openclaw - ✅(Solved) Fix bug(agents): OpenAI WS late-map buffering gates on key existence not phase validity — unphased commentary can leak to UI [5 pull requests, 1 comments, 1 participants]

100yenadmin · 2026-04-05T18:54:31Z

[openclaw] PR 61463: fix agents,gateway : phase-aware assistant text extraction — suppress OpenAI commentary leaks in sessions-helpers, TUI, and REST history -… # PR #61463: fix(agents,gateway): phase-aware assistant text extraction — suppress OpenAI commentary leaks in sessions-helpers, TUI, and REST history - Repository: openclaw/openclaw - Author: 100yenadmin - State: closed | merged: True - Link: https://github.com/openclaw/openclaw/pull/61463 ## Description (problem / solution / changelog) ## What this fixes (plain English) Several places in the codebase that display assistant text were not aware of the phase system (commentary vs. final answer). This meant internal "thinking out loud" commentary could leak into user-visible surfaces like the TUI and HTTP/SSE session history endpoints. This PR makes those surfaces phase-aware, and hardens heartbeat session resolution against subagent key leaks. ## Technical details Follow-up to #59643 and #59150, which fixed phase separation in the core WS path. Post-merge audit found adjacent surfaces still using phase-blind extraction. **Surfaces fixed:** - `src/tui/tui-formatters.ts` — assistant text extraction now uses `extractAssistantVisibleText()` to prefer `final_answer` over `commentary` phase blocks - `src/infra/heartbeat-runner.ts` — heartbeat session resolution now rejects subagent session keys, falling back to the main session key instead of leaking into subagent scopes - `src/gateway/sessions-history-http.test.ts` — regression test: REST history applies `chat.history` sanitization (strips NO_REPLY messages, preserves phase blocks) - `src/tui/tui-formatters.test.ts` — regression test: mixed commentary + final_answer blocks extract only the visible final answer **Explicitly deferred:** `extractAssistantTextForSilentCheck` and buffered delta/final rendering — lower-confidence, more behaviorally sensitive. ## Related - Follow-up to #59643 and #59150 - Follow-up issues: #61474, #61475, #61476, #61477, #61478 - Companion PRs: #61529, #61528, #61527 - Related PRs: #61855, #61816 ## Test plan - [x] 27/27 TUI formatter tests pass - [x] Regression test for mixed commentary + final_answer in TUI extraction - [x] HTTP history regression test (REST path shares chat.history sanitization, strips NO_REPLY messages) - [x] SSE seq validation for NO_REPLY message stripping - [x] sessions-history-http gateway integration tests have 2 pre-existing infra failures (also fail on upstream/main) ## Changed files - `CHANGELOG.md` (modified, +1/-0) - `src/infra/heartbeat-runner.subagent-session-guard.test.ts` (added, +72/-0) - `src/infra/heartbeat-runner.ts` (modified, +24/-17) - `src/tui/tui-formatters.test.ts` (modified, +20/-0) - `src/tui/tui-formatters.ts` (modified, +25/-0) --- # PR #61481: fix(agents): harden OpenAI phase-aware visible text — suppress commentary partials, prevent empty final_answer fallback leak - Repository: openclaw/openclaw - Author: 100yenadmin - State: closed | merged: False - Link: https://github.com/openclaw/openclaw/pull/61481 ## Description (problem / solution / changelog) ## Summary - fix phase-aware visible text extraction so an explicit `final_answer` block never falls back to commentary or legacy unphased text when it sanitizes to empty - suppress all commentary-phase partial streaming output regardless of whether extracted visible text is non-empty - keep session-history HTTP/SSE sanitization aligned with the hardened chat history path - add regression tests covering both leak paths and the session-history follow-through ## Context This hardens the merged #59643 behavior against two P1 leaks: - fixes #61474 - fixes #61475 ## Related issues / bug family - related to #25592 - related to #59536 - related to #59918 - related to #44213 - related to #49438 - related to #53960 ## Parent / sibling PRs - parent: #59643 — core phase-separation fix (merged) - sibling: #61463 — phase-aware extraction in sessions-helpers, TUI, and history paths ## Remaining follow-ups from the same adversarial review - #61476 — replay splitting corrupts phase on mixed messages - #61477 — late-map buffering gates on key existence, not phase validity - #61478 — function-call replay silently loses malformed arguments ## Related open PRs - #59920 — prefer terminal reply fields in CLI JSONL parser - #61151 — drop partialJson streaming artifacts from session history - #61337 — disable OpenAI tool-use pairing repair ## Testing - npm exec -- node --no-maglev ./node_modules/vitest/vitest.mjs run --config vitest.config.ts src/agents/pi-embedded-utils.test.ts src/agents/pi-embedded-subscribe.handlers.messages.test.ts - npm exec -- node --no-maglev ./node_modules/vitest/vitest.mjs run --config vitest.config.ts src/gateway/sessions-history-http.test.ts ## Changed files - `.agents/skills/openclaw-parallels-smoke/SKILL.md` (modified, +13/-0) - `.agents/skills/openclaw-qa-testing/SKILL.md` (added, +86/-0) - `.agents/skills/openclaw-qa-testing/agents/openai.yaml` (added, +4/-0) - `.github/lab

openclaw2026-04-05 18:54:31

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#61477•Fetched 2026-04-08 02:58:13

