Just Now, Claude Code Evolved Again, Drafting 'Feedback Reports' for Users

marsbitPubblicato 2026-08-27Pubblicato ultima volta 2026-08-27

Introduzione

Claude Code has introduced a new feature where it can automatically draft feedback reports on behalf of the user. This occurs in scenarios such as when a tool persistently fails, Claude cannot fulfill a request, an error is identified, or the user explicitly asks for feedback. Drafts are saved locally and are not sent to Anthropic until the user reviews and approves them. Users can view, edit, or delete these drafts via a feedback queue interface and control the feature's behavior through settings. The tool is available in local, interactive terminal sessions using the Claude API but is disabled in non-interactive modes, web sessions, certain cloud platforms, and for organizations with specific data retention policies.

Claude Code has updated with another quite interesting little feature.

This time, it can help you draft feedback reports.

When a certain feature malfunctions, when Claude realizes it made a mistake, or when you point out where something went wrong, it will automatically compile the relevant situation into a report.

You can review, edit it before sending, and decide whether to approve submission.

However, you can also disable this feature in /config, or modify its behavior settings.

The official team has also compiled detailed documentation; let's take a look at the specific content.

Claude Code Starts 'Writing Feedback Reports' for Itself

Feedback drafted by Claude is a report about Claude Code written by Claude on your behalf. This feature requires using Claude Code v2.1.238 or later.

Claude Code saves each feedback draft on your local device, at the path: ~/.claude/feedback/drafts/. Nothing is sent to Anthropic until you actively send it.

Specifically, Claude will automatically draft feedback via the SendFeedback tool in the following situations:

  • A tool or command continuously fails;
  • Claude cannot complete a certain request you made;
  • You point out that Claude made a mistake, or Claude itself realizes it made an error;
  • You ask Claude to submit feedback.

Documentation address:

https://code.claude.com/docs/en/tools-reference#sendfeedback-tool-behavior

What You See When Claude Drafts Feedback

When Claude queues a feedback draft, you will see a card above the input box, displaying the title of that draft. You can:

  • Press 1 to view the draft;
  • Press 2 twice in a row to send it as-is directly;
  • Press 0 to ignore this card.

Even if you ignore the card, the draft will remain in the feedback queue.

After you ignore a feedback card, Claude Code will ask if you want to turn off Claude's automatic feedback drafting feature. If you choose not to turn it off twice in a row, it will stop asking afterwards.

By default, a maximum of 3 feedback cards are displayed per session.

After exceeding this limit, or when you set feedbackDrafts to quiet, only the number of feedback drafts currently queued will be shown at the bottom of the input box, and no specific cards will pop up.

Viewing and Editing Feedback Drafts

Run /feedback without any parameters to open the feedback queue.

This will list all unprocessed drafts from all your sessions, including those for which you closed the feedback card or never saw a card in the first place.

After selecting a draft, you can review it and perform the following operations:

Edit the title, category, and specific content;

Set Send transcript to yes or no. If the session record corresponding to when Claude created this draft still exists, this option defaults to yes, meaning the conversation segment will be submitted to Anthropic along with the feedback; choosing no sends only the feedback report itself;

Send the draft, delete the draft, or temporarily leave it in the queue to handle later.

If you want to manually write a feedback report yourself, press w to open the standard feedback window.

The /feedback command with text content, as well as the /bug command, will also directly open this standard feedback window.

Sending Feedback Drafts

When you send a draft, Claude Code submits it in the same way as a /feedback report, following the same data retention policies. After sending is complete, the draft is deleted from your local device.

If you send directly from a feedback card, it will show: ✓ Sent. If you send from the feedback queue, a receipt ID will be shown when the window closes.

Note that sending directly from a feedback card does not include the conversation transcript.

Claude Code saves your working directory information in the local draft to find the corresponding conversation transcript, but does not send this working directory.

For organizations with Zero Data Retention (ZDR) enabled, Claude Code does not provide this tool, and /feedback is similarly unavailable.

Deleting or Retaining Feedback Drafts

When you delete a draft, Claude Code simply removes it from your local device.

If you leave a draft in the feedback queue unprocessed, it will automatically expire after 30 days.

The feedback queue can save a maximum of 10 drafts across all sessions.

When Claude creates the 11th draft, Claude Code will automatically delete the earliest one.

Sessions Where Claude Cannot Automatically Draft Feedback

Claude Code only provides this feature in the following scenarios:

Interactive terminal sessions running on the user's own computer and directly using the Claude API, not through a cloud service provider.

