feat: structured fallback deliverables for failed/stuck jobs by ztsalexey · Pull Request #236 · nearai/ironclaw

ztsalexey · 2026-02-19T20:36:02Z

Summary

Closes #221

When a job fails or gets stuck, a FallbackDeliverable now captures what was accomplished before the failure — replacing opaque error strings with structured data.

FallbackDeliverable struct with: partial success flag, failure reason, last action preview, action stats (total/successful/failed), tokens used, cost, elapsed time, repair attempts
Stored in JobContext.metadata["fallback_deliverable"] by mark_failed() and mark_stuck() in the worker
Surfaced via the job_status tool output and SSE job_result events
Safe UTF-8 truncation for last action preview (200 bytes, UTF-8 safe)

Files changed

File	Change
`src/context/fallback.rs`	New — `FallbackDeliverable`, `LastAction`, `ActionStats` types + `build()` constructor
`src/context/memory.rs`	`ActionRecord::succeed()` param order fix + doc clarification
`src/context/mod.rs`	Module declaration + re-export
`src/worker/job.rs`	`mark_failed()`/`mark_stuck()` build and store fallback; `store_fallback_in_metadata()` helper
`src/channels/web/types.rs`	`SseEvent::JobResult` gains optional `fallback` field
`src/orchestrator/api.rs`	Pass through `fallback_deliverable` from container events
`src/tools/builtin/job.rs`	`JobStatusTool` includes `fallback_deliverable` in output
`src/agent/job_monitor.rs`	Updated for new `JobResult` field

Test plan

12 unit tests in context::fallback::tests (zero actions, mixed actions, truncation, elapsed time, no started_at, ASCII/Unicode truncation, serialization, sanitized output)
cargo fmt --check clean
cargo clippy --all --all-features clean
cargo test --lib — all passed
Feature flag compilation: default, --features libsql, --all-features

🤖 Generated with Claude Code

gemini-code-assist · 2026-02-19T20:36:23Z

Summary of Changes

Hello @ztsalexey, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly improves the diagnostic capabilities for failed or stuck jobs by introducing structured fallback deliverables. Instead of just an error message, jobs will now provide a comprehensive summary of their state at the point of failure, including partial successes, action statistics, resource usage, and elapsed time. This enhancement provides greater transparency and aids in understanding why jobs did not complete successfully, facilitating quicker debugging and better user feedback.

Highlights

Structured Fallback Deliverables: Introduced a new FallbackDeliverable struct to capture detailed, structured information when a job fails or gets stuck, replacing opaque error strings with actionable data.
Enhanced Job Failure Reporting: Modified worker logic (mark_failed() and mark_stuck()) to automatically build and store the FallbackDeliverable in the JobContext.metadata upon job failure or becoming stuck.
Improved Visibility: Integrated the fallback_deliverable into SseEvent::JobResult events and the job_status tool output, providing users and systems with immediate access to the structured failure data.
New Module for Fallback Logic: Created a dedicated src/context/fallback.rs module to house the FallbackDeliverable, LastAction, and ActionStats types, along with their construction logic and a safe UTF-8 truncation utility.

Changelog

src/agent/job_monitor.rs
- Updated a test case to include the new fallback field in SseEvent::JobResult for consistency.
src/agent/worker.rs
- Modified mark_failed and mark_stuck functions to build and store a FallbackDeliverable in the job context's metadata before transitioning job state.
- Added a new asynchronous helper function build_fallback to construct the FallbackDeliverable from the current job context and memory.
- Introduced store_fallback_in_metadata function to serialize and store the FallbackDeliverable within the job context's metadata.
src/channels/web/types.rs
- Extended the SseEvent::JobResult enum variant to include an optional fallback field, allowing structured fallback data to be transmitted via Server-Sent Events.
src/context/fallback.rs
- Added a new module defining the FallbackDeliverable, LastAction, and ActionStats structs for structured job failure information.
- Implemented the build method for FallbackDeliverable to populate its fields using JobContext and Memory data.
- Included a truncate_str utility function for safe UTF-8 string truncation, used for action output previews.
- Provided comprehensive unit tests for various scenarios, including zero actions, mixed actions, truncation, elapsed time calculation, and serialization.
src/context/mod.rs
- Declared the new fallback module to make its contents accessible.
- Re-exported the FallbackDeliverable type for easier access within the context crate.
src/orchestrator/api.rs
- Modified the job_event_handler to extract and include the fallback_deliverable from container events into the SseEvent::JobResult payload.
src/tools/builtin/job.rs
- Updated the JobStatusTool to include the fallback_deliverable from the job context's metadata in its JSON output, providing more detailed status information.