View on GitHub

Comments

Participants

Timeline

Reactions

Author

100yenadmin

Participants

100yenadmin

Timeline (top)

cross-referenced ×9referenced ×7closed ×1commented ×1

Root Cause

Text deltas are buffered until outputItemPhaseById has the item id. But the map is populated on the first response.output_item.added/done seen for that item, and stores undefined if event.item.phase is missing/invalid at that moment:

outputItemPhaseById.set(event.item.id, itemPhase); // may be undefined
...
if (outputItemPhaseById.has(event.item_id)) emitBufferedTextDelta(...)

The gate is presence of the map key, not validity of the phase. Once an item event arrives with undefined phase, all subsequent text for that item emits immediately as unphased — even if a later output_item.done event would carry the correct phase.

Code Example

outputItemPhaseById.set(event.item.id, itemPhase); // may be undefined
...
if (outputItemPhaseById.has(event.item_id)) emitBufferedTextDelta(...)

RAW_BUFFERClick to expand / collapse

Bug

After #59643 merged, the WS late-map buffering in src/agents/openai-ws-stream.ts can permanently misattribute early text deltas as "no phase."

Root cause

outputItemPhaseById.set(event.item.id, itemPhase); // may be undefined
...
if (outputItemPhaseById.has(event.item_id)) emitBufferedTextDelta(...)

Impact

If a provider emits output_item.added before phase is populated (or emits contradictory metadata between added/done), commentary text can leak as unphased visible content. This is the "malformed/missing phase metadata" edge case that the buffering was meant to protect against.

Code location

src/agents/openai-ws-stream.ts:922-945, 953-969, 1029-1049, 1052-1075

Suggested fix

Gate on outputItemPhaseById.get(event.item_id) !== undefined (phase is known and valid), not just outputItemPhaseById.has(event.item_id) (any item event arrived).

Severity

P2 — requires a specific provider timing quirk to trigger, but when it does, it defeats the buffering protection entirely.

Parent fix: #59643

extent analysis

TL;DR

Update the condition for emitting buffered text deltas to check for a valid phase in outputItemPhaseById instead of just the presence of the item ID.

Guidance

Identify the lines in src/agents/openai-ws-stream.ts where outputItemPhaseById.has(event.item_id) is used to decide whether to emit buffered text deltas.
Replace this condition with outputItemPhaseById.get(event.item_id) !== undefined to ensure that only items with a known and valid phase are emitted.
Verify that this change fixes the issue by testing with providers that previously triggered the "malformed/missing phase metadata" edge case.
Review the code changes in the suggested fix to understand how the buffering protection was meant to work and how the update addresses the problem.

Example

// Before
if (outputItemPhaseById.has(event.item_id)) emitBufferedTextDelta(...)

// After
if (outputItemPhaseById.get(event.item_id) !== undefined) emitBufferedTextDelta(...)

Notes

This fix assumes that the issue is solely due to the incorrect condition in the buffering logic. If other factors contribute to the problem, additional changes may be necessary.

Recommendation

Apply the suggested workaround by updating the condition for emitting buffered text deltas to check for a valid phase, as this directly addresses the identified root cause of the issue.

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 routing #API middleware #SSR setup #ISR setup #authentication setup

Still need to ship something?

×6

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

openclaw - ✅(Solved) Fix bug(agents): OpenAI WS late-map buffering gates on key existence not phase validity — unphased commentary can leak to UI [5 pull requests, 1 comments, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Fix Action

Fixed

PR fix notes

PR #61463: fix(agents,gateway): phase-aware assistant text extraction — suppress OpenAI commentary leaks in sessions-helpers, TUI, and REST history

Description (problem / solution / changelog)

What this fixes (plain English)

Technical details

Related

Test plan

Changed files

PR #61481: fix(agents): harden OpenAI phase-aware visible text — suppress commentary partials, prevent empty final_answer fallback leak

Description (problem / solution / changelog)

Summary

Context

Related issues / bug family

Parent / sibling PRs

Remaining follow-ups from the same adversarial review

Related open PRs

Testing

Changed files

PR #61527: fix(agents): OpenAI function-call replay — preserve malformed arguments instead of silent {} replacement

Description (problem / solution / changelog)

What this fixes (plain English)

Technical details

Related

Test plan

Changed files

PR #61528: fix(agents): OpenAI WS stream — gate buffered text delta on valid phase value, not just outputItemPhaseById key existence

Description (problem / solution / changelog)

What this fixes (plain English)

Technical details

Related

Test plan

Changed files

PR #61529: fix(agents): OpenAI WS replay — inherit message-level phase for untagged blocks when siblings have explicit textSignature

Description (problem / solution / changelog)

What this fixes (plain English)

Technical details

Related

Test plan

Changed files

Code Example

Bug

Root cause

Impact

Code location

Suggested fix

Severity

Related

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING