fix(agents): detect truncated API responses to prevent silent session hang by joelnishanth · Pull Request #89160 · openclaw/openclaw

joelnishanth · 2026-06-01T17:27:05Z

Summary

Fixes #89051.

Preserve Ollama's native done_reason: "length" instead of collapsing it to stop.
Treat length-limited terminal assistant turns as incomplete across runner, lifecycle, and trajectory decisions, including partial streamed text.
Preserve successful terminal outcomes when tools already produced durable output, media, messages, cron work, spawned work, or other committed side effects.
Keep existing toolUse semantics unchanged. No OpenAI or Anthropic transport code changed.

Verification

Focused test set: 345 passed across Ollama stream handling, incomplete-turn classification, trajectory status, lifecycle handling, subscription delivery, and spawn-workspace suites.
TypeScript and lint: changed core/extensions production and test typechecks passed; focused oxlint passed.
Broad Testbox: tbx_01kv3kmhyx52hb7w9awywk9rjy passed pnpm check:changed for core, coreTests, extensions, and extensionTests.
Autoreview: fresh final review reported no accepted/actionable findings.

Real behavior proof

Behavior addressed: Ollama responses ending with done_reason: "length" could be normalized to success and leave an embedded run with partial or empty output instead of an incomplete-turn response.
Real environment tested: local Ollama 0.30.8 with qwen3.5:9b; official OpenAI Codex OAuth gateway harness with an MCP/tool probe.
Exact steps or command run after this patch: forced Ollama truncation with num_predict: 3, then exercised the real OpenClaw Ollama stream adapter and incomplete-turn resolver; ran OPENCLAW_LIVE_CODEX_HARNESS=1 OPENCLAW_LIVE_CODEX_HARNESS_MCP_PROBE=1 OPENCLAW_LIVE_CODEX_HARNESS_MODEL='openai/gpt-5.5' node scripts/test-live.mjs --codex-harness -- src/gateway/gateway-codex-harness.live.test.ts.
Evidence after fix: Ollama produced done_reason: "length"; OpenClaw returned stopReason: "length", partial text The color of, and the incomplete-turn response. The Codex OAuth MCP/tool smoke passed.
Observed result after fix: token-limited partial/empty Ollama responses no longer silently complete, while durable tool output and existing official OpenAI tool calling remain successful.
What was not tested: direct Anthropic live tool calling. Available Anthropic credentials reached the official API but failed billing before prompt/tool execution. Anthropic transport code is untouched; shared lifecycle/tool-output behavior is covered by focused tests.

clawsweeper · 2026-06-01T17:28:59Z

Codex review: found issues before merge. Reviewed June 1, 2026, 7:49 PM ET / 23:49 UTC.

Summary
The PR adds embedded-runner truncated assistant-turn detection, warning logs, regression tests, and a committed live Ollama proof screenshot.

PR surface: Source +55, Tests +148, Config 0. Total +203 across 4 files.

Reproducibility: Do we have a high-confidence way to reproduce the issue? Partly: the linked report and proof screenshot demonstrate an Ollama done_reason: "length" truncation, and source inspection shows the PR's new guard is not reached for current Ollama length terminals unless provider mapping changes.

Review metrics: 1 noteworthy metric.

Committed proof assets: 1 binary image added. OpenClaw policy routes PR proof media to comments or artifact storage, so this is a merge-relevant cleanup fact beyond ordinary file counts.

Merge readiness
Overall: 🧂 unranked krab
Proof: 🐚 platinum hermit
Patch quality: 🧂 unranked krab
Result: blocked by patch quality or review findings.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

[P2] Map Ollama done_reason: "length" to stopReason: "length" and add a native stream regression that reaches the embedded runner.
Remove .github/proof/proof-89051-live-ollama.png from the branch and keep proof in the PR body/comment or artifact storage.
[P1] Get maintainer acceptance for the fail-closed abandoned-run behavior before merge.

Risk before merge

[P1] Merging as-is could leave the reported real Ollama length-truncation path unfixed because the provider stream still normalizes done_reason: "length" to stop before the runner detector runs.
[P1] The PR intentionally turns some malformed partial-payload turns from successful working exits into abandoned error payloads, so maintainers should explicitly accept that fail-closed behavior for existing long-running sessions before merge.

