feat(provider-opencode-go): add OpenCode Go Chat Completions provider worker

.github/scripts/discover_changed_workers.py

@@ -66,6 +66,7 @@
     "provider-llamacpp",
     "provider-openai",
     "provider-openai-codex",
+    "provider-opencode-go",
     "provider-xai",
     "provider-zai",
 }

.github/workflows/alpha-release.yml

@@ -50,6 +50,7 @@ on:
           - provider-llamacpp
           - provider-openai
           - provider-openai-codex
+          - provider-opencode-go
           - provider-xai
           - provider-zai
           - pubsub

.github/workflows/create-tag.yml

@@ -48,6 +48,7 @@ on:
           - provider-llamacpp
           - provider-openai
           - provider-openai-codex
+          - provider-opencode-go
           - provider-xai
           - provider-zai
           - pubsub

.github/workflows/release.yml

@@ -42,6 +42,7 @@ on:
       - 'provider-llamacpp/v*'
       - 'provider-openai/v*'
       - 'provider-openai-codex/v*'
+      - 'provider-opencode-go/v*'
       - 'provider-xai/v*'
       - 'provider-zai/v*'
       - 'pubsub/v*'

README.md

@@ -69,6 +69,7 @@ npx skills add iii-hq/iii --all
 | [`provider-claude-code`](provider-claude-code/) | Rust | Claude Code (Pro/Max subscription) Messages API provider behind `llm-router` — `provider::claude-code::stream` using OAuth credentials from the auth-credentials vault or `~/.claude/.credentials.json`, namespaced `claude-code/*` catalog. Local/personal dev only (ToS caveat). |
 | [`provider-llamacpp`](provider-llamacpp/) | Rust | llama.cpp server (`llama-server`) Chat Completions provider behind `llm-router` — `provider::llamacpp::stream` with optional (no-`--api-key`) auth, real json_schema-constrained output, and live model discovery via `/v1/models` + `/props`. |
 | [`provider-openai`](provider-openai/) | Rust | OpenAI Chat Completions provider behind `llm-router` — `provider::openai::stream` with reasoning support and live chat-model discovery, plus `provider::openai::embed` for batch embeddings (OpenAI-compatible endpoints included). |
+| [`provider-opencode-go`](provider-opencode-go/) | Rust | OpenCode Go Chat Completions provider behind `llm-router` — `provider::opencode_go::stream`, live models.dev-enriched catalog via `refresh_models` |
 | [`provider-xai`](provider-xai/) | Rust | xAI (Grok) Chat Completions provider behind `llm-router` — `provider::xai::stream` with grok reasoning support and live model discovery against `api.x.ai`. |
 | [`provider-zai`](provider-zai/) | Rust | Z.AI (GLM) Chat Completions provider behind `llm-router` — `provider::zai::stream` with GLM thinking/effort support and a curated catalog against `api.z.ai` (no upstream model listing). |
 | [`shell`](shell/) | Rust | Unix shell + filesystem worker — `shell::exec` with denylist/timeout/output caps and background jobs; `fs::ls`/`stat`/`mkdir`/`rm`/`chmod`/`mv`/`grep`/`sed`/`read`/`write` with host jail, denylist, and size caps. |

harness/iii.worker.yaml

@@ -20,5 +20,6 @@ dependencies:
   context-manager: "^1.0.0"
   provider-anthropic: "^1.0.0"
   provider-openai: "^1.0.0"
+  provider-opencode-go: "^1.0.0"
   shell: "^0.10.3"
   scrapling: "^0.2.4"

llm-router/README.md

@@ -213,6 +213,8 @@ The first real provider implementing this protocol is
 implementation alongside the scripted provider in the integration tests.
 [`provider-openai/`](https://github.com/iii-hq/workers/tree/main/provider-openai) follows the same structure for the
 OpenAI Chat Completions API (native structured output, reasoning_effort).
+[`provider-opencode-go/`](https://github.com/iii-hq/workers/tree/main/provider-opencode-go) follows the same structure for the
+OpenCode Go Chat Completions API (curated model metadata, reasoning_effort).
 
 ## Local development & testing
 

provider-opencode-go/.gitignore

@@ -0,0 +1 @@
+/target