README: DeepSWE benchmark results - #1511

…1436)

A task's crew is picked per task by internal/crewroute (class, price on every connected route, quality minus lambda times cost) instead of a stored preset. /crew holds only what is allowed, what is pinned and a daily cap; --best and --cheap move one task. Old profiles migrate once. Route health, a per-seat fallback ladder, per-task and daily spend limits, /redo stronger, remote protocol 18.

Added in review: a pin keeps its thinking level, auto in the reflex or small-work row reads its default and migrates, -yes-spend passes the daily cap, the cap refusal no longer offers --cheap, zero crew money is not drawn, and the manual describes the one seats row; dev merged in over #1429, #1485, #1494 and #1511.

Co-authored-by: Santosh kumar <29346072+santoshkumarradha@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

…side senior-dev

Brings in #1494 (team delegation), #1511 and #1436 (per-task worker, planner and
checker routing). A senior-dev run keeps its own road beside them: it works
alone in the folder it holds, so a via proposal starts one program run and does
not go through the team split; it keeps the models it was asked for, or the
pinned or profile worker, and #1436's per-task routing and $5 task cap apply to
codeaf's own tasks, while senior-dev keeps its finite per-run ceiling. Both
sides had claimed remote protocol version 18; the combined wire is version 19.
Program badges fit #1494's grouped side column, the manuals describe the merged
model choice, and the prompt-size ledger records the combined fixed prefix
(57,218 bytes). dev's unbounded-launch test now holds its six workers at a
barrier instead of guessing with a sleep, which failed on a loaded machine.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

…1635)

The installer on main, on top of v0.4.1 and nothing else from dev: checked
steps with a spinner, a link into a folder already on PATH so codeaf works in
the same terminal, a Get started guide, and on a terminal the question
`Start codeaf in <folder> now? [Y/n]`, read from /dev/tty. The binary is
untouched; only the script, its tests and the pages that describe it move.

scripts/install.sh, test/installer-telemetry.sh and
internal/release/install_test.go are byte-identical to #1635's head, which
also carries the installer halves of two dev changes it was written on: the
installer prints no telemetry notice (#1511, with the matching
docs/TELEMETRY.md paragraph; v0.4.1 still prints the full notice itself
before any count is sent), and an install under another name puts that name
first in its receipt (#1519). docs/GUIDE.md and the two manual pages take
#1635's paragraphs in place of the ones that described the three-line notice.

It also carries the review fixes made on the pull request before it
landed: only the installer's own link on PATH is ever replaced, the start
question is not asked in the home folder or at /, the spinner's frames
survive a UTF-8 locale that is not installed, and the guide sends
DeepSeek, Qwen, GLM, Kimi and Ollama through /connect, since v0.4.1's first
run offers OpenRouter alone.

This commit is merged into staging and dev so main stays an ancestor of
staging and staging of dev, and every later promotion is still a
fast-forward.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

Brings e446507 (the guided installer, on top of v0.4.1) into staging, so
main can fast-forward onto it and the rc it publishes passes the "already on
staging" check. Staging already carried #1511's half of that commit; the
conflicts in scripts/install.sh and test/installer-telemetry.sh resolve to
#1635's head, byte for byte.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>