Maintainer options:

Fix provider length propagation first (recommended)
Map Ollama done_reason: "length" to the shared length stop reason and add a native stream regression before relying on the runner detector.
Accept runner-only mitigation with owner signoff
Maintainers could intentionally land the generic runner guard first, but they should explicitly accept that real Ollama length proof remains incomplete and that partial-payload turns now fail closed.
Pause until the linked issue path is narrowed
If the desired lifecycle behavior is still unsettled, keep this PR paused while the linked issue decides whether truncation should abandon, retry, or recover differently.

Next step before merge

[P1] Maintainer review is needed because the remaining blocker combines provider-boundary ownership with an intentional fail-closed compatibility change, not only a mechanical edit.

Security
Cleared: No dependency, workflow, secret-handling, or code-execution security regression was found; the binary proof image is handled as merge-readiness artifact churn rather than a concrete security issue.

Review findings

[P1] Preserve length stops before relying on this guard — src/agents/embedded-agent-runner/run/incomplete-turn.ts:134
[P2] Remove the committed proof image — .github/proof/proof-89051-live-ollama.png:1

Review details

Best possible solution:

Preserve native provider length termination at the Ollama stream boundary, remove the committed proof image, keep the runner guard as a generic safety net, and land only after maintainer acceptance of the fail-closed liveness behavior.

Do we have a high-confidence way to reproduce the issue?

Do we have a high-confidence way to reproduce the issue? Partly: the linked report and proof screenshot demonstrate an Ollama done_reason: "length" truncation, and source inspection shows the PR's new guard is not reached for current Ollama length terminals unless provider mapping changes.

Is this the best way to solve the issue?

Is this the best way to solve the issue? No; the runner guard is a useful safety net, but the best fix must also preserve the provider's native length terminal signal and get maintainer acceptance for the fail-closed lifecycle change.

Full review comments:

[P1] Preserve length stops before relying on this guard — src/agents/embedded-agent-runner/run/incomplete-turn.ts:134
This guard only fires when the runner sees a missing stop reason or stopReason === "length", but current Ollama stream code builds every non-tool terminal response as stopReason: "stop" and emits done reason "stop" even when upstream done_reason was "length". The live proof's real signal is done_reason: "length", so as-is a real Ollama truncation can still arrive at this new guard as "stop" and fall through the payloadCount > 0 success path. Please map native Ollama length termination to the shared length stop reason and add a native stream regression.
Confidence: 0.9
[P2] Remove the committed proof image — .github/proof/proof-89051-live-ollama.png:1
Repository policy routes PR screenshots and proof media to comments or external artifact storage, but this branch adds a binary proof image under .github/proof. Keeping proof media in the product repo creates permanent artifact churn unrelated to runtime behavior; the existing PR/comment screenshot link is the right place for it.
Confidence: 0.97

Overall correctness: patch is incorrect
Overall confidence: 0.87

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 086274fd7e7a.

Label changes

Label justifications:

P1: The PR targets an urgent embedded-agent silent hang that can stall real long-running sessions after truncation or compaction.
merge-risk: 🚨 compatibility: The diff changes malformed partial assistant turns from a successful partial-output path into an abandoned error path, which can change existing session behavior on upgrade.
rating: 🧂 unranked krab: Overall readiness is 🧂 unranked krab; proof is 🐚 platinum hermit and patch quality is 🧂 unranked krab.
status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Override: The contributor posted a terminal screenshot from a live Ollama truncation and included proof: override; it is useful after-fix evidence, but it does not settle the provider-boundary finding because the screenshot does not show OpenClaw's Ollama stream preserving done_reason: "length".
proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. The contributor posted a terminal screenshot from a live Ollama truncation and included proof: override; it is useful after-fix evidence, but it does not settle the provider-boundary finding because the screenshot does not show OpenClaw's Ollama stream preserving done_reason: "length".

