Bundu standards

Harness conformance checklist

Status: complete as of 2026-11-17, on the owner's request "finish the harness checklist". It is a checklist, not a standard: it has no schema and no vocabulary terms. It is published at standards.bundu.org/harness-checklist/ (owner, 2026-11-19), so its register entry (harness_checklist) is proposed, awaiting the owner's adoption. Tracked in #50.

A harness is the loop around a model: it builds the context, calls the model, runs tools, asks for permission, keeps a log and may run code in a sandbox. Following AGENTS.md ("adopt the global standard; where none exists, write one"), this checklist does not define a harness. It says what a conforming Bundu harness must expose, names the existing standard to use for each part, and states the gaps. Claims are labelled measured (read at source on the date and URL given) or inferred (my reading; verify before relying on it).

1. Parts that already have a standard: use it

Every row below is a standard in the register (register/register.yaml). The version and licence are the register's, each read at source on the date it records.

PartA conforming harness must…Use (register id, status)Version / licence
Tools and contextcall tools and read context through the Model Context ProtocolMCP (mcp, adopted)revision 2026-07-28
Instructionsread project instructions from AGENTS.mdAGENTS.md (agents_md, adopted)unversioned; MIT
Skillsload reusable skills as SKILL.md foldersAgent Skills (agent_skills, adopted)unversioned (no tags); Apache-2.0 code, CC-BY-4.0 docs
Model wire shapeexchange one request and response as Open Responses itemsOpen Responses (open_responses, adopted)pin the dated OpenAPI file (2026-04-24), not openapi.json; Apache-2.0
Agent to agentdelegate to other agents through A2AA2A (a2a, adopted)1.0.0
Sandbox lifecyclecreate, run in and destroy a sandbox through a standard protocolOpenSandbox (opensandbox, adopted 2026-11-17)Lifecycle API 0.1.0 (pre-v1), Execd API 1.0.0; Apache-2.0; an AAIF project. Measured 2026-11-17 at commit f1e4ac0
Editor to agentif it talks to an editor, use ACPAgent Client Protocol (agent_client_protocol, adopted 2026-11-15)protocol v1; Apache-2.0; interim Zed and JetBrains governance, no foundation host
Stored conversationsexport and import chats, projects, saved answersBCI (bci, adopted 2026-11-15)0.1.0; first implementation nyuchi/nyuchi-servers-api#50; vocabulary terms stable in vocab.bundu.org
Session logwrite each session as an ordered trajectoryATIF (atif, adopted 2026-11-14)ATIF-v1.8 (RFC 0001, Active, April 2026); Apache-2.0

ACP and BCI were adopted in #70 (merged 2026-11-17), and OpenSandbox by the owner on 2026-11-17. Every row's standard is now adopted. OpenSandbox's Lifecycle API is pre-v1, so a harness pins the OpenAPI files it builds against. Bundu runs no sandbox today, so that row applies only once a Bundu harness runs code.

The Agentic AI Foundation's projects

The AAIF lists ten projects (aaif.io/projects, read 2026-11-17). Measured.

2. Parts a second gap check found partly covered

Read at source 2026-11-11. ATIF: harbor-framework/harbor, rfcs/0001-trajectory-format.md (Apache-2.0, last push 2026-11-11, current format ATIF-v1.8, no spec release other than the RFC's version history). OpenTelemetry GenAI: open-telemetry/semantic-conventions-genai docs/gen-ai/ (Apache-2.0, last push 2026-11-11, every document status Development, no release cut).

PartWhat existsEvidence
Session logATIF-v1.8 is a session-log interchange format: ordered steps with source (system, user, agent), message, tool_calls, observation, metrics, embedded subagent trajectories and audio. Measured. It is Harbor's own format, written for evaluation and training runs.ATIF RFC, sections II and version history
Context managementATIF section VII is a convention (step.extra.context_management) that records compaction, pruning and injection, with a normative replace boundary rule, plus is_copied_context. Measured. It records what happened; it does not say what a harness should keep.ATIF RFC, section VII
TelemetryOTel GenAI defines spans for inference, embeddings, retrieval, execute_tool, create_agent, invoke_agent, memory operations (gen_ai.memory.client) and agent-skill loading, with gen_ai.conversation.id. Measured. Development status: names may change.README.md, gen-ai-spans.md, execute-tool.md, gen-ai-agent-spans.md
PermissionsACP v1 has session/request_permission (coordinator, 2026-11-11). No permission field appears in the ATIF RFC or in six OTel GenAI documents searched by keyword (permission, approval). Measured for those files only.keyword search of the files named

3. Gaps, checked at source 2026-11-17

Each gap below was checked at source on 2026-11-17. Repositories were read at these commits: Codex 05ae1b0, Gemini CLI 4fa64e7, OpenHands software-agent-sdk 06f643c, goose eb4f412, MCP 05aeb07, A2A b30ab16, OpenTelemetry semantic-conventions-genai e6658f1, Harbor 110c71b, Open Responses dce9ddb and LangGraph 02f2c2e.

