PR #75980: fix(model): clarify session-scoped model switches

• Repository: openclaw/openclaw
• Author: addu2612
• State: closed | merged: False
• Link: https://github.com/openclaw/openclaw/pull/75980

Description (problem / solution / changelog)

Summary

Describe the problem and fix in 2-5 bullets:

• Problem: /model acknowledged a model switch without saying the override is scoped to the current session.
• Why it matters: users can mistake the acknowledgement for a durable agent default change, then get surprised after a reset or restart.
• What changed: model switch acknowledgements now say for this session when setting a non-default model.
• What did NOT change (scope boundary): this does not change persistence semantics, model selection logic, or default reset wording.

Change Type (select all)

• Bug fix
• Feature
• Refactor required for the fix
• Docs
• Security hardening
• Chore/infra

Scope (select all touched areas)

• Gateway / orchestration
• Skills / tool execution
• Auth / tokens
• Memory / storage
• Integrations
• API / contracts
• UI / DX
• CI/CD / infra

Linked Issue/PR

• Closes #75965
• Related #
• This PR fixes a bug or regression

Root Cause (if applicable)

• Root cause: the acknowledgement text did not describe the existing session-scoped behavior.
• Missing detection / guardrail: model directive tests checked that the success message existed, but not that it communicated the scope.
• Contributing context (if known): N/A

Regression Test Plan (if applicable)

• Coverage level that should have caught this:
  • Unit test
  • Seam / integration test
  • End-to-end test
  • Existing coverage already sufficient
• Target test or file: src/auto-reply/reply/directive-handling.model.test.ts
• Scenario the test should lock in: /model openai/gpt-4o reports that the model is set for this session.
• Why this is the smallest reliable guardrail: the affected behavior is the directive acknowledgement string.
• Existing test that already covers this (if any): model directive persistence tests already covered successful switching.
• If no new test is added, why not: N/A

User-visible / Behavior Changes

/model acknowledgements for non-default selections now say the switch applies to this session.

Diagram (if applicable)

Before:
/user sends /model openai/gpt-4o -> "Model set to openai/gpt-4o."

After:
/user sends /model openai/gpt-4o -> "Model set to openai/gpt-4o for this session."

Security Impact (required)

• New permissions/capabilities? (Yes/No) No
• Secrets/tokens handling changed? (Yes/No) No
• New/changed network calls? (Yes/No) No
• Command/tool execution surface changed? (Yes/No) No
• Data access scope changed? (Yes/No) No
• If any Yes, explain risk + mitigation: N/A

Repro + Verification

Environment

• OS: Linux
• Runtime/container: local repo test runner
• Model/provider: N/A
• Integration/channel (if any): text command acknowledgement
• Relevant config (redacted): N/A

Steps

1. Send /model openai/gpt-4o in a session where that model is allowed.
2. Read the acknowledgement text.

Expected

• The acknowledgement makes clear the switch applies to this session.

Actual

• Before this PR, the acknowledgement did not state the scope.

Evidence

Attach at least one:

• Failing test/log before + passing after
• Trace/log snippets
• Screenshot/recording
• Perf numbers (if relevant)

pnpm test src/auto-reply/reply/directive-handling.model.test.ts

Result: 47 tests passed.

Human Verification (required)

What you personally verified (not just CI), and how:

• Verified scenarios: model directive success acknowledgement includes for this session, alias acknowledgement includes the same scope text, and the targeted test file passes.
• Edge cases checked: default reset wording is unchanged.
• What you did not verify: live Telegram group behavior.

Review Conversations

• I replied to or resolved every bot review conversation I addressed in this PR.
• I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

• Backward compatible? (Yes/No) Yes
• Config/env changes? (Yes/No) No
• Migration needed? (Yes/No) No
• If yes, exact upgrade steps: N/A

Risks and Mitigations

• Risk: acknowledgement text changes can affect brittle tests or docs that assert the exact sentence.
  • Mitigation: updated the targeted unit tests for the new user-facing wording.

Changed files

• src/auto-reply/reply/directive-handling.impl.ts (modified, +1/-1)
• src/auto-reply/reply/directive-handling.model.test.ts (modified, +4/-1)
• src/auto-reply/reply/get-reply-directives-apply.ts (modified, +1/-1)