Evidence reviewed

PR surface:

Source +55, Tests +148, Config 0. Total +203 across 4 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	56	1	+55
Tests	1	148	0	+148
Docs	0	0	0	0
Config	1	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	4	204	1	+203

What I checked:

PR diff surface: The head diff adds isTruncatedTerminalAssistantTurn, wires it into resolveIncompleteTurnPayloadText, adds a runner warning, adds regression tests, and adds .github/proof/proof-89051-live-ollama.png. (src/agents/embedded-agent-runner/run/incomplete-turn.ts:116, 20360049eed8)
Provider contract supports length: The shared stream contract already defines StopReason as including length, so preserving provider length termination is a supported cross-provider signal. (packages/llm-core/src/types.ts:255, 086274fd7e7a)
Ollama currently drops length termination: Current buildAssistantMessage ignores done_reason and maps every non-tool Ollama terminal response to stop, which prevents a real done_reason: "length" response from reaching the PR's new stopReason === "length" guard. (extensions/ollama/src/stream.ts:1063, 086274fd7e7a)
Ollama done event also emits stop: The current stream terminal event also emits reason stop unless there are tool calls, so the native stream path needs a regression for length termination rather than only a runner-level synthetic case. (extensions/ollama/src/stream.ts:1451, 086274fd7e7a)
Current runner success guard: Current main suppresses incomplete-turn errors when payloadCount !== 0 unless the terminal state is tool use; the PR's bypass only helps real Ollama once the provider leaves a missing or length stop reason visible to the runner. (src/agents/embedded-agent-runner/run/incomplete-turn.ts:271, 086274fd7e7a)
Proof artifact policy: Root repository policy says PR screenshots and proof assets should be attached to the PR/comment or external artifact storage and not pushed into the product repository. (AGENTS.md:172, 086274fd7e7a)

Likely related people:

steipete: Recent commits on both the Ollama stream and embedded-agent incomplete-turn paths include fix(ollama): suppress disabled reasoning output, broad agent runtime refactors, and cleanup around warning/retry behavior. (role: recent area contributor; confidence: high; commits: 7562afdca37a, 4252f07ff0f1, bb46b79d3c14; files: extensions/ollama/src/stream.ts, src/agents/embedded-agent-runner/run/incomplete-turn.ts, src/agents/embedded-agent-runner/run.ts)
vincentkoc: Recent history on extensions/ollama/src/stream.ts includes Ollama stream processing and tool-call behavior fixes, which are the provider boundary implicated by this PR. (role: recent Ollama contributor; confidence: high; commits: c7b190beec73, 21e69fdd4fa8, dfadc7b704d2; files: extensions/ollama/src/stream.ts)
obviyus: Recent history on the embedded-agent incomplete-turn file includes fix(agents): surface internal abort incomplete turns, which is adjacent to the PR's error surfacing path. (role: recent incomplete-turn contributor; confidence: medium; commits: 1556e3c68ca0; files: src/agents/embedded-agent-runner/run/incomplete-turn.ts, src/agents/embedded-agent-runner/run.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

joelnishanth · 2026-06-01T17:51:51Z

Real Behavior Proof: Live Ollama Truncation Detection

Tested against a real Ollama instance (llama3.2:3b) running locally. The proof script forces a truncated response using num_predict=3 and validates the new detection + error surfacing logic.

Screenshot: Live proof execution (real Ollama API)

What was proven

Real truncation reproduced: Ollama returns done_reason: "length" when num_predict is hit — exactly what happens when context window fills or API rate-limits truncate responses.
Detection works: isTruncatedTerminalAssistantTurn correctly identifies these as truncated (Cases A & B) while not flagging valid responses (Case C — no false positives).
Error surfacing works: resolveIncompleteTurnPayloadText now returns an error message instead of null when payloadCount > 0 but the response is truncated — this is the exact code path that caused the silent hang in [Bug]: Embedded agent session silently hangs after auto-compaction with no error logging or recovery #89051.
No regressions: All 242 existing tests pass.

Unit Tests (242 passing)

 Test Files  2 passed (2)
      Tests  242 passed (242)
   Duration  27.30s

proof: override — This is a defensive detection/logging fix; the "before" state was silent failure (no observable behavior to screenshot). The proof demonstrates the fix activates against real API responses.

— Joel Nishanth · offlyn.AI

Co-authored-by: joelnishanth <[email protected]>

steipete · 2026-06-14T17:59:27Z

Land-ready verification for 50e143ec37924dddc41aaab00d7578ce986ab355:

