Response rate-limit headers are no longer returned. Read the access token
from the Claude Code profile credentials (user:profile scope), report
5h/7d usage and resets, and add plan info with an inferred monthly renewal.
Claude-Session: https://claude.ai/code/session_01Gz3N3q53Bx9pbjB9tZT9dt
Flash is the default model; --m3 falls back to M3, --effort overrides.
Defaults: max (review-minimax, review-loop, mm-worktree-task), medium
(explore), low (ci-triage). ask-minimax-run applies MINIMAX_EFFORT to
Flash models when --effort is not passed. Bump stale fixture date.
After tmux new-session, call claude-sessions register with the
project_dir, profile, mode, and session name. Non-fatal — if
claude-sessions is not installed the spawn still proceeds.
Catches two failure modes that each felled a previous spec-amendment
attempt: a fabricated Revokes-prior-text quote (text not in the file at
--base) and a normative line silently deleted with no quote at all.
Generic: any --glob x --base <sha> against any repo, with optional --tag
filter. Reuses the collapse() / quote_line_re() shape from the M33
reference, adds a Check D for deleted/renamed files (-M30 rename
threshold), and four violation categories: unquoted deletions,
fabricated quotes, malformed markers, deleted since base. Stdlib Python
only, --json output, --dryrun prints resolved config and still runs the
checks (read-only by nature).
Across ~12 supervised MiniMax units, more than half reported a green suite
where a manual re-run found red (see memory/gotchas-minimax.md). Add
--gate "<command>" (with --gate-timeout, default 900s): after the detached
sub-session exits, mm-worktree-task itself re-runs the command in the
worktree against the sub-session's LAST commit, in its own reapable process
group (setsid + group kill, so a hung gate and everything it forked are
bounded and cleaned up), and appends an unambiguous PASSED/FAILED verdict —
plus an explicit MISMATCH callout when the agent's own report claimed
success — to the result file. A missing command, non-zero exit, timeout, or
dirty worktree are all failures, never a silent skip. mm-worktree-task's own
exit code is unchanged: the launch already returns before the sub-session
(and gate) run, detached.
Claude-Session: https://claude.ai/code/session_014KNyfHmHpMbdMrHZXDRkAp
Committing work found uncommitted in the checkout: --base lets a unit be based
on a branch other than main (used throughout the M32 cut-over session for
u6-tests and hatchmate-migration bases), and the bare 'return' statements
become 'return 0' so they cannot abort under set -e when the preceding test is
false.
Per the project agent-safety rule: untracked/uncommitted work that matters gets
committed the day it is found, so local loss cannot take it.
Claude-Session: https://claude.ai/code/session_014KNyfHmHpMbdMrHZXDRkAp
cp_cli lives in agent-runtimes; previously every planner call ran 'python3 -m lib.cp_cli' from the current repo with no --context, so the script only worked inside agent-runtimes. The context now resolves from ~/.cpconfig by matching project_id to the repo directory name. Verified live from hatchmate (item + parent + documents fetched via the hatchmate context).
Claude-Session: https://claude.ai/code/session_01JgJbWzVJioVznVTFyQFEfx
Wraps ask-minimax-run to run a MiniMax M3 implementation sub-session in an
isolated git worktree, with the prompt assembled from a planner work item
(cp_cli item + documents + parent/siblings). Supports --dryrun, --collect,
and --upload, per the pattern used for the 2026-09-10 seven-worktree batch
(see agent-runtimes memory/gotchas-minimax.md).
Claude-Session: https://claude.ai/code/session_015nXvGNNNixJPFwZKZHNyha
Identities live in ~/.git-identities (alias|Name|email). Interactive
menu to select, add, or remove identities; direct mode via alias
argument; --global/-g scope flag (defaults to local inside a repo,
global fallback outside); --list/--current helpers. Full --dryrun
support and a 27-assertion test suite driven through dryrun.
