OnyxSi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WORKSPACE | No | CLI --workspace DIR: directory to serve over JSON-RPC stdio. When omitted in global client configs, OnyxSi targets the current project/workspace. | |
| MAX_INDEX_MB | No | CLI --max-index-mb MB: per-file size cap. | 2.0 |
| PROJECT_NAME | No | CLI --project-name NAME: namespace for the task wiki and antibody store. Defaults to the workspace folder name. | |
| MAX_SHADOW_MB | No | CLI --max-shadow-mb MB: temp shadow copy cap for tests. | 512.0 |
| TELEMETRY_OUT | No | CLI --telemetry-out PATH: append per-tool JSONL telemetry on shutdown. | |
| MAX_INDEX_FILES | No | CLI --max-index-files N: cap on indexed .py files. | 5000 |
| PYTHONIOENCODING | No | Python runtime environment variable used in the example MCP configuration. | utf-8 |
| PYTHONUNBUFFERED | No | Python runtime environment variable used in the example MCP configuration. | 1 |
| MAX_INDEX_TOTAL_MB | No | CLI --max-index-total-mb MB: total index byte budget. | 128.0 |
| NO_PRE_FLIGHT_GATE | No | CLI --no-pre-flight-gate: set to 'true' to allow vfs_mutate without causal_flight pre_flight. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vfs_inspectA | Read-only view: action=tree (dir map), skeleton (AST outline), read (line range), symbols (exact/prefix symbol lookup), grammar (GBNF export), resolve (canonical path or ref:// handle). USE WHEN: orienting, reading code, fetching folded content, finding a symbol, or checking the tool grammar. DO NOT USE: to write or run tests. |
| vfs_mutateA | Stage a write in the in-RAM Ghost overlay (disk untouched until commit). op=replace_file (default) | replace_node | insert_after | slice_patch | merge_patches (non-overlapping agent patches, unified imports). USE WHEN: applying a speculative code edit. DO NOT USE: for reads, or before causal_flight pre_flight. |
| ghost_sandboxB | Ghost overlay lifecycle: begin, mutate (path+content), test (blast-radius selection, or an explicit command run in a shadow copy of the workspace), commit (atomic, fsync+replace), discard, plus fork / switch_branch / list_branches / merge_best for in-RAM MCTS branches. USE WHEN: you need speculative edits, a rollback point, competing fixes, or to run the project's own tests against staged content. DO NOT USE: before knowing the blast radius. |
| causal_flightA | 4-stage flight recorder. pre_flight declares blast radius; ghost_burn checks drift (<15%); verify re-parses staged files; commit logs; reflect resets the 3-strike budget; bisect finds the culprit checkpoint. USE WHEN: before/after any non-trivial edit. DO NOT USE: instead of running the affected tests. |
| hypothesis_branchB | Orthogonal hypotheses (Jaccard <= 0.70) with falsification probes. mode=register|falsify (pass the observed probe_succeeded)|select. USE WHEN: several plausible root causes to prune. DO NOT USE: to run the probe. |
| wiki_task_syncA | Persist task state in .onyxsi/wiki/projects//tasks/TASK-/ (spec, progress, log), render AGENT_HANDOFF.md, and write TIME_TRAVEL_REPLAY.md. op=init|update|handoff|replay. USE WHEN: starting work, checkpointing, handing off. NOT a scratchpad; it writes real files. |
| graph_computeA | Deterministic local compute. engine=bm25 (CSR+BM25 search) | blast_radius (select+run impacted tests) | alu (type=eval | matrix_matmul | matrix_inv | ieee754). USE WHEN: locating code, checking test impact, or arithmetic without an LLM. DO NOT USE: for free-form reasoning or file edits. |
| mcp_orchestrateA | Run meta-tools as one dependency-ordered DAG; later steps read earlier output via '$prev.output' or '$.output'. USE WHEN: a fix needs inspect->mutate->test in one round-trip. DO NOT USE: for one call, parallel work, or nesting. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| tool-schema | Live JSON Schema of the Fixed 8 meta-tools. |
| tool-grammar | GBNF grammar compiled from the live tool schemas. |
| boot-audit | Zero-dependency / zero-UI audit of the kernel package. |
| telemetry | Call counters mirrored through the HAL shared-memory superblock. |
TDQS
Scored across 8 tools
Most tools occupy distinct phases (read, mutate, compute, orchestrate), and descriptions include explicit USE/DO NOT USE boundaries. However, vfs_mutate and ghost_sandbox both stage mutations in the Ghost overlay, and graph_compute overlaps slightly with vfs_inspect for code location, so an agent could confuse those boundaries.
All names use lowercase snake_case without camelCase or inconsistent casing. The structure is not a strict verb_noun pattern; some are domain-prefixed actions (vfs_inspect), others are noun compounds (ghost_sandbox, causal_flight), but it remains readable and predictable.
Eight tools are well-scoped for a speculative coding agent workflow, and each covers a distinct capability area (inspect, mutate, compute, sandbox, flight recorder, hypotheses, task sync, orchestration). No obvious redundancy that bloats the surface.
The set covers the core lifecycle: inspect, search/compute, speculative mutation, sandbox testing/commit/discard, causal tracking, hypothesis falsification, task persistence, and orchestration. Minor gaps exist around direct task query/list/delete or explicit file creation/deletion, but agents can likely work around them via overlay and wiki operations.