Addressed the prior review findings: Ollama now preserves native done_reason: "length", native stream regressions cover it, and the committed proof image is removed.
Focused proof: 345 tests passed:
node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.cwd-split.test.ts src/agents/embedded-agent-runner/run/attempt.spawn-workspace.context-injection.test.ts src/agents/embedded-agent-runner/run/attempt.spawn-workspace.context-engine.test.ts extensions/ollama/src/stream.test.ts src/agents/embedded-agent-runner/run.incomplete-turn.test.ts src/agents/embedded-agent-runner/run/attempt-trajectory-status.test.ts src/agents/embedded-agent-subscribe.handlers.lifecycle.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.subscribeembeddedagentsession.test.ts
Broad proof: Testbox tbx_01kv3kmhyx52hb7w9awywk9rjy passed pnpm check:changed for core/core tests/extensions/extension tests.
Live Ollama proof: forced qwen3.5:9b truncation returned done_reason: "length"; OpenClaw preserved stopReason: "length" and surfaced the incomplete-turn response instead of silently completing.
Official OpenAI tool-path proof: Codex OAuth gateway MCP/tool smoke passed with openai/gpt-5.5.
Fresh autoreview: clean, no accepted/actionable findings.
GitHub CI, CodeQL, OpenGrep, dependency guard, workflow sanity, critical-quality, and real-behavior-proof checks are green.

Known proof gap: direct Anthropic live tool calling could not run because available credentials failed billing before prompt/tool execution. No Anthropic or OpenAI transport code changed; shared terminal-output and tool-use behavior has focused regression coverage.

Preserve Ollama length termination and surface incomplete token-limited embedded-agent turns without discarding durable tool output. Fixes openclaw#89051. Co-authored-by: joelnishanth <[email protected]>

joelnishanth mentioned this pull request Jun 1, 2026

[Bug]: Embedded agent session silently hangs after auto-compaction with no error logging or recovery #89051

Closed

openclaw-barnacle Bot added agents Agent runtime and tooling size: S triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 1, 2026

joelnishanth force-pushed the fix/embedded-agent-truncated-response-recovery branch from a392986 to 5721545 Compare June 1, 2026 17:43

openclaw-barnacle Bot added size: M and removed size: S labels Jun 1, 2026

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 1, 2026

clawsweeper Bot added rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. and removed rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. labels Jun 1, 2026

ArthurusDent mentioned this pull request Jun 3, 2026

[Bug]: Agent stalls indefinitely when model emits stopReason="stop" with no toolCall — only thinking block generated #89787

Closed

DaleXiao mentioned this pull request Jun 8, 2026

Bug: DeepSeek V4 Flash incomplete turn (payloads=0, tools=2, replaySafe=no, stopReason=stop) in 2026.5.27/28 #88657

Open

fix(ollama): preserve length-limited responses

50e143e

Co-authored-by: joelnishanth <[email protected]>

steipete force-pushed the fix/embedded-agent-truncated-response-recovery branch from 2036004 to 50e143e Compare June 14, 2026 17:52

openclaw-barnacle Bot added extensions: ollama size: L and removed size: M labels Jun 14, 2026

steipete merged commit 81924cf into openclaw:main Jun 14, 2026
180 of 184 checks passed

github-actions Bot mentioned this pull request Jun 14, 2026

📡 Upstream Digest — 2026-06-14 19:12 UTC curtismercier/openclaw-mods#1079

Open

clawsweeper Bot mentioned this pull request Jun 18, 2026

[Feature]: Agent Runtime: Configurable stopReason="length" catch-and-continue for mode:"run" sessions #63188

Open

ttomiczek mentioned this pull request Jul 5, 2026

Skill and Read tools truncating output at ~600-700 chars in 2026.6.11 #100458

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(agents): detect truncated API responses to prevent silent session hang#89160

fix(agents): detect truncated API responses to prevent silent session hang#89160
steipete merged 1 commit into
openclaw:mainfrom
joelnishanth:fix/embedded-agent-truncated-response-recovery

joelnishanth commented Jun 1, 2026 •

edited by steipete

Loading

Uh oh!

clawsweeper Bot commented Jun 1, 2026 •

edited

Loading

Uh oh!

joelnishanth commented Jun 1, 2026 •

edited

Loading

Uh oh!

steipete commented Jun 14, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

joelnishanth commented Jun 1, 2026 • edited by steipete Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

clawsweeper Bot commented Jun 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

joelnishanth commented Jun 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Real Behavior Proof: Live Ollama Truncation Detection

Screenshot: Live proof execution (real Ollama API)

What was proven

Unit Tests (242 passing)

Uh oh!

steipete commented Jun 14, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

joelnishanth commented Jun 1, 2026 •

edited by steipete

Loading

clawsweeper Bot commented Jun 1, 2026 •

edited

Loading

joelnishanth commented Jun 1, 2026 •

edited

Loading