fixup(opencode): fmt, changelog, config test, docs

Audit follow-ups pushed onto the PR branch (maintainer edit):

- merge current main into the branch (was 56 commits behind, no conflicts)
- run cargo fmt on opencode.rs / lib.rs (the rustfmt CI job was failing)
- CHANGELOG [Unreleased] entries for the new provider and the compose
  env_file switch
- config test pinning opencode / opencode-zen / opencode_zen parsing,
  the claude-sonnet-4-6 default model, and OPENCODE_API_KEY sourcing,
  following the per-provider test convention
- README provider row + docs/install.md provider-defaults table row
- compose comment now lists every provider option including opencode

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+- OpenCode Zen/Go is now a first-class LLM provider:
+  `AI_MEMORY_LLM_PROVIDER=opencode` (alias `opencode-zen`) routes
+  consolidation through `https://opencode.ai/zen/go/v1` using the OpenAI
+  chat-completions wire format. Authenticate with `OPENCODE_API_KEY`
+  (key from `opencode.ai/auth`); the default model is `claude-sonnet-4-6`.
+  `ai-memory llm-test --provider opencode` exercises it end-to-end ([#147]).
+- `docker/docker-compose.yml` now loads provider credentials from a
+  gitignored `docker/.env` via `env_file` (optional — existing deployments
+  without that file keep working), replacing the commented-out inline
+  provider blocks ([#147]).
+
 ### Fixed
 - The detached drainer's `logs/hook-drain.log` now rotates once it exceeds
   1 MiB (previous contents move to `hook-drain.log.old`), so an agent

README.md

@@ -34,7 +34,7 @@
 | Antigravity CLI | Supported | MCP config (`serverUrl`) + lifecycle hooks (`agy` alias). |
 | Grok Build CLI | Hooks | Lifecycle hooks via `install-hooks --agent grok` (`~/.grok/hooks/ai-memory.json`, Grok-specific hook bundle, native `--agent grok`). Capture works; no handoff injection — Grok ignores `SessionStart` stdout, so recover handoffs via MCP `memory_handoff_accept`. |
 | VS Code Copilot | MCP-only | `.vscode/mcp.json` for Copilot agent mode; no lifecycle hooks (Copilot does not expose them yet). |
-| LLM/auth providers | Supported | Anthropic, OpenAI, OpenAI OAuth/Codex, GitHub Copilot, Gemini, OpenAI-compatible endpoints, and generic OIDC device auth for native hooks. |
+| LLM/auth providers | Supported | Anthropic, OpenAI, OpenAI OAuth/Codex, GitHub Copilot, Gemini, OpenCode Zen/Go, OpenAI-compatible endpoints, and generic OIDC device auth for native hooks. |
 | Embedding providers | Supported | OpenAI, Voyage, and Google Gemini. |
 
 ## What it is

crates/ai-memory-cli/src/config.rs

@@ -1335,6 +1335,36 @@ mod tests {
         );
     }
 
+    #[test]
+    fn opencode_provider_resolves_choice_default_model_and_api_key() {
+        for spelling in ["opencode", "opencode-zen", "opencode_zen"] {
+            let cfg = Config {
+                llm_provider: Some(spelling.into()),
+                runtime_env: RuntimeEnv {
+                    opencode_api_key: Some(SecretString::from("sk-opencode-test")),
+                    ..RuntimeEnv::default()
+                },
+                ..Config::default()
+            };
+
+            let provider = cfg.llm_provider_config().unwrap().unwrap();
+            assert_eq!(provider.provider, ProviderChoice::OpenCode, "{spelling}");
+            assert_eq!(provider.model, "claude-sonnet-4-6", "{spelling}");
+            assert_eq!(
+                provider.auth.requirement(),
+                AuthRequirement::RequiredApiKey {
+                    env_var: "OPENCODE_API_KEY"
+                },
+                "{spelling}"
+            );
+            assert_eq!(
+                provider.auth.require_api_key().unwrap().expose_secret(),
+                "sk-opencode-test",
+                "{spelling}"
+            );
+        }
+    }
+
     #[test]
     fn anthropic_oauth_provider_underscore_alias_also_resolves() {
         let cfg = Config {

