Replace default Voyager controller with upstream AltoClef 0.19 gamer, retain current world and inventory, correct client startup and telemetry, Survival/Normal, and Muse-only OpenCode coaching. Verified Java17 bridge build and 57 targeted tests.
Restore Naldo Muse connection and start a fresh normal world
Recover Mineflayer socket errors and pending requests, activate connection guards, bound startup, and recover stalled Naldo runs. Start a new normal world and fresh Naldo checkpoint while retaining old worlds, checkpoints and Xbox authentication. Verified 15 Node connection tests and 57 targeted Python tests; old flat-generator expectation mismatch remains unchanged.
29 days ago
Add AltoClef third player supervised by keyless OpenCode
Keep Minecraft and bots separate from model weights in Mine. Add pinned AltoClef 0.19/Fabric 1.19.4 CPU client through the existing ViaProxy, local telemetry bridge and OpenCode 1.18.34 using the user-owned Mine endpoint. Preserve Creative world, Xbox auth and existing checkpoints. Verify completion only after entering End and observing credits. Reviewed and compiled locally; 43 tests passed, 1 skipped. Full client startup remains to be verified in the Space.
Repair Voyager deadlines and connect both bots to Mine
Keep server-only mode and saved worlds. Restore the missing engine deadline helper, clean isolated runner process groups, and route both bots to the separate Mine endpoint. Preserve checkpoints and existing Creative mode.
debug: add /voyager/probe to tell a wedged runner from a busy one (app.py)
The status published `gpu_enabled: False` and `n_gpu_layers: 0` as hardcoded literals. Nothing checked anything, so if the installed wheel had CUDA compiled in and a load site ever asked for offload, the status would still have said 'cpu-only'.
cpu_backend.py now derives the claim:
- the native backend libraries actually shipped with llama_cpp are listed, and any CUDA/cuBLAS/Vulkan/Metal/ROCm one would be named;
- every Llama(...) load site is asserted to pass n_gpu_layers=0 and offload_kqv=False, because omitting the argument is not the same as passing zero -- it lets the library decide;
- /status publishes cpu_only, gpu_offload_supported, gpu_backend_libraries and cuda_libraries_present, and gpu_enabled is now computed rather than typed;
- the boot log prints the same evidence once.
A mistake was made here and caught before deploying, which is why the binary query is opt-in. The first version called llama_cpp.llama_supports_gpu_offload() at module import, before llama_backe…
Stop the leave/rejoin loop, and give Voyager the strongest CPU-viable brain
1. Why Gemini_Bot left and rejoined the server
Measured from the run logs: three leave/rejoin cycles in 3.5 minutes, at 07:06:23, 07:07:55 and 07:09:46. Each one is
openai.error.ServiceUnavailableError: The server is overloaded or not ready yet.
raised out of curriculum.run_qa -> qa_llm -> the Gemini proxy returning 503. Upstream lets it propagate, so main() unwinds, the finally block kills the Mineflayer child, and the watchdog restarts the runner -- the bot leaves the game and comes back. restart_count was 4.
voyager_runner now retries the learning loop in place with bounded backoff (VOYAGER_LEARN_BACKOFF_SECONDS, doubling to VOYAGER_LEARN_BACKOFF_CAP_SECONDS) instead of exiting, so a provider blip no longer costs the Minecraft connection. learn(reset_env=False) is safe to re-enter: upstream sets self.resume = True after the first call, so a retry takes the soft-reset branch and keeps the inventory.
2. The brain
granite-4.0-h-tiny (7B total / 1B active) could not ge…
Restore official Voyager decision agents and attest the runtime
naldo
5ddf32a
Remove the local curriculum/action/critic/skill overrides, the
deterministic action parser, the affordance catalog, and the build
blueprints, so Curriculum, Action, Critic and SkillManager are the
upstream implementations at the pinned commit.
The single declared adaptation is the curriculum parse-failure retry
feedback, applied through voyager_runtime_contract and recorded in
.upstream-expected/ for the AST attestation. Skill templates are
quarantined before the learning loop, and template skills can no longer
drive a build catalog.
Add Gemini CLI Flash Lite companion bot and server stability telemetry
naldo
7e83939
Optimize Granite Voyager for 16 CPU cores
naldo
1105b06
Benchmark Granite H Tiny for Voyager
naldo
3d231ae
Switch Voyager to Qwen2.5 Coder 7B
naldo
c79a040
Switch Voyager to Qwen2.5 Coder 3B
naldo
8c766aa
Document and validate Voyager 4B runtime
naldo
4c939e3
Reset Voyager world and harden surface navigation
naldo
23dd9d0
Run Voyager entirely on Qwen3 4B Q4_K_M
naldo
0b6aa0b
Restore high-throughput CPU batching
naldo
22ffce1
Optimize CPU inference latency for Voyager
naldo
fd35e0e
Align runtime with official Voyager environment
naldo
38fde3a
Use 30B for all Voyager agents and pin Minecraft 1.19
naldo
06b864a
Route Voyager critical agents to 30B and auxiliary agents to 4B
naldo
9b4728a
Restore best-compatible Qwen3 Coder brain
naldo
0c7e75a
Switch Voyager brain to Qwen3 4B agentic model
naldo
f9c7f63
Add service watchdog for continuous Minecraft autonomy
naldo
efbddab
Run original Voyager autonomously in same ZeroGPU Space