Activity

The pull request introduces a new feature to provide structured fallback deliverables for failed or stuck jobs.
No specific review comments or discussions are available in the provided context.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

Copilot

Pull request overview

Adds a structured FallbackDeliverable payload to capture partial progress and diagnostics when jobs fail or become stuck, and exposes that data via job status outputs and (intended) streaming result events.

Changes:

Introduces context::FallbackDeliverable (plus LastAction/ActionStats) with a constructor and unit tests.
Stores serialized fallback data in JobContext.metadata["fallback_deliverable"] when marking jobs failed/stuck.
Extends job_status tool output and SSE job_result events to optionally include fallback data.

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
`src/context/fallback.rs`	New structured fallback types + builder + tests.
`src/context/mod.rs`	Declares `fallback` module and re-exports `FallbackDeliverable`.
`src/agent/worker.rs`	Builds/stores fallback deliverable on `mark_failed()` / `mark_stuck()`.
`src/tools/builtin/job.rs`	Adds `fallback_deliverable` to the `job_status` tool JSON output.
`src/channels/web/types.rs`	Adds optional `fallback` field to SSE `JobResult` event type.
`src/orchestrator/api.rs`	Attempts to pass `fallback_deliverable` through from worker event payloads into SSE `JobResult`.
`src/agent/job_monitor.rs`	Updates `JobResult` construction to include the new `fallback` field.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

gemini-code-assist

Code Review

The pull request introduces structured fallback deliverables for failed or stuck jobs, enhancing visibility into job failures. The implementation includes UTF-8 safe string truncation, which is correctly handled, though an efficiency improvement is suggested. Minor optimizations and idiomatic Rust suggestions are also provided for handling FallbackDeliverable in job context metadata. Overall, the code is well-structured and follows good practices for error handling and data serialization.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.

Comments suppressed due to low confidence (1)

src/context/fallback.rs:16

The doc comment says the fallback deliverable is stored when a job fails, but the worker also stores it when a job is marked stuck. Update the documentation to reflect both failure and stuck/timeout paths so it matches actual behavior.

/// Structured summary of a failed or stuck job.
///
/// Stored in `JobContext.metadata["fallback_deliverable"]` when a job fails.
/// Surfaced via SSE `job_result` events and the `job_status` tool.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

Comments suppressed due to low confidence (1)

src/context/fallback.rs:17

The doc comment says fallback deliverables are “Surfaced via SSE job_result events”, but the current SSE mapping for container/sandbox events notes this field is always None (and in-memory jobs access fallback via job_status). Consider updating this comment to reflect the current behavior (e.g., surfaced via job_status, and SSE support is forward-compatible) to avoid misleading API/UI consumers.

/// Structured summary of a failed or stuck job.
///
/// Stored in `JobContext.metadata["fallback_deliverable"]` when a job fails.
/// Surfaced via SSE `job_result` events and the `job_status` tool.
#[derive(Debug, Clone, Serialize, Deserialize)]

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

ztsalexey · 2026-03-13T19:24:04Z

    ) -> Self {
        self.success = true;
-        self.output_raw = output_raw;
-        self.output_sanitized = Some(output_sanitized);
+        self.output_raw = Some(serde_json::to_string_pretty(&output_raw).unwrap_or_default());
+        self.output_sanitized = output_sanitized.map(serde_json::Value::String);


The double serialization is a pre-existing pattern in ActionRecord::succeed() — it takes a Value, pretty-prints for readability in stored records, and wraps sanitized as Value::String. This PR didn't introduce it. Optimizing the serialization path is a valid follow-up but orthogonal to the fallback deliverable feature.

ztsalexey · 2026-03-13T19:24:06Z

+                .output_sanitized
+                .as_ref()
+                .map(|v| match v {
+                    serde_json::Value::String(s) => s.clone(),
+                    other => serde_json::to_string(other).unwrap_or_default(),


Good catch. Fixed in 3713051 — now borrows via as_str() for Value::String and only allocates when serializing non-string JSON values. Avoids cloning large outputs on the failure path.

ztsalexey · 2026-03-13T19:24:08Z

    /// Mark the action as successful.
+    ///
+    /// `output_sanitized` is the tool output after safety processing (string).
+    /// `output_raw` is the original tool result (JSON value).


