Sudden 5-hour session window squeeze starting Apr 29, 2026 evening

Open 💬 37 comments Opened Apr 30, 2026 by DEF29

Summary

Since the evening of April 29, 2026, the 5-hour session window depletes 5–10× faster than before for the same kind of work. A typical light editing session (a few scp, Read, small patches via Edit) burns ~20–25% of the session window in well under an hour. Sonnet sub-agents launched via Agent repeatedly hit "You've hit your limit" within 15–30 minutes of work — they used to run for hours.

The frustrating part is that the weekly quota is barely touchedW shows ~59% remaining with 23+ hours of headroom — yet the session-window cap blocks me from using that headroom. I have plenty of weekly budget, but the 5-hour window won't let me spend it.

Context

I'm aware of the April 23, 2026 post-mortem about restoring high reasoning effort and reverting the verbosity prompt. Those changes do explain some token-cost increase per turn. They do not explain the disproportionate ratio between session-window depletion and weekly-quota consumption that started on April 29 specifically — i.e. several days after the April 23 fix.

Reproduction signals

  • S (5-hour session window) hits 20%+ within 30–60 minutes of light tool use.
  • W (weekly) shows large remainder + many real-time hours of headroom.
  • Multiple parallel Agent (Sonnet sub-agent) launches all hit limit within minutes — burning quota seemingly faster than total work would suggest.
  • Started: 2026-04-29 evening (Europe/Kaliningrad timezone). Confirmed by independent users referencing the same date.

Ask

  1. Please confirm whether anything changed in the session-window accounting on April 29 (UTC evening).
  2. Either widen the session window proportionally to the new per-turn cost, or document the new ratio so users can plan around it.

Impact

Right now Claude Code, for which I subscribe primarily on Max tier, is significantly less usable than it was a week ago — not because of model quality (which is good), but because the cadence of forced waits has gone from "rare and predictable" to "every hour or so, no matter how lightly I work."

I do want this to keep working — that's why I'm reporting.

---

Mitigations I've applied so far:

  • Lowered effortLevel from high to medium in ~/.claude/settings.json (~1.5× longer windows but at quality cost).
  • Stopped launching Sonnet sub-agents in parallel (they cannibalize each other's quota).
  • Splitting big tasks into ~30-minute Sonnet chunks instead of 90.

These help, but they're workarounds, not solutions.

View original on GitHub ↗

37 Comments

WhitleyStriber · 2 months ago

+1. Few bug reports are opening now that see the same issue. I've also experienced this as well.

alessandroavenali · 2 months ago

Looks like many people are reporting this kind of issue today. The shrinking is simply too much and makes the Max plan unusable. +1

AizenvoltPrime · 2 months ago

I leave this here, this happened yesterday 29/04/2026 :

<img width="1368" height="754" alt="Image" src="https://github.com/user-attachments/assets/aaa03efe-b162-481a-b079-504570cbffe7" />

x20 plan the 5 hour limit reached in 20 minutes with one session running that had 5 subagents running in parallel. This has never happened before. It was outside of peak hours.

github-actions[bot] · 2 months ago

Found 3 possible duplicate issues:

  1. https://github.com/anthropics/claude-code/issues/54726
  2. https://github.com/anthropics/claude-code/issues/54714
  3. https://github.com/anthropics/claude-code/issues/54672

This issue will be automatically closed as a duplicate in 3 days.

  • If your issue is a duplicate, please close it and 👍 the existing issue instead
  • To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

nullcrimson · 2 months ago

+1. totally unusable

nullcrimson · 2 months ago

@claude

adeagoro52 · 2 months ago

Same issue on Claude 20x Max, started 2026-04-28. ~50% reduction in effective per-session throughput vs prior baseline, same workload. Feedback ID: 6df5e904-d285-43cc-ab11-4518e6f909df

Showdown76py · 2 months ago

Hi, just experienced the same issue. First, everything was normal, the 5h limit was being consumed at normal speed. Then suddenly, a request made my usage go from ~35% to 90% (Opus 4.7, xhigh). Just after that, I asked Claude Opus 4.7 (this time with medium reasoning) to perform "git push". Went from 90% to 100% usage, while I believe the cache was still up as I replied immediately after it responded. I'm on a 5x Max plan, and the context window for this chat was 233.6k/1.0M.

szwang · 2 months ago

Hi all, so sorry about this, we are investigating.

  • If you haven't already, could you please go into those high usage sessions and run /feedback? Then post your feedback uuid here.
  • If you're unable to share, a version number would be great.

More information here will be incredibly helpful.

