openclaw - 💡(How to fix) Fix feat: expose resolved backend model in session_status and agent runtime [2 comments, 3 participants]

openclaw2026-03-21 05:48:06

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

openclaw/openclaw#51441•Fetched 2026-04-08 01:11:11

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Participants

Timeline (top)

commented ×2

Fix Action

Fix / Workaround

Workaround in use

Code Example

model: litellm/complex (requested)
   resolvedModel: openai/gpt-5.4 (actual)
   fallbackUsed: true

RAW_BUFFERClick to expand / collapse

Problem

When using LiteLLM (or any routing proxy) as the LLM provider, agents only see the requested model alias (e.g. litellm/complex) — not the actual backend model that was used (e.g. openai/gpt-5.4 or anthropic/claude-sonnet-4-6).

This creates a blind spot: agents can't answer "did a fallback happen?" or "what model actually served this response?" without log-diving.

Current behavior

session_status returns the configured/requested model. The agentMeta.model in runResult.meta is populated from CLI runners (claude-cli, codex, etc.) but not from the OpenAI-compatible path — so when LiteLLM routing is used, agentMeta.model falls through to fallbackModel ?? defaultModel (the configured alias, not the resolved backend).

persistSessionUsageUpdate stores modelUsed and providerUsed from agentMeta, so this gap flows through to the session store.

Requested feature

Capture response.model from OpenAI-compatible responses in the provider transport layer and expose it as agentMeta.resolvedModel / agentMeta.resolvedProvider
Add resolvedModel, resolvedProvider, fallbackUsed fields to GatewaySessionRow and persist them via persistSessionUsageUpdate

Expose in session_status tool output:

model: litellm/complex (requested)
resolvedModel: openai/gpt-5.4 (actual)
fallbackUsed: true

Include in agent runtime text injection so agents can introspect routing decisions without tool calls
Optional: pass session/agent metadata as LiteLLM request tags so /spend/logs entries can be correlated to specific agent sessions

Workaround in use

We currently query http://localhost:4000/spend/logs directly (LiteLLM's spend log API) to surface resolved model info. The fields model_group (= requested tier) and model (= actual backend) are both present there. This works but requires a separate API call and is not surfaced to the agent in-band.

Files involved

dist/agents/steerable-provider-transport.js — capture response.model from API responses
dist/auto-reply/reply/session-usage.js + .d.ts — add new fields to persistSessionUsageUpdate
dist/auto-reply/reply/agent-runner.js + followup-runner.js — pass resolved fields to usage update
dist/gateway/session-utils.types.d.ts + session store — add resolvedModel, resolvedProvider, fallbackUsed to GatewaySessionRow
dist/agents/tools/session-status-tool.js — expose in tool output
dist/commands/status.summary.js — expose in CLI status output

Impact

High — any deployment using LiteLLM, OpenRouter, or any routing proxy is blind to actual model routing. Debugging fallbacks requires log access rather than in-band observability.

extent analysis

Fix Plan

To address the issue, we need to capture the response.model from OpenAI-compatible responses and expose it as agentMeta.resolvedModel / agentMeta.resolvedProvider. Here are the concrete steps:

In dist/agents/steerable-provider-transport.js, capture response.model from API responses:

const response = await fetch(url, options);
const responseBody = await response.json();
const resolvedModel = responseBody.model;
// Expose resolvedModel as agentMeta.resolvedModel

In dist/auto-reply/reply/session-usage.js, add new fields to persistSessionUsageUpdate:

interface GatewaySessionRow {
  // ...
  resolvedModel: string;
  resolvedProvider: string;
  fallbackUsed: boolean;
}

function persistSessionUsageUpdate(sessionRow: GatewaySessionRow) {
  // ...
  sessionRow.resolvedModel = agentMeta.resolvedModel;
  sessionRow.resolvedProvider = agentMeta.resolvedProvider;
  sessionRow.fallbackUsed = agentMeta.fallbackUsed;
  // ...
}

In dist/auto-reply/reply/agent-runner.js and followup-runner.js, pass resolved fields to usage update:

function runAgent() {
  // ...
  const agentMeta = {
    // ...
    resolvedModel: resolvedModel,
    resolvedProvider: resolvedProvider,
    fallbackUsed: fallbackUsed,
  };
  // ...
  persistSessionUsageUpdate(sessionRow);
}

In dist/gateway/session-utils.types.d.ts, add resolvedModel, resolvedProvider, fallbackUsed to GatewaySessionRow:

interface GatewaySessionRow {
  // ...
  resolvedModel: string;
  resolvedProvider: string;
  fallbackUsed: boolean;
}

In dist/agents/tools/session-status-tool.js, expose in tool output:

function getSessionStatus() {
  // ...
  console.log(`model: ${agentMeta.model} (requested)`);
  console.log(`resolvedModel: ${agentMeta.resolvedModel} (actual)`);
  console.log(`fallbackUsed: ${agentMeta.fallbackUsed}`);
}

Verification

To verify that the fix worked, you can:

Check the session_status tool output to see if the resolvedModel and fallbackUsed fields are populated correctly.
Query the http://localhost:4000/spend/logs API to see if the model_group and model fields match the resolvedModel and fallbackUsed fields in the session_status tool output.
Test the agent runtime text injection to see if the agents can introspect routing decisions without tool calls.

Extra Tips

Make sure to update the documentation to reflect the new fields and behavior.
Consider adding logging or monitoring to track the usage of the new fields and detect any potential issues

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #autograd error #index setup #retrieval issue #search optimization #API routing

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

openclaw - 💡(How to fix) Fix feat: expose resolved backend model in session_status and agent runtime [2 comments, 3 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

Workaround in use

Code Example

Problem

Current behavior

Requested feature

Workaround in use

Files involved

Impact

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

TRENDING

openclaw - 💡(How to fix) Fix feat: expose resolved backend model in session_status and agent runtime [2 comments, 3 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

Workaround in use

Code Example

Problem

Current behavior

Requested feature

Workaround in use

Files involved

Impact

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING