joaomarcos a23d5073fb fix(agent): stop switch_model from pairing new provider with stale base_url ... switch_model() unconditionally set agent.provider but only set agent.base_url when the resolved value was truthy. When a real provider change resolved an empty base_url (e.g. minimax after copilot), the agent ended up with provider="minimax" but base_url still pointing at api.githubcopilot.com. That incoherent pair then got snapshotted into agent._primary_runtime, so it kept re-applying on every subsequent turn via restore_primary_runtime() until the process restarted. try_activate_fallback() and _swap_credential() were audited and confirmed unaffected: both always derive base_url from an actually constructed client, never from a possibly-empty resolver hint. Fix: when base_url is empty AND the provider is genuinely changing, raise ValueError instead of silently keeping the old provider's URL. This routes through switch_model()'s existing snapshot/rollback path, and callers (tui_gateway/server.py's _apply_model_switch) already catch and surface a clean "switch failed, staying on X" message. Re-selecting the SAME provider with an empty base_url (credential-only refresh) still keeps the current URL, unchanged. Fixes #47828 Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>		2026-07-09 16:36:06 -07:00
..
lsp	refactor(setup): route dependency installs through the canonical uv→pip→ensurepip ladder	2026-07-07 04:09:35 -07:00
pet	fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)	2026-07-05 13:42:46 -07:00
secret_sources	feat(secrets): adapt 1Password onto the SecretSource interface	2026-07-06 04:58:07 -07:00
transports	refactor(salvage): scope #40632 to the two live copy-on-write sites	2026-07-09 14:35:14 +05:30
__init__.py	…
account_usage.py	fix(usage): scope Codex usage pool fallback to AuthError, keep singleton token on account_id read failure	2026-07-07 12:01:33 +05:30
agent_init.py	feat(openai): complete gpt-5.6 E2E — codex catalog + 272K compaction auto-raise	2026-07-10 00:47:51 +05:30
agent_runtime_helpers.py	fix(agent): stop switch_model from pairing new provider with stale base_url	2026-07-09 16:36:06 -07:00
anthropic_adapter.py	fix(auth): per-profile Anthropic OAuth file + complete port-binding platform set (#57563 salvage) (#59339)	2026-07-07 08:33:06 +00:00
async_utils.py	…
auxiliary_client.py	feat(openai): complete gpt-5.6 E2E — codex catalog + 272K compaction auto-raise	2026-07-10 00:47:51 +05:30
azure_identity_adapter.py	…
background_review.py	fix(background-review): guard summarize against list-shaped tool responses (#59437)	2026-07-06 03:28:30 -07:00
bedrock_adapter.py	…
billing_view.py	…
bounded_response.py	fix(agents): bound streaming error-response body reads	2026-07-05 14:00:20 -07:00
browser_provider.py	…
browser_registry.py	…
chat_completion_helpers.py	fix: preserve fallback switch notice on successful fallback	2026-07-09 13:40:19 +05:30
codex_responses_adapter.py	fix(codex): route commentary-phase preamble text to reasoning channel (fixes #41293)	2026-07-05 06:29:45 -07:00
codex_runtime.py	feat(agent): add Codex-native compaction paths	2026-07-07 02:39:54 -07:00
coding_context.py	…
context_breakdown.py	…
context_compressor.py	fix(compression): stop compaction thrash — 75% trigger floor under 512K, no summary output cap, reasoning-trace exclusion (#60989)	2026-07-08 11:56:17 -07:00
context_engine.py	…
context_references.py	…
conversation_compression.py	feat(agent): add Codex-native compaction paths	2026-07-07 02:39:54 -07:00
conversation_loop.py	fix: preserve fallback switch notice on successful fallback	2026-07-09 13:40:19 +05:30
copilot_acp_client.py	…
credential_persistence.py	…
credential_pool.py	fix(secrets): make 1Password bootstrap token reliable outside systemd	2026-07-06 04:58:07 -07:00
credential_sources.py	…
credits_tracker.py	…
curator.py	…
curator_backup.py	fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)	2026-07-05 13:42:46 -07:00
display.py	feat(display): show file_path in skill_view tool progress lines (#60079)	2026-07-07 01:07:49 -07:00