Showdown76py · 2 months ago
Hi all, so sorry about this, we are investigating. If you haven't already, could you please go into those high usage sessions and run /feedback? Then post your feedback uuid here. If you're unable to share, a version number would be great. More information here will be incredibly helpful.

/feedback doesnt seem to exist on Claude Code Desktop. I would love to help but I can't find a way to get a UUID from the app.
Claude Desktop version: Claude 1.5354.0 (9a9e3d) 2026-04-29T01:14:34.000Z

alessandroavenali · 2 months ago
Hi all, so sorry about this, we are investigating. If you haven't already, could you please go into those high usage sessions and run /feedback? Then post your feedback uuid here. If you're unable to share, a version number would be great. More information here will be incredibly helpful.

Good day Suzanne.
How can we get into previous closed sessions or report session ID's? Also, it's not really about specific sessions. The issue is happening at every session. Usage speeded up twice at least.

louiscavalcante · 2 months ago

@szwang I've tried the Claude Code version from last week release and the token consumption is still insanely abnormal. The problem started for me around 29 of April 7:00AM UTC.

I've got several 5h window consumed really fast (under 30 minutes). One 5h window of (~30 min usage) is consuming 15% of the weekly quota. On this pace I will consume my weekly quota in under 3 days. Usually the weekly quota for the Max 5x plan is almost unreachable even when using the effort on max.

Feedback ID: 94b7c59a-e350-4c9a-ae7d-3408768e4a8b

kamalptw · 2 months ago

Claude code 20x subscriber here. I never even saw a usage limit past 6 months. Last 2 weeks, the $200 plan feels like the $20 plan.

Dasein732 · 2 months ago
Hi all, so sorry about this, we are investigating. If you haven't already, could you please go into those high usage sessions and run /feedback? Then post your feedback uuid here. If you're unable to share, a version number would be great. More information here will be incredibly helpful.

Feedback ID: 501f7790-3d15-441e-99ea-318491022f18, Claude Code 5x.
I never got a warning that I was nearing the limit. And I had much longer sessions without even hitting 80% on previous days(even without compacting the session, which I did now), and I pretty much never hit the limit 2~ hours into the session window before this.

alessandroavenali · 2 months ago

In my case it happened between 14:00 and 19:00 (2-7 PM) CET.
I understand it might have happened during the "rush hour" in which Anthropic declared to have shrinked the usage limits, but this might have gone too far if that's the case. If there's a dynamic usage allowance, it's not tuned in a sustainable way for the user. Just my 2c.

alessandroavenali · 2 months ago

I must say the non-rush-hour limits feels like they've been shrinked too. Hit the limit in 2h single agent on Max 5x, Opus 4.7. Only coding and self-review. I barely intereacted with it.

adeagoro52 · 2 months ago

This is looking better now. I've been working non stop for the last 3 hours and i'm only at 18% session usage for the 5 hour window. Way more like we expect.

alessandroavenali · 2 months ago
This is looking better now. I've been working non stop for the last 3 hours and i'm only at 18% session usage for the 5 hour window. Way more like we expect.

I can confirm. 2h30' @ 60% (5x Max) - maybe we are out of rush hours?

louiscavalcante · 2 months ago

v2.1.126 using since 01 of May 00:05 (UTC) the abnormal usage is gone.

I've noticed that the subagents are back to the old version where the conversation cannot be accessed.
Thanks for fixing the bug.

PS: I just want to add a note that the usage available is still too strict and has been reduced drastically, specially the 5h window. It should be a daily window instead, this 5h window is degrading people's sleeping cycle.

adeagoro52 · 2 months ago
This is looking better now. I've been working non stop for the last 3 hours and i'm only at 18% session usage for the 5 hour window. Way more like we expect.

This was me speaking too soon.

saratpediredla-level5 · 2 months ago

Same issue until this evening UK time. Rarely used to hit 5h limit but consistently hit it last 3 days since 29th

alessandroavenali · 2 months ago
Same issue until this evening UK time. Rarely used to hit 5h limit but consistently hit it last 3 days since 29th

+1 Italy here. Hit the 5h mark in 1h 30' <1M tokens. Definitely a daytime issue. limits are at least 2x tighter.

adeagoro52 · 2 months ago

My weekly quota is now depleted too, resetting on Tuesday. This is an absolute nightmare.

i-monarch · 2 months ago

I am seeing the same issue on Claude Max 20x.

This has been happening for 3 days. On May 2, 2026, immediately after my weekly limits reset, one prompt consumed 28% of my 5-hour session window. Weekly usage was still only 4% All models and 5% Sonnet-only.

