedConfig.Worker pinnedCfg(String model, String baseUrl, String mcpUrl) {
|
||||
return new BridgedConfig.Worker("local", baseUrl, model, null, "BRIDGED_WORKER_TOKEN",
|
||||
List.of("opencode"), "tab", "bridged-workers", "opencode: {model} #{n}", mcpUrl,
|
||||
null, null, null, null, BridgedConfig.Worker.KIND_OPENCODE);
|
||||
}
|
||||
|
||||
@Test
|
||||
void baseUrlDeclaresACustomOpenAiCompatibleProvider(@TempDir Path root) throws Exception {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
service(herdr, root, pinnedCfg("local-vllm/deepseek-v4-flash", "http://127.0.0.1:8000", null))
|
||||
.spawn();
|
||||
|
||||
String cfgPath = startEnv(herdr).get("OPENCODE_CONFIG");
|
||||
assertNotNull(cfgPath, "a pinned endpoint needs a config file even with no bridge MCP url");
|
||||
JsonNode provider = new ObjectMapper().readTree(Path.of(cfgPath).toFile())
|
||||
.path("provider").path("local-vllm");
|
||||
|
||||
assertFalse(provider.isMissingNode(), "the provider id comes from the model selector");
|
||||
assertEquals("@ai-sdk/openai-compatible", provider.path("npm").asText());
|
||||
assertEquals("http://127.0.0.1:8000/v1", provider.path("options").path("baseURL").asText(),
|
||||
"a bare host:port gets /v1 appended — that is where these servers mount the API");
|
||||
assertFalse(provider.path("options").path("apiKey").asText().isBlank(),
|
||||
"the AI SDK requires a non-empty key even when the server ignores it");
|
||||
assertFalse(provider.path("models").path("deepseek-v4-flash").isMissingNode(),
|
||||
"the model half of the selector is declared under the provider");
|
||||
}
|
||||
|
||||
@Test
|
||||
void aBaseUrlThatAlreadyCarriesAPathIsUsedVerbatim(@TempDir Path root) throws Exception {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
service(herdr, root, pinnedCfg("local-vllm/m", "http://127.0.0.1:8000/openai/v1", null)).spawn();
|
||||
|
||||
JsonNode json = new ObjectMapper()
|
||||
.readTree(Path.of(startEnv(herdr).get("OPENCODE_CONFIG")).toFile());
|
||||
assertEquals("http://127.0.0.1:8000/openai/v1",
|
||||
json.path("provider").path("local-vllm").path("options").path("baseURL").asText(),
|
||||
"an endpoint mounted on a custom path must not have /v1 bolted on");
|
||||
}
|
||||
|
||||
@Test
|
||||
void aPinnedEndpointRejectsAModelWithNoProviderPrefix(@TempDir Path root) {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
OpenCodeLauncher launcher =
|
||||
service(herdr, root, pinnedCfg("deepseek-v4-flash", "http://127.0.0.1:8000", null));
|
||||
|
||||
// Silently falling back to the default gateway would point the worker at the wrong LLM
|
||||
// while looking healthy — the one failure mode worth being loud about.
|
||||
IllegalArgumentException e = assertThrows(IllegalArgumentException.class, launcher::spawn);
|
||||
assertTrue(e.getMessage().contains("<provider>/<model>"), "the error says how to fix it");
|
||||
}
|
||||
|
||||
@Test
|
||||
void aPinnedEndpointAndTheBridgeMcpCoexistInOneConfig(@TempDir Path root) throws Exception {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
service(herdr, root, pinnedCfg("local-vllm/deepseek-v4-flash",
|
||||
"http://127.0.0.1:8000", "http://127.0.0.1:8766/mcp")).spawn();
|
||||
|
||||
JsonNode json = new ObjectMapper()
|
||||
.readTree(Path.of(startEnv(herdr).get("OPENCODE_CONFIG")).toFile());
|
||||
assertEquals("remote", json.path("mcp").path("bridge").path("type").asText(),
|
||||
"pinning an endpoint must not drop the bridge MCP mount");
|
||||
assertFalse(json.path("provider").path("local-vllm").isMissingNode(),
|
||||
"and the provider block is still declared alongside it");
|
||||
assertTrue(json.path("instructions").isArray() && !json.path("instructions").isEmpty(),
|
||||
"the reply charter survives too");
|
||||
}
|
||||
|
||||
@Test
|
||||
void noBaseUrlDeclaresNoProviderSoTheDefaultGatewayIsUsed(@TempDir Path root) throws Exception {
|
||||
FakeHerdr herdr = new FakeHerdr();
|
||||
service(herdr, root, opencodeCfg("opencode/some-free-model", "http://127.0.0.1:8766/mcp", null))
|
||||
.spawn();
|
||||
|
||||
JsonNode json = new ObjectMapper()
|
||||
.readTree(Path.of(startEnv(herdr).get("OPENCODE_CONFIG")).toFile());
|
||||
assertTrue(json.path("provider").isMissingNode(),
|
||||
"without a baseUrl opencode resolves its own provider as before");
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user