GIT_IDENTITIES_FILE env override for testability.
try_submit() returned after a single submission and was only called at
startup and once per completion, capping real concurrency at 1 task
regardless of the parallel setting — the ThreadPoolExecutor pool was
sized but never filled. Loop until every free slot is filled or no
eligible candidate remains, per spec §10 (wording sharpened to make the
whole-pool semantics explicit). No stub-claude harness exists yet to
test dispatch concurrency end-to-end; verified live against the real
queue (36 candidates, parallel=20).
Claude-Session: https://claude.ai/code/session_01Lgv4Qn82boNFC1jn8QXSNw
Optional config key (default false). When true, research candidates are
offered even at max_unreviewed_research_per_dossier; research_sampled
bookkeeping, mark sampled, and status flags are unchanged so unsampled
items stay visible for later human verification.
Claude-Session: https://claude.ai/code/session_01Lgv4Qn82boNFC1jn8QXSNw
idle-draft.state.json is now gitignored in the target repo; explicitly
git add-ing an ignored path errors, which broke every success commit.
The state file is still written atomically — just no longer tracked.
Claude-Session: https://claude.ai/code/session_01Lgv4Qn82boNFC1jn8QXSNw
Lock-contention test added; children die with the dispatcher (SIGTERM/
SIGINT handlers + atexit); tmp files are per-invocation (.tmp.<pid>) so
a SIGKILL-orphaned child can never collide with a new instance.
Claude-Session: https://claude.ai/code/session_01YQDoWNM7XPPii28khFWoMc
Research and topic_ideas runs get --allowedTools WebSearch,WebFetch;
research template mandates >=1 web search for related stories with
full-URL + access-date citations under the dossier's status labels.
Claude-Session: https://claude.ai/code/session_01YQDoWNM7XPPii28khFWoMc
Required --style, --json machine-readable output, mandatory --dryrun.
Engine unchanged; known limitation documented: already-scored paragraphs
are never re-examined (present in the original).
Claude-Session: https://claude.ai/code/session_01YQDoWNM7XPPii28khFWoMc
New script that launches Claude Code (via claude-profile) inside a detached
tmux session with --remote-control enabled, in a project's directory, named
after the project (Title-cased, auto-incrementing #N on collision). Lets a
session be started for later attach over VPN or control from the Claude app.
Spec-first per repo conventions: specs/claude-tmux.spec.md, script, and
tests/test-claude-tmux.sh (18 dryrun assertions, all passing).
Claude-Session: https://claude.ai/code/session_014oa7T7z1h5n34vu8vX9zGT
Passing combined context inline as a CLI arg hits Linux ARG_MAX (~2 MB)
when project CONTEXT.md or MEMORY.md are large. Three changes:
1. Write combined_context to a mktemp file and pass via
--append-system-prompt-file instead of the inline --append-system-prompt arg.
2. Drop exec in favour of a subprocess call so the EXIT trap fires
after claude exits, properly resetting the WezTerm theme and cleaning
up the temp file. (With exec, bash is replaced immediately and traps
never fire on success — WezTerm reset was silently broken.)
3. Warn when context exceeds 150 KB and show context size (in KB) on
the launch line and in dryrun output, so oversized CONTEXT.md files
are visible before they become a crash.
Provider selection phase removed; Anthropic driver→model_id is now
hardcoded in the script and non-Anthropic profiles supply provider.env
(MODEL_ID, ANTHROPIC_BASE_URL, ANTHROPIC_API_KEY_FILE).
Test suite baseline changes 58 → 41 assertions: the 17 dropped
assertions covered the removed provider-yaml selection phase, not
retained behaviour.
Includes refactor-derived memory: decisions (provider architecture,
driver enforcement via --model), bash gotchas (read -rp under set -e,
never eval user config), process lessons.
MiniMax changed from category_remains[text_generation] with count fields
to model_remains[general] with remaining_percent fields. Now tries v2
first (100 - remaining_percent), falls back to v1 count-based calculation.
Probes Anthropic OAuth and MiniMax subscription usage and displays
percentage consumed for 5-hour and 7-day windows with colour-coded output.
Ported probe logic from agent-runtimes/scripts/ralph_code.