Environment:

  • Plan: Max 20x
  • Claude Code: 2.1.126
  • Timezone: Europe/Kiev
  • Current session after one prompt: 28% used
  • Weekly All models: 4% used
  • Weekly Sonnet-only: 5% used

This makes Claude Code unusable for normal work. It looks like the 5-hour session window accounting is draining far faster than weekly usage, even immediately after the weekly reset.

i-monarch · 2 months ago

I am seeing the same issue on Claude Max 20x.

This has been happening for 3 days. On May 2, 2026, immediately after my weekly limits reset, one prompt consumed 28% of my 5-hour session window. After the second prompt, the 5-hour session window reached 50% used.

Weekly usage was still only 7% All models and 9% Sonnet-only.

Environment:

  • Plan: Max 20x
  • Claude Code: 2.1.126
  • Timezone: Europe/Kiev
  • Current session after first prompt: 28% used
  • Current session after second prompt: 50% used
  • Weekly All models after second prompt: 7% used
  • Weekly Sonnet-only after second prompt: 9% used

This makes Claude Code unusable for normal work. It looks like the 5-hour session window accounting is draining far faster than weekly usage, even immediately after the weekly reset.

i-monarch · 2 months ago

I am seeing the same issue on Claude Max 20x.

This has been happening for 3 days. On May 2, 2026, immediately after my weekly limits reset, one prompt consumed 28% of my 5-hour session window. After the second prompt, the 5-hour session window reached 50% used. After the next prompt/action, the current 5-hour session reached 83% used.

Weekly usage was still only 11% All models and 16% Sonnet-only.

Environment:

  • Plan: Max 20x
  • Claude Code: 2.1.126
  • Timezone: Europe/Kiev
  • Current session after first prompt: 28% used
  • Current session after second prompt: 50% used
  • Current session after next prompt/action: 83% used
  • Weekly All models after latest screenshot: 11% used
  • Weekly Sonnet-only after latest screenshot: 16% used
  • Claude Design: 0% used

This makes Claude Code unusable for normal work. It looks like the 5-hour session window accounting is draining far faster than weekly usage, even immediately after the weekly reset.

i-monarch · 2 months ago

Follow-up: the 5-hour session is now fully exhausted.

After only a few prompts/actions since the weekly reset:

  • Current 5-hour session: 100% used
  • Weekly All models: 14% used
  • Weekly Sonnet-only: 19% used
  • Claude Design: 0% used
  • Reset shown for current session: 3h 8m

So the session window is completely depleted while weekly usage is still low. This strongly suggests the 5-hour session window is being accounted much more aggressively than the weekly limits.

alessandroavenali · 2 months ago

I found it to be strictly time-related. There are rush hours that aggressively let you eat up those limits. For me in central EU is during the afternoon.

E-G-O-7 · 2 months ago

I’m using Claude Code v2.1.126 on the Pro plan. This morning, I asked two built-in subagents to change my codebase, and they consumed my entire 5-hour usage window in less than 10 minutes. The change itself was simple: replacing instances of System.out.println and System.out.printf in Java code with Log4j method calls.

I had the subagents’ JSONL logs analyzed with a quick Bash script, and it showed 78 Read operations across 23 files, as well as 75 Edit operations across 8 of those files. In particular, the most extreme case appears to have performed 17 full-file Reads on the same file.

I’m still new to Claude Code, so I assume this may have been due to how I used the subagents. Still, I can’t help but question whether this is expected behavior for the built-in subagents. I’m not sure whether this is related to this issue, but I hope the information is useful for the investigation.

grep -hoE '"name"[[:space:]]:[[:space:]]"[^"]+"' "$J1" "$J2" | sort | uniq -c | sort -nr
78 "name":"Read"
75 "name":"Edit"
3 "name":"Bash"
1 "name":"ToolSearch"

== Usage summary ==

usage_entries: 185
input_tokens: 21,269
output_tokens: 47,811
cache_creation_input_tokens: 1,649,869
cache_read_input_tokens: 13,782,441
new-ish input + output: 1,718,949
logged incl cache_read: 15,501,390

i-monarch · 2 months ago

Escalation update, May 3, 2026:

This is still happening after the new paid Max 20x subscription period/payment. This is not a stale report from Apr 29/30.

