Bryan Johnson
4f1ea86051
Diagnose-don't-assume rate-limit cluster (Clover #8). The rate_limit_error on a work-box with 90% of the 5h Max quota free was a short-window BURST rail, not 5h exhaustion — tripped by a stream->non-stream double-send per turn with no backoff. - Rate-limit backoff honoring retry-after (else exp 2/4/8 cap 30) + actionable header-parsed message naming the tripped rail; headers.log now captures every 429 (was OAuth+unified-* only), tagged with retry-after + rail. - parse_stream_to_response detects a non-SSE JSON error body (429/overload) and returns a distinct code so agent_turn surfaces it WITH backoff instead of re-sending the whole prompt (single-send invariant). Auto LARRY_NO_STREAM=1 on MobaXterm/Cygwin/MSYS; explicit LARRY_NO_STREAM=0 still forces streaming on. - ErrorPI fix: strip_cr on err_type/err_msg in _humanize_api_error (a trailing CR broke the case match AND carriage-overprinted "API error"); err/warn/log now strip embedded CRs defensively. (v0.7.5 sweep missed the error-display path.) - phi tier-5 notice once-per-session via $LARRY_HOME/.phi-notice-shown SESSION_ID flag (old export flag died in the $(...) subshell -> per-turn nag). Same-pattern sweep fixed the identical subshell-flag bug in _auto_phi_b64_roundtrip. Deliverable: Deliverables/2026-05-27-cloverleaf-larry-v085-ratelimit-streaming-fixes.md Co-Authored-By: Clover (Claude Opus 4.7) <noreply@anthropic.com>
26 lines
414 B
Plaintext
26 lines
414 B
Plaintext
# Larry runtime artifacts (created in $LARRY_HOME, not the source repo, but
|
|
# included here for defensive hygiene in case someone runs Larry from the repo dir).
|
|
sessions/
|
|
journal/
|
|
knowledge/
|
|
.env
|
|
bin/jq
|
|
bin/jq.exe
|
|
*.larry-prerollback.*
|
|
*.larry-tmp.*
|
|
.phi-notice-shown
|
|
.b64-py3-notice-shown
|
|
.last-stream-headers
|
|
|
|
# Editor / OS noise
|
|
.DS_Store
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
.vscode/
|
|
.idea/
|
|
|
|
# Backup files from sed -i
|
|
*.bak
|
|
*.bak2
|