xxxigm 3b6f57fa66 fix(run-agent): treat any 403 on xai-oauth as entitlement to stop refresh-loop ... The existing ``_is_entitlement_failure`` heuristic only fires when the response body contains specific substrings ("do not have an active Grok subscription", etc.). xAI has been seen to 403 standard SuperGrok subscribers with a terser body that doesn't match those keywords (#26847), and the recovery path would then mint a fresh token, get a fresh 403, and loop until Ctrl+C. Add a defense-in-depth check at the recovery call site: any 403 on ``provider == "xai-oauth"`` short-circuits ``try_refresh_current`` so the error surfaces immediately with the friendly hint from ``_summarize_api_error``. Keeps the existing keyword path for all other providers untouched.		2026-05-18 20:08:09 -07:00
..
lsp	chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355)	2026-05-17 02:29:41 -07:00
transports	fix(codex): allow kanban worker board writes	2026-05-17 11:50:43 -07:00
__init__.py
account_usage.py
agent_init.py	fix(compress): make abort-on-summary-failure opt-in via config flag (#28117)	2026-05-18 10:28:20 -07:00
agent_runtime_helpers.py	fix(run-agent): treat any 403 on xai-oauth as entitlement to stop refresh-loop	2026-05-18 20:08:09 -07:00
anthropic_adapter.py	feat(azure-foundry): add Microsoft Entra ID auth	2026-05-18 10:14:38 -07:00
async_utils.py
auxiliary_client.py	fix(xai-responses): strip enum values containing '/' from tool schemas	2026-05-18 10:37:35 -07:00
azure_identity_adapter.py	feat(azure-foundry): add Microsoft Entra ID auth	2026-05-18 10:14:38 -07:00
background_review.py	feat(bg-review): add bundled/pinned skill protection rules to review prompts (#27644)	2026-05-18 20:02:22 -07:00
bedrock_adapter.py	chore(deps): lazy-install boto3/botocore for bedrock adapter	2026-05-17 02:31:18 -07:00
browser_provider.py	fix(browser): self-review pass — dead-import, log levels, future-proofing	2026-05-17 04:04:15 -07:00
browser_registry.py	fix(browser): self-review pass — dead-import, log levels, future-proofing	2026-05-17 04:04:15 -07:00
chat_completion_helpers.py	fix(xai-responses): strip enum values containing '/' from tool schemas	2026-05-18 10:37:35 -07:00
codex_responses_adapter.py
codex_runtime.py	fix(xai): surface provider 'error' SSE frame in Codex fallback stream (#27184)	2026-05-16 23:41:09 -07:00
context_compressor.py	fix(compress): make abort-on-summary-failure opt-in via config flag (#28117)	2026-05-18 10:28:20 -07:00
context_engine.py
context_references.py
conversation_compression.py	fix(compress): abort instead of dropping messages when summary LLM fails (#28102)	2026-05-18 10:19:40 -07:00
conversation_loop.py	fix: wrap _pool_may_recover_from_rate_limit call through run_agent namespace	2026-05-18 20:04:57 -07:00
copilot_acp_client.py
credential_pool.py	fix(codex-oauth): quarantine terminal refresh errors so dead tokens are not replayed across sessions	2026-05-18 10:31:40 -07:00
credential_sources.py
curator.py
curator_backup.py
display.py
error_classifier.py	fix(error_classifier): classify xAI Grok entitlement SSE errors as auth	2026-05-18 10:24:13 -07:00
file_safety.py
gemini_cloudcode_adapter.py
gemini_native_adapter.py
gemini_schema.py
google_code_assist.py
google_oauth.py
i18n.py
image_gen_provider.py
image_gen_registry.py
image_routing.py
insights.py
iteration_budget.py	refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget	2026-05-16 17:59:32 -07:00
lmstudio_reasoning.py
manual_compression_feedback.py
markdown_tables.py
memory_manager.py	🐛 fix(memory): require newline after context tag	2026-05-18 10:53:08 -07:00
memory_provider.py
message_sanitization.py	refactor(run_agent): extract message sanitization to agent/message_sanitization.py	2026-05-16 17:41:09 -07:00
model_metadata.py	fix(metadata): qwen3.6-plus has a 1M context window (#27008)	2026-05-17 02:31:18 -07:00
models_dev.py
moonshot_schema.py
nous_rate_guard.py
onboarding.py
plugin_llm.py
portal_tags.py
process_bootstrap.py	refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget	2026-05-16 17:59:32 -07:00
prompt_builder.py	fix(agent): add qwen and deepseek to TOOL_USE_ENFORCEMENT_MODELS	2026-05-18 20:06:49 -07:00
prompt_caching.py
rate_limit_tracker.py
redact.py	fix(security): redact xAI (Grok) API keys in logs	2026-05-18 10:21:22 -07:00
retry_utils.py
shell_hooks.py	refactor(security): extract _block_message helper to unify block logic in _parse_response	2026-05-17 02:31:18 -07:00
skill_commands.py	fix(skills): load symlinked skill slash commands	2026-05-18 00:34:29 -07:00
skill_preprocessing.py	fix: treat inline-shell timeout guard as timeout	2026-05-18 19:36:04 -07:00
skill_utils.py
stream_diag.py	refactor(run_agent): extract stream diagnostics to agent/stream_diag.py	2026-05-16 18:28:17 -07:00
subdirectory_hints.py
system_prompt.py	perf(prompt-cache): date-only timestamp + loud gateway-DB roundtrip logging	2026-05-17 23:20:37 -07:00
think_scrubber.py
title_generator.py
tool_dispatch_helpers.py	feat: add supports_parallel_tool_calls for MCP servers (#26825) — port to tool_dispatch_helpers	2026-05-16 23:36:37 -07:00
tool_executor.py	feat(session_search): single-shape tool with discovery, scroll, browse — no LLM (#27590)	2026-05-17 23:28:45 -07:00
tool_guardrails.py
tool_result_classification.py
trajectory.py
usage_pricing.py
video_gen_provider.py
video_gen_registry.py
web_search_provider.py
web_search_registry.py