Opencode improvements

README.md

@@ -63,8 +63,9 @@ Supported keys when the manifest is present:
 | `name` | project directory name | Must match `^[A-Za-z0-9_.-]+$`. Used for image/container naming. |
 | `packages_extra` | *empty* | Additional Debian packages installed during `docker/podman build`. Tokens must be alphanumeric plus `+.-`. |
 | `agent` | `codex` | AI backend: `codex` (OpenAI Codex CLI) or `opencode` (Anomaly opencode CLI). |
-| `opencode_server` | `http://localhost:11434` | OpenAI-compatible server URL (opencode only). Supports llama.cpp, Ollama, vLLM, etc. |
-| `opencode_model` | `llama3` | Model name on the server (opencode only). |
+| `opencode_server` | `http://localhost:8080` | OpenAI-compatible server URL (opencode only). Supports llama.cpp, Ollama, vLLM, etc. |
+| `opencode_model` | `bartowski/Qwen_Qwen3.5-9B-GGUF:Q8_0` | Model name on the server (opencode only). |
+| `opencode_context` | `256K` | Context window for the opencode model. Accepts an integer optionally suffixed with `K`, `M`, or `G`. |
 | `allow_host_network` | `false` | `true` opts into `--network host`; keep `false` unless the project absolutely requires direct access to host-local services. |
 
 Values containing `$`, `` ` ``, or newlines are rejected to prevent command injection. Setting illegal keys or malformed values aborts the run before containers start.
@@ -73,7 +74,7 @@ Values containing `$`, `` ` ``, or newlines are rejected to prevent command inje
 
 **Codex** (default): Uses OpenAI Codex CLI with state stored in `~/.codex/`. Supports login mode for credential sharing.
 
-**opencode**: Uses Anomaly opencode CLI with state stored in `~/.opencode/`. Connects to any OpenAI-compatible inference server (llama.cpp, Ollama, vLLM, etc.). No authentication required for self-hosted models; API keys supported via manifest if needed.
+**opencode**: Uses Anomaly opencode CLI with state stored in `~/.opencode/`. sloptrap downloads the latest Linux CLI release artifact from Anomaly during image builds, verifies its digest from the GitHub release metadata, and copies it into the container image. Connects to any OpenAI-compatible inference server (llama.cpp, Ollama, vLLM, etc.). When `opencode_server` points at `localhost` under isolated networking, sloptrap rewrites it to `http://sloptrap.host:...` so host-local model servers remain reachable from inside the container. No authentication required for self-hosted models; API keys supported via manifest if needed.
 
 ### `.sloptrapignore`
 
@@ -142,7 +143,7 @@ The launcher executes targets sequentially, so `./sloptrap repo build run` perfo
   - **Codex**: project directory at `/workspace`; `${HOME}/.codex/sloptrap/state/<project-hash>` at `/codex`; auth at `/codex/auth.json`.
   - **opencode**: project directory at `/workspace`; `${HOME}/.opencode/sloptrap/state/<project-hash>` at `/codex/state/opencode`; state at `/codex/state`.
 - Ignore filter: `.sloptrapignore` entries are overlaid with tmpfs directories or empty bind mounts so data remains unavailable to the agent.
-- Network: isolated networking is used by default; `allow_host_network=true` opts into `--network host`.
+- Network: isolated networking is used by default; `allow_host_network=true` opts into `--network host`. For isolated runs, sloptrap injects `sloptrap.host` as a container-side hostname for the host gateway. On Podman `slirp4netns`, opencode runs also enable host loopback access so host-local servers bound to `localhost` remain reachable.
 - Process context: standard runs drop capabilities, set `no-new-privileges`, use a read-only root filesystem, and keep scratch paths (`/tmp`, `/run`, `/run/lock`) on tmpfs.
 - Agent configuration:
   - **Codex**: runtime flags fixed to `--sandbox danger-full-access --ask-for-approval never`. Supports login mode for credential sharing.