  1. Context policy: partly covered. This is what a harness must keep, drop or summarise, and who may see it.

    • Open Responses 2026-04-24 has truncation ("auto": the server "MAY truncate earlier parts" and "SHOULD apply sensible heuristics"), previous_response_id (the server "MUST preserve the semantic order") and a /responses/compact endpoint. That is provider-side policy, not harness policy.
    • ATIF section VII reconstructs the context after the fact.
    • OTel GenAI says instrumentations "SHOULD NOT capture" inputs and outputs by default, which covers telemetry only.
    • No rule for what a harness keeps, or for who may see it, was found in MCP. Measured.
  2. Permission model: partly covered.

    • MCP 2026-07-28 (server/tools.mdx): "there SHOULD always be a human in the loop with the ability to deny tool invocations".
    • MCP elicitation (client/elicitation.mdx): clients MUST "provide clear decline and cancel options".
    • MCP tool annotations (destructiveHint and the others) are hints that clients MUST treat as untrusted unless the server is trusted.
    • A2A 1.0.0 section 7.6: an agent that needs human approval before a destructive action MUST move to TASK_STATE_AUTH_REQUIRED. Section 7.6.4 leaves "scope, representation, validity, or revocation" undefined.
    • ACP has session/request_permission, between an editor and an agent only.
    • Measured. No standard defines remembered grants, grant scope or how an approval is recorded.
  3. Cross-harness tool-call dialects: still a gap. Four wire dialects are in use: Chat Completions tool_calls, the Responses API's function_call items, Anthropic tool_use and Gemini functionCall. None of the products below claims Open Responses conformance. The Codex CLI accepts only the Responses wire, which Open Responses is based on. Measured for the repositories and vendor pages named. The Qwen Responses page was read from search excerpts only.

    ProductTool-call wireSessions on diskMCPAGENTS.mdSkillsACP
    DeepSeekChat Completions; Anthropic Messages; Responses (no store)n/an/an/an/an/a
    QwenChat Completions; Responses (OpenAI-compatible); DashScope nativen/an/an/an/an/a
    GLM (z.ai)Chat Completions; Anthropic Messagesn/an/an/an/an/a
    Codex CLIResponses only (wire_api = "chat" is refused)JSONL rollout filesyesyesyesthrough an adapter
    Gemini CLIGemini functionCallJSONL chat filesyesif configuredyesyes, as an agent
    OpenHandsChat Completions or Responses, through LiteLLMa state file and one JSON file per eventyesyesyesyes, as a client
    gooseits own message type, translated per providerSQLiteyesyesyesyes, as an agent

    So the harnesses agree on MCP, AGENTS.md, Agent Skills and, increasingly, ACP. They disagree on the model wire and on how a session is stored. BCI (stored conversations) and ATIF (session log) are the register's answer to the second disagreement. Nothing in the register answers the first beyond adopting Open Responses.

  4. Portable session log: decided. The owner adopted ATIF on 2026-11-14 (register id atif). BCI's ordered Message stream maps onto ATIF steps rather than defining its own log; the mapping is an open item on #48. ATIF is Harbor-hosted and evaluation-oriented, with no foundation host, so the adoption is of the format, not an endorsement of its steward.

    • ISO/IEC 24970 "AI system logging" (JTC 1/SC 42) is at stage 60.00, under publication. It is the nearest formal standard and has not been read here. Measured status only.

Checked and found not to be harness standards:

4. Bundu's own rules (not an external standard)

These are Bundu's rules for a conforming harness, taken from Shamwari. They are requirements here, not part of any standard above.

5. How to use this

A harness passes when, for every row of section 1 that applies to it, it uses the named standard, and it satisfies section 4. Section 3 lists what it cannot yet be checked against. Where section 3 names a partial standard (MCP's human-in-the-loop rules, A2A's AUTH_REQUIRED), a harness follows it.

What is left is the owner's, not the checklist's:

  1. Whether to write a Bundu profile for the two partly covered gaps: context policy, and permission grants. AGENTS.md's rule says to write one where none exists. The checklist does not start one.
  2. Running this checklist against Shamwari's harness (shamwari-ai/shamwari). The data-plane audit is nyuchi/nyuchi-servers-api#48.