Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

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

AkitaOnRails3a89394a76c3
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1b44a481..e08fba2a 100644
--- a/CHANGELOG.md
+++ b/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
diff --git a/README.md b/README.md
index 4e90679b..747cbf4a 100644
--- a/README.md
+++ b/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
diff --git a/crates/ai-memory-cli/src/config.rs b/crates/ai-memory-cli/src/config.rs
index d1796f83..85de56ee 100644
--- a/crates/ai-memory-cli/src/config.rs
+++ b/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 {
diff --git a/crates/ai-memory-llm/src/lib.rs b/crates/ai-memory-llm/src/lib.rs
index b4f98dad..b5f20645 100644
--- a/crates/ai-memory-llm/src/lib.rs
+++ b/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};
diff --git a/crates/ai-memory-llm/src/opencode.rs b/crates/ai-memory-llm/src/opencode.rs
index 0d2c668a..4d1cb5c5 100644
--- a/crates/ai-memory-llm/src/opencode.rs
+++ b/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 })
}
}
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index 6e510e5e..4ed7a753 100644
--- a/docker/docker-compose.yml
+++ b/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
diff --git a/docs/install.md b/docs/install.md
index adfbbdb3..3aa77907 100644
--- a/docs/install.md
+++ b/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. |