crates/ai-memory-llm/src/lib.rs

@@ -71,10 +71,10 @@ pub use oidc::{
 };
 pub use openai::OpenAiProvider;
 pub use openai_compat::OpenAiCompatProvider;
-pub use opencode::{OPENCODE_DEFAULT_MODEL, OPENCODE_ZEN_BASE_URL, OpenCodeProvider};
 pub use openai_oauth::{
     CODEX_CLIENT_ID, CODEX_RESPONSES_URL, OPENAI_OAUTH_AUTH_URL, OPENAI_OAUTH_ISSUER,
     OPENAI_OAUTH_TOKEN_URL, OpenAiOAuthProvider, OpenAiOAuthToken, OpenAiOAuthTokenResponse,
 };
+pub use opencode::{OPENCODE_DEFAULT_MODEL, OPENCODE_ZEN_BASE_URL, OpenCodeProvider};
 pub use provider::{LlmProvider, complete_structured};
 pub use types::{ChatMessage, ChatRequest, ChatResponse, Role, Usage};

crates/ai-memory-llm/src/opencode.rs

@@ -33,8 +33,7 @@ impl OpenCodeProvider {
     /// # Errors
     /// Returns a `reqwest::Error` if the HTTP client cannot be built.
     pub fn new(api_key: SecretString, model: impl Into<String>) -> LlmResult<Self> {
-        let inner =
-            OpenAiCompatProvider::new(OPENCODE_ZEN_BASE_URL, Some(api_key), model.into())?;
+        let inner = OpenAiCompatProvider::new(OPENCODE_ZEN_BASE_URL, Some(api_key), model.into())?;
         Ok(Self { inner })
     }
 }

docker/docker-compose.yml

@@ -28,9 +28,10 @@ services:
         required: false
     environment:
       - RUST_LOG=ai_memory=info,ai_memory_store=info,ai_memory_wiki=info,ai_memory_mcp=info,tracing_appender=warn
-      # LLM provider configured via docker/.env (gitignored).
-      # Options: anthropic | openai | openai-compat | gemini | copilot
-      # See .env.production.example for full reference.
+      # LLM provider configured via docker/.env (gitignored). Options:
+      # anthropic | openai | openai-oauth | anthropic-oauth | copilot |
+      # gemini | openai-compat | opencode
+      # See .env.production.example for the full reference.
     healthcheck:
       test: ["CMD", "/usr/local/bin/ai-memory", "status"]
       interval: 30s

docs/install.md

@@ -806,6 +806,7 @@ If you set only the provider, ai-memory picks a sensible default:
 | `AI_MEMORY_LLM_PROVIDER=openai-oauth` | `gpt-5.5` | ChatGPT/Codex backend. Run `ai-memory auth login openai-oauth` once; ai-memory stores the refresh token in `<data_dir>/auth.json` and refreshes access tokens automatically. |
 | `AI_MEMORY_LLM_PROVIDER=copilot` | `gpt-5.5` | GitHub Copilot Chat backend. ai-memory stores a GitHub user token in `<data_dir>/auth.json`, exchanges it for a short-lived Copilot API token, and refreshes before expiry. |
 | `AI_MEMORY_LLM_PROVIDER=gemini` | `gemini-2.5-flash` | Google's hosted option with a generous free tier. ai-memory disables Gemini 2.5 Flash's default dynamic thinking so hidden thought tokens do not truncate strict JSON. Set `GEMINI_API_KEY` (or `GOOGLE_API_KEY`). |
+| `AI_MEMORY_LLM_PROVIDER=opencode` | `claude-sonnet-4-6` | [OpenCode Zen/Go](https://opencode.ai) cloud API — OpenAI-compatible endpoint at `opencode.ai/zen/go/v1`. Set `OPENCODE_API_KEY` (key from `opencode.ai/auth`). Alias: `opencode-zen`. |
 | `AI_MEMORY_EMBEDDING_PROVIDER=openai` | `text-embedding-3-small` (1536-dim) | 5× cheaper than `-3-large` with marginal recall loss. |
 | `AI_MEMORY_EMBEDDING_PROVIDER=openai` + `AI_MEMORY_EMBEDDING_BASE_URL=https://openrouter.ai/api/v1` | `openai/text-embedding-3-small` via [OpenRouter](https://openrouter.ai) | Reuses `LLM_API_KEY` or `OPENAI_API_KEY` with the OpenAI-compatible embedding client. |
 | `AI_MEMORY_EMBEDDING_PROVIDER=voyage` | `voyage-3` (1024-dim) | Voyage's current general-purpose recommendation. |