error_classifier.py	fix(error-classifier): retry HTTP 408 as timeout instead of aborting as format_error	2026-07-06 01:56:09 -07:00
errors.py	…
file_safety.py	…
gemini_native_adapter.py	fix(agents): bound streaming error-response body reads	2026-07-05 14:00:20 -07:00
gemini_schema.py	…
i18n.py	…
image_gen_provider.py	…
image_gen_registry.py	…
image_routing.py	Guard native image routing with file safety	2026-07-05 03:15:03 -07:00
insights.py	…
iteration_budget.py	…
jiter_preload.py	…
learn_prompt.py	…
learning_graph.py	…
learning_graph_render.py	fix: cover remaining GNU-only %-d strftime site in learning graph render	2026-07-05 00:59:35 -07:00
learning_mutations.py	…
lmstudio_reasoning.py	…
manual_compression_feedback.py	…
markdown_tables.py	…
memory_manager.py	refactor: address Phase-2 review findings on /new boundary handoff	2026-07-09 03:21:54 +05:30
memory_provider.py	…
message_content.py	…
message_sanitization.py	…
moa_loop.py	…
moa_trace.py	…
model_metadata.py	review fixes: openai-api pricing route normalization, GA pricing_version, invariant tests	2026-07-10 00:47:51 +05:30
models_dev.py	…
moonshot_schema.py	…
nous_rate_guard.py	…
onboarding.py	fix(config): close unreadable-overwrite bug class at a single chokepoint	2026-07-05 23:00:34 +05:30
oneshot.py	…
plugin_llm.py	…
portal_tags.py	…
process_bootstrap.py	fix(agent): apply pool-level keepalive to the process_bootstrap sibling builder	2026-07-05 03:14:55 -07:00
prompt_builder.py	perf(skills): speed up snapshot prompt builds	2026-07-09 02:41:24 +05:30
prompt_caching.py	refactor(salvage): scope #40632 to the two live copy-on-write sites	2026-07-09 14:35:14 +05:30
rate_limit_tracker.py	…
reasoning_timeouts.py	fix(reasoning): add deepseek-v4-flash and deepseek-v4-pro to reasoning timeout floor	2026-07-09 15:04:14 +05:30
redact.py	fix(redact): skip env-lookup exception for JSON/YAML config field redaction	2026-07-05 13:58:19 -07:00
replay_cleanup.py	fix: redact expired confirmations in place to preserve role alternation	2026-07-07 14:40:32 +05:30
retry_utils.py	refactor(retry): single-source Z.AI overload short-attempts + drop change-detector assert	2026-07-07 11:57:01 +05:30
runtime_cwd.py	…
secret_scope.py	…
shell_hooks.py	fix(cli): safe mode also skips shell-hook registration	2026-07-07 02:32:32 -07:00
skill_bundles.py	fix(gateway): apply platform-disabled skill gate to bundle invocations (#59156)	2026-07-05 14:48:11 -07:00
skill_commands.py	fix(cron): normalize absolute skill paths before skill_view (#59824)	2026-07-07 14:40:56 +05:30
skill_preprocessing.py	…
skill_utils.py	perf(skills): speed up snapshot prompt builds	2026-07-09 02:41:24 +05:30
ssl_guard.py	…
ssl_verify.py	…
stream_diag.py	…
subdirectory_hints.py	…
system_prompt.py	fix(agent): tag desktop chat sessions as desktop	2026-07-08 06:18:18 -07:00
think_scrubber.py	…
thinking_timeout_guidance.py	…
thread_scoped_output.py	…
title_generator.py	…
tool_dispatch_helpers.py	…
tool_executor.py	feat(plugins): pass approve rule keys to approval gate	2026-07-07 15:14:30 -07:00
tool_guardrails.py	…
tool_result_classification.py	…
trace_upload.py	feat(sessions): trace export + HF upload via 'sessions export --format trace' (#60507)	2026-07-07 15:12:49 -07:00
trajectory.py	…
transcription_provider.py	…
transcription_registry.py	…
tts_provider.py	…
tts_registry.py	…
turn_context.py	feat(agent): add Codex-native compaction paths	2026-07-07 02:39:54 -07:00
turn_finalizer.py	…
turn_retry_state.py	…
usage_pricing.py	feat(openai): cover gpt-5.6 -pro variants (PR #61587 complement)	2026-07-10 00:47:51 +05:30
verification_evidence.py	…
verification_stop.py	…
verify_hooks.py	…
vertex_adapter.py	…
video_gen_provider.py	…
video_gen_registry.py	…
web_search_provider.py	fix(web): widen config-aware env resolution to exa/parallel/tavily/brave-free providers	2026-07-06 02:42:24 -07:00
web_search_registry.py	fix(web): correct 'disabled plugin' diagnosis for web backends (#59573)	2026-07-06 04:38:17 -07:00