Commit Graph

4 Commits

Author SHA1 Message Date
cbe15d548f v0.5.3: send User-Agent + Accept headers in OAuth token exchange
Confirmed against live token endpoint (HTTP/2 200, valid sk-ant-oat01- and
sk-ant-ort01- tokens returned) that the v0.5.2 0.5.2 request body and
URLs were correct — the EXCHANGE itself works fine from my Mac. Bryan's
work-box launches still get 'rate_limit_error' from the same script.

Only meaningful differences in the working curl vs the failing one:
  - Working: explicit User-Agent (claude-cli/2.1.85) + Accept: application/json
  - Failing: defaults (curl/X.Y.Z, no Accept)

Anthropic's OAuth endpoint apparently checks User-Agent (or the Accept
header) and returns the misleading rate_limit_error for unrecognized
clients. Adding both headers to match what claude-cli and droidrun
send. Patched in cmd_login AND cmd_refresh.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 09:41:21 -07:00
c42fd92292 v0.5.2: OAuth endpoint migration — console.anthropic.com → platform.claude.com
Root cause of every prior 'rate_limit_error' on OAuth login: Anthropic
migrated all the Claude-subscription OAuth endpoints from
console.anthropic.com / claude.ai to platform.claude.com / claude.com.
The old endpoints aren't 404 — they accept the POST and return a generic
'rate_limit_error' for every request, which is what mis-led both me and
several public community implementations.

Confirmed against two current working clients (droidrun/mobilerun and
motiful/cc-gateway, both using the same Claude Code public client_id):

  AUTHORIZE_URL: claude.ai/oauth/authorize
              → claude.com/cai/oauth/authorize
  TOKEN_URL:     console.anthropic.com/v1/oauth/token
              → platform.claude.com/v1/oauth/token
  REDIRECT_URI:  console.anthropic.com/oauth/code/callback
              → platform.claude.com/oauth/code/callback
  SCOPE:         org:create_api_key user:profile user:inference
              → ...plus user:sessions:claude_code user:mcp_servers user:file_upload

Also updated the error-hint text to mention the misleading-rate-limit
pattern for both 'malformed code' AND 'dead endpoint' cases, and to cite
the current TOKEN_URL — so if/when these move again, the next person
hitting the same trap finds the answer in the script's own output.

The CODE#STATE parsing from 0.5.0 was correct and stays. State IS sent
in the token-exchange body (verified against droidrun's working flow).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 09:13:47 -07:00
28622ca40b v0.5.0: MANIFEST-driven self-update + OAuth code#state parsing
Self-update overhaul (no more manual reinstalls when lib/ changes):
- New MANIFEST file at repo root lists every file that should auto-sync
  (top-level scripts, agents/, lib/, VERSION, MANUAL.md).
- larry.sh self_update() reworked into two phases:
    Phase A — local sync: if $LARRY_HOME/.last-sync-version != $LARRY_VERSION,
      fetch MANIFEST and refresh every listed file. Stamps version after.
    Phase B — remote check: fetch $LARRY_BASE_URL/VERSION; if newer, pull
      larry.sh, self-replace, relaunch with LARRY_JUST_UPDATED=1 so phase B
      is skipped on the relaunch (phase A then pulls everything else).
- New LARRY_BASE_URL env var (the legacy LARRY_UPDATE_URL / LARRY_AGENTS_URL
  still work as overrides).
- Bumped LARRY_VERSION and VERSION to 0.5.0.

OAuth fix (lib/oauth.sh):
- Anthropic's callback returns the code as 'CODE#STATE' (URL fragment, not
  query). Previous prompt told users to copy "between code= and the next &"
  which produced the wrong substring; the token endpoint then returned a
  misleading 'rate_limit_error' on the malformed code.
- Now splits the pasted input on '#', verifies the returned state matches
  the one we generated, sends only CODE to the token endpoint.
- Updated user-facing prompt and error hints to describe the real format
  and explain the misleading rate_limit_error symptom.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 08:50:46 -07:00
61f1500492 v0.3.1: OAuth subscription auth + offline manual cheat sheet
Two additions:

1. OAuth subscription auth (lib/oauth.sh + larry-auth.sh)
   - PKCE-based out-of-band flow against Claude.ai (no localhost server
     needed; works behind any firewall).
   - Uses the same client_id Claude Code uses, so calls bill against your
     Max/Pro subscription quota instead of pay-as-you-go API metering.
   - Tokens stored at $LARRY_HOME/.oauth.json (mode 0600), auto-refresh.
   - larry.sh now detects oauth file at startup and uses Bearer auth.
   - First-run flow now offers OAuth or API key; /login, /logout, /auth
     slash commands in the REPL.
   - Transparent fallback to API key if OAuth flow fails.

2. MANUAL.md — offline tool cheat sheet
   - Documents every lib/*.sh script with copy-paste examples.
   - Bryan's backup plan: when Anthropic is unreachable (no internet, on
     a plane, etc.), all the underlying tools work standalone from the
     shell. Larry just sequences them; they do not need Larry to run.
   - Quick-recipe table at the bottom for the common day-to-day asks.

Files added:
  - lib/oauth.sh
  - larry-auth.sh
  - MANUAL.md

Files modified:
  - larry.sh — auth-mode detection, /auth /login /logout commands
  - install-larry.sh — fetch new files

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 09:57:44 -07:00