Latest observed usage:

  • Current 5-hour session: 34% -> 56% shortly after normal Claude Code work
  • Weekly All models: 18% -> 21%
  • Weekly Sonnet-only: 24% -> 28%
  • Claude Design: 0%

Support response says the pattern can be explained by parallel sessions, subagents, and >150K context. I understand those factors increase usage, but this is still not an acceptable/accountable product state for Max 20x:

  • Claude Code can burn a paid 5-hour window extremely quickly without a hard warning
  • Users do not get a per-session/per-process breakdown in the web UI
  • Users cannot identify which Claude Code/VS Code/Desktop process is consuming the quota
  • The web UI temporarily changed/reset and hid rows while CLI /usage still showed consumption
  • The only workaround is to manually close sessions and avoid built-in subagents, which defeats a major part of Claude Code

Local process check on Windows showed many active Claude/Node/Bun processes, so the parallel-session explanation is plausible. But that strengthens the request: Claude Code should expose, warn, or cap this behavior before it silently burns Max 20x quota.

Please escalate this as a cost/accounting UX bug, not only "expected usage". Paid users need either:

  • a clear fix,
  • a documented explanation of the new accounting behavior,
  • a per-session/process usage breakdown,
  • and/or reset/refund/credit for quota consumed unintentionally by this behavior.

Environment:

  • Plan: Max 20x
  • Claude Code: 2.1.126
  • Platform: Windows / VS Code / PowerShell
  • Timezone: Europe/Kiev
  • Existing Feedback ID in issue #55597: e2a121b8-2fd2-4721-98a4-f74edd479ab7
pablofuenteaguirre · 2 months ago

Same issue here. Within minutes, my Max (20x) plan is hitting limits, and what is worse, draining hundreds of euros from the extra usage balance. We need Claude to solve these issues, reset limits and refund us the money.

junaidtitan · 2 months ago

Session window draining 5-10x faster is usually accumulated context bloat — old tool outputs, stale reads, and metadata all get re-sent every turn. Cozempic's guard daemon auto-prunes continuously with 4 thresholds so context stays lean throughout the session. pip install cozempic — hooks wire automatically on first run. https://github.com/Ruya-AI/cozempic — let me know if it helps.

vintage-retro-guy · 2 months ago

My Claude Code on PRO is unusable, I get one or two prompts and my usage jumps to 74% straight away and then runs out. I put $5 API credit in and got one prompt and it was used up. I tried to run /feedback but I get the error "/feedback is only available for local sessions on this desktop build"

louiscavalcante · 2 months ago

5h window still consuming 12% of weekly usage on Max 5x using effort xhigh
It wasn't able to complete the plan without hitting the 5h limit and the main conversation context was still under 150k
Built-in subagents were used to avoid context rot, each tackling 1 phase of the plan.
Fedback ID: c5e34a45-b519-48ba-bd78-64854fee5467

davedavinci · 2 months ago

At this point it's clear this was intentional.
Now they released the news about SpaceX partnership which will grant more computational power and allow them to remove the peak hour squeeze: basically back to pre-April 29th (intentionally) bugged limits. Cringe af.

DEF29 · 1 month ago

The exact same issue recurred on June 10, 2026 — one-to-one with the original April 29 squeeze.

Timeline (Europe/Kaliningrad):

  • For the past 2 weeks we've been running the same daily workload on ultracode / effort xhigh (long-running infra+trading sessions, multi-agent workflows via the Workflow tool) with no session-window problems whatsoever. Effort level is constant in our setup, so it is not the variable.
  • June 9, ~21:05 — a session that had plenty of window left hit "You've hit your session limit" mid-workflow; in-flight Sonnet sub-agents started failing with the limit error exactly like in April.
  • June 10, ~02:00 — resuming a cached workflow (only ~8 sub-agents actually re-ran) burned the session window 51% → 82% → 93% within ~7 minutes. We stopped everything.
  • June 10, ~05:34, right after the window reset12% of a fresh 5-hour window was consumed within the first 2–3 minutes of light work: a handful of ssh/Read/Edit calls plus one background Sonnet sub-agent. This is the same 5–10× depletion rate described in the original report.

What changed on our side right before the recurrence: the session was migrated to the newly released model (claude-fable-5) after the model update rolled out. Same machine, same settings, same workload pattern as the previous two weeks.

Symptoms identical to April 29:

  • 5-hour window depletes 5–10× faster for the same kind of work;
  • sub-agents (Agent/Workflow) hit "You've hit your session limit" within minutes;
  • weekly quota barely moves while the session window evaporates.

Will attach a /feedback UUID from the affected installation shortly.

wozcode-helper · 7 days ago

i'm seeing the same since apr 29 evening, the 5 hour session window burns 5 to 10x faster for light edits and sonnet agents hit limit in 15 to 30 minutes. fwiw wozcode cut my token spend about 50 percent with better caching https://wozcode.com