The tool is not provided in the following scenarios:

  • Non-interactive -p run modes, and Agent SDK sessions, as these scenarios lack an interface for reviewing the feedback queue;
  • Cloud sessions, such as Claude Code on the web, because it cannot write feedback drafts to your local device;

Sessions run through the following platforms:

  • Amazon Bedrock
  • Claude Platform on AWS
  • Google Cloud Agent Platform
  • Microsoft Foundry

Sessions with the following environment variables or related configurations set:

  • CLAUDE_CODE_SEND_FEEDBACK=0
  • DISABLE_FEEDBACK_COMMAND=1
  • Setting CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC to any non-empty value
  • Feature-flag fetching is turned off;
  • Organizations that have turned off product feedback functionality;
  • Organizations with Zero Data Retention (ZDR) enabled.

This article is from the WeChat public account "Machine Heart"

Domande pertinenti

QWhat is the main new feature introduced in the latest Claude Code update according to the article?

AThe main new feature is that Claude Code can now automatically draft feedback reports for users when issues occur, such as tool failures, errors made by Claude, or user-reported problems.

QWhere are the feedback drafts saved locally on a user's device, and when is the content transmitted to Anthropic?

AThe feedback drafts are saved locally at ~/.claude/feedback/drafts/. The content is not transmitted to Anthropic until the user actively sends the report.

QHow can a user open the feedback queue to review and manage pending drafts in Claude Code?

AA user can open the feedback queue by running the /feedback command without any parameters.

QUnder what conditions will Claude automatically draft a feedback report using the SendFeedback tool?

AClaude will automatically draft feedback when: a tool or command repeatedly fails; Claude cannot complete a user's request; the user points out an error or Claude realizes it made a mistake; or the user explicitly asks Claude to submit feedback.

QIn which types of sessions is the automatic feedback drafting feature NOT available in Claude Code?

AThe feature is not available in: non-interactive -p run modes and Agent SDK sessions; cloud-based sessions like Claude Code on the web; sessions run through platforms like Amazon Bedrock, Claude Platform on AWS, Google Cloud Agent Platform, or Microsoft Foundry; and sessions with specific environment variables or configurations that disable feedback or non-essential traffic, or in organizations that have disabled product feedback or enabled Zero Data Retention.

Letture associate

The Analysts Who Accurately Predicted the Silver Crash: Bitcoin Has Peaked in the Short Term, May Experience an 'Ultimate Washout' Dropping to $40,000 Between September and October

CMT analyst AG Thorson analyzes recent market movements driven by the US Treasury's bond buyback announcement. The move pushed the US Dollar below its 200-day moving average, fueling a strong rally in precious metals (gold, silver, platinum), which are seen as having confirmed major mid-year lows. Miner stocks (GDX) have surged over 40% from their bottom and are expected to lead the sector, potentially hitting new all-time highs before the metals themselves. Bitcoin also saw a sharp spike due to the Treasury news and a pro-crypto White House event, triggering a record $3 billion in short liquidations. However, Thorson maintains a cautious outlook for BTC. While admitting his confidence is wavering due to Bitcoin's reclaim of the 200-day MA, he still anticipates a potential final "washout" decline in September, possibly testing the $40,000 area (near the Bitcoin Equilibrium Price of $39,880) by October. He argues such a move is needed to shake out remaining bullish sentiment. If this drop does not materialize by September, his timing for a cycle bottom may be off by roughly three months. In summary, the analyst is bullish on precious metals and miners post their mid-year lows but remains watchful for one last significant dip in Bitcoin before a potential sustained upward move.

marsbit3 min fa

The Analysts Who Accurately Predicted the Silver Crash: Bitcoin Has Peaked in the Short Term, May Experience an 'Ultimate Washout' Dropping to $40,000 Between September and October

marsbit3 min fa

Re-Evaluating $HTX as the Bull Market Returns: The Token Connecting Global Assets to the Crypto Space

$HTX’s role is undergoing a fundamental transformation. As the governance token of HTX DAO and the sole designated partner token of the HTX exchange, $HTX has, to some extent, functioned as a platform token. Historically, its valuation has been anchored to crypto spot and futures trading volumes. Moving forward, it should be re-evaluated as a token that connects global assets to the crypto space—a stake in the very gateway through which global capital enters the crypto ecosystem. To ground this narrative in concrete analysis, this paper complements the thesis with a full quantitative projection. Three dimensions are assessed: (i) the aggregate scale of global traditional finance, (ii) the current size of the crypto market, and (iii) HTX’s market share within it. Assuming even a limited inflow of global capital, together with the TradFi sector’s current growth momentum, the market capitalization of $HTX is projected over a five-year horizon.