Add a warning when ANTHROPIC_BASE_URL would be set but the active profile's
.credentials.json would override ANTHROPIC_API_KEY with subscription OAuth,
routing requests to Anthropic instead of the intended provider.
Fixes the MiniMax routing issue: use --profile minimax (~/.claude-minimax/,
no stored credentials) for non-Anthropic providers.
Update presets example to use profile: minimax for quick-minimax preset.
63 tests passing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Introduces provider files (`data/claude-profile/providers/*.yaml`) that
bundle model ID, API base URL, API key source, and extra env vars. Phase 2.5
(provider selection) added between mode selection and launch, with a default
derived from the mode's driver field so existing Anthropic usage is unchanged.
Ships 5 providers: anthropic-haiku/sonnet/opus/opus-1m and minimax-sonnet.
MiniMax token decrypted from agent-runtimes SOPS env, stored at
~/.claude-secrets/minimax-auth-token. Adding new providers = one YAML file,
no script changes.
58 dryrun tests passing (up from 37).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Polls /api/v1/repos/<owner>/<repo>/releases and matches each tag_name
against a shell-style glob (e.g. v1.2.3.*). Default 600s timeout, 5s
interval, both overridable. Exits 0 with the matched tag on stdout,
1 on timeout, 2 on usage error, 3 on terminal API error (401/403/404).
Intended to run in the background of a Claude Code session while CI
produces the release.
Includes spec and 42-assertion test using a PATH-shadowed mock curl.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Computes MAJOR.MINOR.PATCH.BUILD from NEW_MAJOR/NEW_MINOR/NEW_PATCH
whole-line tokens in commit messages since the last release tag.
Non-main branches get a BRANCH-SHORTSHA suffix and never release.
Maintains VERSION.md, writes $GITHUB_OUTPUT, and optionally creates
a Gitea release via API.
Includes spec, 67-assertion test, usage guide (docs/semver-ci.md),
and a drop-in Gitea Actions workflow template.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- claude-profile: phase 1-3 picker (profile, mode, launch) with preset support,
dryrun, WezTerm theming, and --append-system-prompt mode body injection
- 5 mode files (chat/quick/deep/hybrid/orch) with YAML frontmatter + prose body;
new escalates_to field drives statusline →Opus arrow for deep and hybrid
- statusline.sh reads CLAUDE_CONFIG_DIR/active-mode.env to show
[Sonnet→Opus] deep · topic format when launched via claude-profile
- Root CLAUDE.md session-start: auto-selects project from cwd or CLAUDE_PROJECT
in active-mode.env, skipping the interactive picker when context is clear
- Spec, tests (37 assertions, 9 test files, all passing), context docs, and
preset example included
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Uses ffmpeg to generate an H.264/AAC video from an MP3 file with a
centred title overlay. Supports optional background image (title at
bottom) or solid colour (title centred). Includes spec, dryrun support,
and 10 tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds gotchas-wezterm and updates gotchas-bash from recent reflections.
Prunes old reflected log. Updates MEMORY.md index.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove ^, +, ~, :, @ from the allowed charset. The ^ character breaks
SQLAlchemy DATABASE_URL parsing, + becomes space in URL query strings,
: and @ are URL delimiters. The remaining charset (A-Za-z0-9._-) is
safe in URLs, database connection strings, YAML, JSON, and shell
without any encoding.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Outputs cryptographically random strings using only characters safe
for unquoted use in bash, YAML, and JSON: [A-Za-z0-9._+\-:@^~]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Splits the current pane into evenly-sized grid using wezterm cli
split-pane. Supports optional command per pane, dryrun mode, and
auto-detects native or Flatpak WezTerm CLI.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
claude-profile now:
- Syncs all repos (git pull --ff-only) before starting a session
- Emits WezTerm user-var escape sequences to trigger profile themes
- Resets terminal theme on session exit via trap
New script sync-repos pulls latest for all git repos under ~/dev/claude
with --dryrun support and color status output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Utility for switching between Claude Code skill profiles by
managing the ~/.claude/skills symlink target.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
