Skip to main content
Glama
Praket7

agent-interop-runtime

by Praket7

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEX_HOMENoPath to Codex configuration directory when using a nonstandard location.
FREEBUFF_CLI_PATHNoAbsolute path to the Freebuff executable (e.g., freebuff.exe on Windows). Used in CLI mode.
INTEROP_READ_ONLYNoSet to '1' to enable read-only mode.0
OPENCODE_AUTO_STARTNoSet to 'false' to disable automatic starting of the OpenCode local server.true
OPENCODE_SERVER_URLNoURL for an existing OpenCode server. Set to another local port or remote URL.
FREEBUFF_MCP_CLI_MODENoSet to 'pty' for explicit Freebuff CLI mode. CLI mode always wins over Desktop discovery.
FREEBUFF_PROJECT_ROOTNoAbsolute path to the project root for CLI mode.
INTEROP_TOOLS_PROFILENoToolset profile: 'core', 'legacy', or 'full' (default 'full').full
OPENCODE_SERVER_PASSWORDNoPassword for remote OpenCode server.
OPENCODE_SERVER_USERNAMENoUsername for remote OpenCode server.
FREEBUFF_CLI_READY_PATTERNNoCustom regular expression for Freebuff CLI readiness detection.
INTEROP_ALLOW_VERIFICATIONNoSet to '1' to allow local verification (disabled by default).0
INTEROP_HANDOFF_TOKEN_BUDGETNoToken budget for handoff packets (default 2000).2000
FREEBUFF_DESKTOP_READINESS_FILENoPath to a readiness file containing a loopback URL/port and a current launch ID for Freebuff Desktop. Records older than ten minutes are ignored.

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
freebuff_statusB

Detect Freebuff and bridge capabilities.

list_projectsA

List discovered Freebuff projects.

list_threadsC

List Freebuff Desktop threads.

get_threadB

Read thread metadata.

get_thread_messagesA

Read visible messages for a thread.

get_active_workC

Read visible active work.

get_thread_progressC

Read live Desktop progress events for a thread. Results are bounded and read-only.

watch_threadB

Wait up to 30 seconds for live progress events, then return the bounded read-only snapshot.

get_thread_progress_summaryA

Return a simple user-facing live progress summary without raw event details.

watch_active_threadsA

Return the latest live progress summary for each active Desktop thread.

list_project_filesC

List safe project files.

read_project_fileC

Read one safe project file.

list_modelsA

List models exposed by the installed bridge.

list_agentsA

List provider adapters and their real capability grades.

list_agent_sessionsA

Discover native sessions across configured providers. Provider failures are returned separately from an empty session list.

get_work_graphA

Return the provider independent session and evidence graph, including any durable state recovery warning.

get_agent_diffB

Read native diff evidence while preserving provider identity.

events_readA

Read bounded native events from one shared per-session stream. Count- and deadline-bounded; pass the last event sequence back as afterSequence for exactly-once continuation.

evidence_listA

List evidence captured by the runtime. Metadata only: contents are addressable by evidence ID.

work_listA

List durable work records with objective previews and criteria counts.

work_getB

Read a durable work record and its evidence.

handoff_packetA

Read the bounded delivery packet for a handoff: fields kept within the token budget plus explicit omissions and how to request them.

conversation_listA

List shared conversations; metadata only unless detail:true.

conversation_readA

Read a cursor-paged transcript page; pass next back for exactly-once reads.

permission_pendingA

List provider permission requests awaiting an explicit human decision. Never auto-approved.

send_messageA

Send a text prompt to an existing Freebuff thread.

stop_threadB

Stop a running Freebuff turn.

resume_threadC

Resume a paused Freebuff thread.

set_modelC

Set the model for an existing thread when supported.

set_reasoningC

Set the reasoning effort for an existing thread when supported.

agent_sendB

Send a message to a provider native session. Model, agent, and reasoning are separate controls. For OpenCode, accepted means transport queued the prompt and does not mean completion.

agent_cancelC

Cancel work in a provider native session.

session_createC

Create a native provider session when supported.

session_resumeC

Resume or reattach to an exact native session.

permission_respondC

Respond to a provider permission request when supported.

session_set_modelC

Change the model for an exact native session when supported. OpenCode accepts providerID and modelID.

session_set_reasoningB

Change reasoning effort for an exact native session when supported.

conversation_createC

Create a local shared conversation coordinator record.

conversation_reconcileA

Recover interrupted outbound sends after a crash: reclassify stuck queued/unknown records and close them with caller-verified provider receipts (never auto-resends).

conversation_joinC

Attach an exact native provider session to a shared conversation.

conversation_sendA

Persist before delivery; receipt distinguishes queued/rejected/delivery_unknown. Pass idempotencyKey (e.g. workId/handoffId) to make retries safe. Replies need another explicit send.

work_createB

Create a durable work item with acceptance criteria.

handoff_createB

Create a structured work handoff between exact native sessions. The durable record keeps every field; the response reports the delivery packet size against the token budget and any explicit omissions.

review_createB

Record a review; caller submissions are agent_claim, never provider observations.

review_requestB

Send an evidence-backed review request; the repository-diff fallback requires the subject session workspace and never guesses process.cwd().

work_verifyB

Run all accepted verification commands (max 8). Entries are strings or {executable,args,cwd}. Requires INTEROP_ALLOW_VERIFICATION=1.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.7/5.0

Scored across 46 tools

Disambiguation2/5

Several tools have overlapping boundaries: send_message, agent_send, and conversation_send all send prompts in different contexts, while watch_thread, watch_active_threads, get_thread_progress, and get_thread_progress_summary all expose live progress. The thread/session/conversation layering is substantial and requires careful reading to avoid misselection.

Naming Consistency2/5

Naming conventions are mixed: some tools use verb_noun (list_models, create_work), others use noun_verb (evidence_list, work_get, conversation_read), and there are inconsistent variants like set_model vs session_set_model and send_message vs agent_send. The lack of a single predictable pattern makes the 46-tool surface harder to navigate.

Tool Count2/5

46 tools is too many for a coherent agent-facing surface, even for a broad interop runtime. While the domain is genuinely large, the count forces agents to choose among dozens of closely related operations and would benefit from consolidation or grouping.

Completeness3/5

The set covers a broad runtime lifecycle: sessions, conversations, durable work, handoffs, reviews, permissions, and evidence. Notable gaps remain, however: evidence contents are said to be addressable by ID but there is no generic evidence read tool, and durable work/handoff/conversation records lack update, close, or delete operations.

Maintenance

ActivityMaintained
ResponsivenessNo issues