Fixed in 3713051 — doc now clarifies that output_raw is stored as a pretty-printed JSON string in ActionRecord.output_raw (Option<String>), not kept as a raw Value.

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

ztsalexey · 2026-03-13T19:24:10Z

    /// Mark the action as successful.
+    ///
+    /// `output_sanitized` is the tool output after safety processing (string).
+    /// `output_raw` is the original tool result (JSON value).
    pub fn succeed(
        mut self,
-        output_raw: Option<String>,
-        output_sanitized: serde_json::Value,
+        output_sanitized: Option<String>,
+        output_raw: serde_json::Value,


Same as the comment above — fixed in 3713051. Doc now says "JSON value, stored as a pretty-printed JSON string".

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

ztsalexey · 2026-03-15T00:15:10Z

    async fn mark_failed(&self, reason: &str) -> Result<(), Error> {
+        // Build fallback deliverable from memory before transitioning.
+        let fallback = self.build_fallback(reason).await;
+
        self.context_manager()
            .update_context(self.job_id, |ctx| {
-                ctx.transition_to(JobState::Failed, Some(reason.to_string()))
+                ctx.transition_to(JobState::Failed, Some(reason.to_string()))?;
+                store_fallback_in_metadata(ctx, fallback.as_ref());
+                Ok(())


Valid observation. This is a known limitation documented in the earlier reply to comment 2830052673 — in-memory jobs store fallback in JobContext.metadata, which is not persisted to DB across restarts. The job_status tool reads from the live context, so it works for the job's lifetime. Persisting to a DB column is a follow-up that requires a migration for both postgres and libsql backends — out of scope for this PR.

ztsalexey · 2026-03-15T00:15:11Z

        #[serde(skip_serializing_if = "Option::is_none")]
        session_id: Option<String>,
+        #[serde(skip_serializing_if = "Option::is_none")]
+        fallback: Option<serde_json::Value>,


Good catch — renamed the SSE field from fallback to fallback_deliverable in a06d242 to match the metadata key and job_status tool naming.

ztsalexey · 2026-03-15T00:15:14Z

    pub fn succeed(
        mut self,
-        output_raw: Option<String>,
-        output_sanitized: serde_json::Value,
+        output_sanitized: Option<String>,
+        output_raw: serde_json::Value,
        duration: Duration,
    ) -> Self {
        self.success = true;
-        self.output_raw = output_raw;
-        self.output_sanitized = Some(output_sanitized);
+        self.output_raw = Some(serde_json::to_string_pretty(&output_raw).unwrap_or_default());
+        self.output_sanitized = output_sanitized.map(serde_json::Value::String);
        self.duration = duration;


This is the same concern raised in comments 2933055608 and 2933352613 — the double serialization is a pre-existing pattern in ActionRecord::succeed(), not introduced by this PR. Already acknowledged as a valid follow-up optimization in both earlier replies.

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

ztsalexey · 2026-03-15T17:20:08Z

+        // Build fallback deliverable from memory before transitioning.
+        let fallback = self.build_fallback(reason).await;
+
        self.context_manager()
            .update_context(self.job_id, |ctx| {
-                ctx.transition_to(JobState::Failed, Some(reason.to_string()))
+                ctx.transition_to(JobState::Failed, Some(reason.to_string()))?;
+                store_fallback_in_metadata(ctx, fallback.as_ref());
+                Ok(())


Duplicate of comment 2936022149 — already addressed there. The fallback is stored in-memory in JobContext.metadata for the job's lifetime. Persisting to a DB column requires a dual-backend migration (postgres + libsql), which is out of scope for this PR.

