Claude Code repeatedly rediscovers solved problems

Preflight Checklist

• [x] I have searched existing requests and this feature hasn't been requested yet
• [x] This is a single feature request (not multiple features)

Problem Statement

Claude Code currently has no mechanism to feed implicit session knowledge back into the model. Every conversation starts from zero — including known pitfalls, correct solution paths, and better tool choices that were discovered the hard way in previous sessions.

There is no structured channel for implicit session knowledge to flow back to the model. Bug reports and GitHub issues require deliberate user effort. The vast majority of inefficient paths are never reported — they just silently repeat.

This is also worth naming directly: the current per-token pricing model creates a weak structural disincentive to fix this. Shorter, more efficient sessions cost less. Anthropic's long-term interest (user satisfaction, retention, trust) clearly points the other way — but the incentive tension is real and worth acknowledging when designing a solution.

Proposed Solution

Opt-in "Lessons Learned" Feedback

Add an opt-in mechanism — never on by default — that allows users to submit anonymized session efficiency data:

Session: jira-mcp-setup
Actual path: 31 tool calls, 3 restarts, 45 minutes
Optimal path: 5 tool calls, 0 restarts, 3 minutes
Root cause: Model chose community npm package over official vendor MCP server
Correct first step: claude mcp add --transport http atlassian https://mcp.atlassian.com/v1/mcp

This data could feed into:

• Fine-tuning / RLHF pipelines (with consent)
• A curated internal knowledge base for known tool/integration patterns
• Proactive documentation improvements

Why This Matters Beyond User Experience

• Environmental impact: Unnecessary tool calls burn real electricity at scale
• Cost efficiency: Compute saved on redundant paths can fund better model capabilities
• Trust: Users who watch Claude go in circles repeatedly lose confidence — not in the task, but in the tool

What This Is NOT
This is not a request to collect conversation content. It is a request for a structured, opt-in, anonymized signal: "This session took X steps, the optimal path was Y, here is why."

Alternative Solutions

_No response_

Priority

High - Significant impact on productivity

Feature Category

Performance and speed

Use Case Example

Today I spent approximately 30 tool calls and multiple reload cycles trying to connect Jira via MCP. The correct solution — Atlassian's official remote MCP server at https://mcp.atlassian.com/v1/mcp — was available from the start, but Claude chose community npm packages instead and went down a dead end.

With the right knowledge available upfront, this would have taken ~5 tool calls. That is a 6x efficiency gap — in compute, electricity, and user time.

Current path (dead-end): ████████████████████████████████ 30 tool calls
Optimal path (with memory): █████ 5 tool calls

Waste per session: 83% of tokens were avoidable

Additional Context

The following is a conservative order-of-magnitude simulation based on the example above.

Assumptions:

| Parameter | Value |
|---|---|
| Claude Code active users | 1,000,000 |
| Sessions per user per day | 3 |
| Sessions with avoidable dead-end paths | 15% |
| Tokens wasted per dead-end session | ~50,000 |
| Energy per 1,000 inference tokens | ~0.003 kWh |

Estimated impact at scale:

| Metric | Current | With feedback loop | Reduction |
|---|---|---|---|
| Wasteful sessions/day | 450,000 | ~90,000 | −80% |
| Tokens wasted/day | ~22.5 billion | ~4.5 billion | −80% |
| Energy wasted/year | ~24,600 MWh | ~4,900 MWh | ~19,700 MWh saved |
| CO₂ equivalent/year | ~9,850 tonnes | ~1,970 tonnes | −7,880 tonnes CO₂ |
| Compute cost saved/year | — | — | ~$985,000 |
| User time saved/day | — | ~75,000 hours | 75,000 hours/day |

Even at a conservative 5% dead-end session rate and 50% resolution through the feedback loop, savings remain in the thousands of MWh and millions of user-hours annually.

The environmental and economic case is strong. The 19,700 MWh saved annually is equivalent to the yearly electricity consumption of ~1,800 average EU households — purely from eliminating known, repeatable inefficiencies.