HTX News6 min fa

Re-Evaluating $HTX as the Bull Market Returns: The Token Connecting Global Assets to the Crypto Space

HTX News6 min fa

LBank launches physical Visa crypto card with up to 10% cashback for real-world Web3 payments

LBank, a global cryptocurrency exchange, has launched a physical Visa card, enabling users to spend their crypto holdings at Visa merchants and ATMs worldwide. The card allows direct payments from the user's LBank spot account, with digital assets converted to local currency in real-time. It features zero monthly, top-up, and foreign-exchange fees, a 0.8% spending fee, and support for Apple Pay and Google Pay. Key benefits include up to 10% cashback on transactions, referral commissions of up to 30%, and monthly spending limits up to 1,000,000 USDT for higher-tier users. Idle USDT can also earn up to 10% APR through flexible savings, with promotional boosts. Complementing the card is LBank Pay, a QR-based payment solution supporting multiple digital assets and integrated with local payment networks in regions like Southeast Asia and Latin America. According to LBank's Eric He, these products aim to reduce friction and integrate digital assets into everyday financial habits and existing payment infrastructure.

cointelegraph8 min fa

LBank launches physical Visa crypto card with up to 10% cashback for real-world Web3 payments

cointelegraph8 min fa

As the Bull Market Returns, Reassessing $HTX: The Equity Token for Global Assets Entering the Crypto World

The role of $HTX is undergoing a fundamental change. As the governance token of HTX DAO and the sole designated cooperative token of Huobi HTX, it partially functions as a platform token. In the past, its valuation was anchored to the trading volume of crypto spot and futures markets. In the future, it should be reinterpreted as the 'Equity Token for Global Assets Entering the Crypto World'—when global capital passes through the gateway to the Crypto world, holding $HTX means owning a part of that gateway. To substantiate this judgment, this article will supplement a comprehensive quantitative analysis beyond the narrative: assessing the size of the global traditional financial system, the current size of crypto, Huobi HTX's market share, and where the market cap of $HTX should stand five years from now, considering even a small inflow of global capital combined with the incremental growth rate of the TradFi sector this year.

9 min fa

As the Bull Market Returns, Reassessing $HTX: The Equity Token for Global Assets Entering the Crypto World

9 min fa

Behind the Trillion-Dollar Capital Gamble: Time is Becoming the Counterparty to AI

Amidst unprecedented capital investment in AI, a trillion-dollar "gamble" is unfolding where time itself is becoming the opposing force. Recent events illustrate the volatility and profound uncertainty underlying this rush. In July 2026, hedge fund Situational Awareness, founded by Leopold Aschenbrenner and heavily leveraged on AI hardware stocks like Sandisk, lost $35 billion in a month as a market selloff triggered massive declines, highlighting the irrational human foundations of even AI-augmented markets. Simultaneously, the regulatory landscape is shifting dramatically. Social media addiction lawsuits in the US have exploded, with major platforms like Meta, Snap, TikTok, and Google now facing billions in liabilities. This signals a critical change: the "algorithm is neutral" defense is crumbling for AI, introducing massive legal and governance uncertainties that threaten AI's business models. Financially, the sector is fueled by unsustainable capital intensity. Google reported its first-ever negative free cash flow (-$5.9B) in Q2 2026, while its AI capex is projected to hit $200B. Industry-wide, debt issuance for AI infrastructure could reach $1.5 trillion. Companies like OpenAI and Anthropic project profitability only by 2030, betting on future revenues in the hundreds of billions. This mirrors a national dilemma: the U.S. faces a looming debt crisis, with interest costs projected to exceed $1 trillion annually, creating pressure to secure technological supremacy through AI. The core paradox is that this historic capital infusion aims to buy time for AI to mature and dominate. However, if the anticipated technological leap or market scale fails to materialize within the narrow window before profitability deadlines or a debt crisis, the simultaneous collapse of both corporate and national financial bets could be catastrophic. The race is not just for technological advantage, but against the clock.

marsbit13 min fa

Behind the Trillion-Dollar Capital Gamble: Time is Becoming the Counterparty to AI

marsbit13 min fa

Trading

Spot
活动图片