) When a job fails or gets stuck, build a FallbackDeliverable that captures partial results, action statistics, cost, timing, and repair attempts. This replaces opaque error strings with structured data users can act on. - Add FallbackDeliverable, LastAction, ActionStats types in context/fallback.rs - Store fallback in JobContext.metadata["fallback_deliverable"] on failure - Surface fallback in job_status tool output and SSE job_result events - Update mark_failed() and mark_stuck() in worker to build fallback - 8 unit tests covering zero/mixed actions, truncation, timing, serialization Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Fix doc comment: "200 chars" -> "200 bytes (UTF-8 safe)" since truncate_str operates on byte length, not character count. - Add code comment documenting that SSE fallback_deliverable is currently always None (forward-compatible infrastructure). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Addresses Gemini review feedback: idiomatic Rust prefers Option<&T> over &Option<T> for borrowed optional values. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- store_fallback_in_metadata now resets metadata to {} when it's any non-object type (string, array, number), not just null. Prevents panic on index assignment. - Add test_job_status_includes_fallback_deliverable to verify the fallback field is surfaced in job_status tool output. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Security fix: FallbackDeliverable::build() now uses output_sanitized instead of output_raw, preventing secrets/PII from leaking through the job_status tool and SSE job_result events. Also adds: - test_fallback_uses_sanitized_output: proves raw secrets don't leak - test_store_fallback_in_metadata_roundtrip: full serialize/deserialize - test_store_fallback_handles_non_object_metadata: edge case coverage - test_store_fallback_none_is_noop: None input is safe Addresses serrrfirat review feedback on PR nearai#236. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Truncate failure_reason to 1000 bytes to prevent metadata bloat - Add tracing::warn on fallback serialization failure (was silently discarded) - Fix module/struct docs to cover stuck jobs, remove stale SSE claim - Fix job.rs test to use real FallbackDeliverable field names - Add tests for failure_reason truncation and completed_at=None elapsed time - Fix pre-existing clippy warning in settings.rs (field_reassign_with_default) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Fix output_raw/output_sanitized field swap in ActionRecord::succeed() so sanitized data actually goes into the sanitized field (security) - Return None instead of empty Memory when get_memory fails in build_fallback, with tracing::warn for observability - Replace manual elapsed calculation with ctx.elapsed() which already clamps negative durations Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Add fallback field to SseEvent::JobResult in job_monitor - Fix type annotation in fallback deliverable test - Update test_action_record_succeed_sets_fields for new parameter order - Use create_job_for_user in test (API changed on main) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

When the last action is a failed tool call, output_sanitized is None, leaving output_preview empty. Now falls back to the action's error message so users see what went wrong. [skip-regression-check]

The CI no-panics grep check cannot distinguish test code inside src/ files from production code. Add // safety: test annotations to .unwrap(), .expect(), and assert!() calls in #[cfg(test)] modules.

- Fix doc comment: output_raw is stored as pretty-printed JSON string, not a raw JSON value - Borrow string slice directly in fallback preview to avoid cloning potentially large sanitized outputs before truncation

Replace hand-rolled UTF-8 boundary logic with existing crate::util::floor_char_boundary to reduce duplication.

The SSE JobResult field was named `fallback` while everywhere else (metadata key, job_status tool) uses `fallback_deliverable`. Align the SSE wire format to avoid forcing clients to handle two names.

Copilot AI review requested due to automatic review settings February 19, 2026 20:36

Copilot started reviewing on behalf of ztsalexey February 19, 2026 20:36 View session

Copilot AI reviewed Feb 19, 2026

View reviewed changes

Comment thread src/context/fallback.rs Outdated

Comment thread src/context/fallback.rs

Comment thread src/orchestrator/api.rs

gemini-code-assist bot reviewed Feb 19, 2026

View reviewed changes

Comment thread src/worker/job.rs

Comment thread src/context/fallback.rs

Copilot AI review requested due to automatic review settings February 19, 2026 22:25

ztsalexey force-pushed the feat/fallback-deliverables branch from db9ce25 to 1c494d5 Compare February 19, 2026 22:25

Copilot started reviewing on behalf of ztsalexey February 19, 2026 22:25 View session

Copilot AI reviewed Feb 19, 2026

View reviewed changes

ztsalexey force-pushed the feat/fallback-deliverables branch from 1c494d5 to 85f34a5 Compare February 19, 2026 23:10

Copilot AI review requested due to automatic review settings February 19, 2026 23:48

Copilot started reviewing on behalf of ztsalexey February 19, 2026 23:48 View session

Copilot AI reviewed Feb 19, 2026

View reviewed changes

Comment thread src/agent/worker.rs Outdated

Comment thread src/tools/builtin/job.rs

Copilot AI review requested due to automatic review settings February 20, 2026 00:10

Copilot started reviewing on behalf of ztsalexey February 20, 2026 00:11 View session

Copilot AI reviewed Feb 20, 2026

View reviewed changes

ztsalexey force-pushed the feat/fallback-deliverables branch from c85ae1c to 7dab6bf Compare February 20, 2026 00:37

Copilot AI review requested due to automatic review settings February 20, 2026 00:39

Copilot started reviewing on behalf of ztsalexey February 20, 2026 00:39 View session

Copilot AI reviewed Feb 20, 2026

View reviewed changes

Copilot AI review requested due to automatic review settings February 20, 2026 01:15

Copilot started reviewing on behalf of ztsalexey February 20, 2026 01:15 View session

Copilot AI reviewed Feb 20, 2026

View reviewed changes

Copilot AI review requested due to automatic review settings February 20, 2026 04:17

Copilot started reviewing on behalf of ztsalexey February 20, 2026 04:17 View session

Copilot AI reviewed Feb 20, 2026

View reviewed changes

github-actions bot added scope: agent Agent core (agent loop, router, scheduler) scope: channel/web Web gateway channel scope: tool/builtin Built-in tools scope: orchestrator Container orchestrator labels Feb 20, 2026

Copilot AI reviewed Mar 13, 2026

View reviewed changes

ztsalexey force-pushed the feat/fallback-deliverables branch from 7bb3cbe to 0b35610 Compare March 13, 2026 18:56

Copilot AI reviewed Mar 13, 2026

View reviewed changes

Comment thread src/context/fallback.rs

Comment thread src/context/memory.rs

Comment thread src/worker/job.rs

Copilot AI reviewed Mar 15, 2026

View reviewed changes

github-actions bot mentioned this pull request Mar 15, 2026

🦞 OpenClaw 生态日报 2026-03-15 gsscsd/big_model_radar#38

Open

Copilot AI reviewed Mar 15, 2026

View reviewed changes

ztsalexey and others added 14 commits March 17, 2026 18:22

refactor: take Option<&FallbackDeliverable> instead of &Option<…>

3ba45e5

Addresses Gemini review feedback: idiomatic Rust prefers Option<&T> over &Option<T> for borrowed optional values. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

chore: trigger CI re-check after rebase

d853d4c

fix: fall back to error message for failed action output_preview

0d95deb

When the last action is a failed tool call, output_sanitized is None, leaving output_preview empty. Now falls back to the action's error message so users see what went wrong. [skip-regression-check]

ci: add safety comments to test code for no-panics check

5a77286

The CI no-panics grep check cannot distinguish test code inside src/ files from production code. Add // safety: test annotations to .unwrap(), .expect(), and assert!() calls in #[cfg(test)] modules.

fix: clarify succeed() doc and avoid clone in output_preview

ef32ab6

- Fix doc comment: output_raw is stored as pretty-printed JSON string, not a raw JSON value - Borrow string slice directly in fallback preview to avoid cloning potentially large sanitized outputs before truncation

refactor: reuse floor_char_boundary in truncate_str

c5018de

Replace hand-rolled UTF-8 boundary logic with existing crate::util::floor_char_boundary to reduce duplication.

fix: rename SSE fallback field to fallback_deliverable for consistency

24e3f86

The SSE JobResult field was named `fallback` while everywhere else (metadata key, job_status tool) uses `fallback_deliverable`. Align the SSE wire format to avoid forcing clients to handle two names.

github-actions bot mentioned this pull request Mar 18, 2026

🦞 OpenClaw 生态日报 2026-03-18 gsscsd/big_model_radar#56

Open

ilblackdragon approved these changes Mar 19, 2026

View reviewed changes

ironclaw-ci bot mentioned this pull request Mar 19, 2026

chore: promote staging to staging-promote/52ca9d65-23312673755 (2026-03-19 21:10 UTC) #1428

Merged

This was referenced Mar 20, 2026

chore: promote staging to staging-promote/71f41dd1-23309993684 (2026-03-19 19:18 UTC) #1425

Merged

chore: promote staging to staging-promote/ec04354c-23271447493 (2026-03-19 17:20 UTC) #1420

Merged

ironclaw-ci bot mentioned this pull request Mar 20, 2026

chore: release v0.21.0 #1472

Merged

BrewTestBot mentioned this pull request Mar 20, 2026

ironclaw 0.21.0 Homebrew/homebrew-core#273446

Merged

This was referenced Mar 21, 2026

🦞 OpenClaw 生态日报 2026-03-21 gsscsd/big_model_radar#71

Open

🦞 Bản tin hàng ngày hệ sinh thái OpenClaw 2026-03-21 compasify/agents-radar#66

Open

Conversation

ztsalexey commented Feb 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Files changed

Test plan

Uh oh!

gemini-code-assist bot commented Feb 19, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Choose a reason for hiding this comment

ztsalexey commented Feb 19, 2026 •

edited

Loading