Brooklyn Nicholson f726090d48 feat(sessions): name a session the moment it starts ... Titling fired on the first response, so a session sat unnamed for the whole opening turn - p50 151s, p90 1212s across real sessions, because a turn is tool calls, not one round-trip. A turn that failed or was interrupted never got a title at all. Four surfaces each carried their own copy of the call. Move it into the shared turn prologue and split it in two: a deterministic title derived from the user's opening message, written inline before the model runs, then one small-model call that upgrades it. The response is constrained to a JSON object so there is no preamble to strip, and control wrappers are stripped rather than refused, so a slash command titles as what the user asked for instead of the command itself.		2026-08-08 17:07:21 -05:00
..
lsp	…
monitoring	…
pet	…
proxy_sources	…
secret_sources	…
transports	feat(compression): native OpenAI Responses server-side compaction for gpt-5.6	2026-08-08 11:24:45 -07:00
verify	…
__init__.py	…
account_usage.py	…
agent_init.py	feat(compression): native OpenAI Responses server-side compaction for gpt-5.6	2026-08-08 11:24:45 -07:00
agent_runtime_helpers.py	feat(agent): read_window_below tool — which OS window is underneath the desktop app	2026-08-08 12:17:50 -05:00
anthropic_adapter.py	…
async_utils.py	…
aux_accounting.py	…
auxiliary_client.py	perf(sessions): resolve the titling model from the provider's live catalog	2026-08-08 17:07:21 -05:00
azure_identity_adapter.py	…
backend_identity.py	…
background_review.py	…
battery.py	…
bedrock_adapter.py	…
billing_links.py	…
billing_usage.py	…
billing_view.py	…
bounded_response.py	…
browser_provider.py	…
browser_registry.py	…
chat_completion_helpers.py	feat(compression): native OpenAI Responses server-side compaction for gpt-5.6	2026-08-08 11:24:45 -07:00
codex_responses_adapter.py	feat(compression): native OpenAI Responses server-side compaction for gpt-5.6	2026-08-08 11:24:45 -07:00
codex_runtime.py	…
coding_context.py	…
context_breakdown.py	…
context_compressor.py	fix(compression): correct prune boundary + exempt native compaction checkpoints	2026-08-08 14:09:41 -07:00
context_engine.py	Revert "fix: rewire DCP context engine to current main architecture"	2026-08-08 23:09:45 +05:30
context_references.py	fix(docker): read attached binary files in backend (#76577)	2026-08-08 05:44:18 -07:00
conversation_compression.py	fix(sessions): give titles provenance so they stop overwriting themselves	2026-08-08 17:07:21 -05:00
conversation_loop.py	fix(compression): correct prune boundary + exempt native compaction checkpoints	2026-08-08 14:09:41 -07:00
copilot_acp_client.py	…
credential_persistence.py	…
credential_pool.py	…
credential_sources.py	fix(auth): read .env as utf-8-sig in the dotenv-vs-shell detector	2026-08-08 12:32:23 -07:00
credits_tracker.py	…
curator.py	…
curator_backup.py	refactor: fold simplify findings — 6th copy in update_cmd, drop dead wrapper + speculative kwarg, behavior-contract tests	2026-08-08 15:10:35 +05:30
delegation_context.py	…
display.py	…
error_classifier.py	…
errors.py	…
estop.py	fix: post-merge audit follow-ups for #81138/#81139/#81141/#81148	2026-08-08 05:21:09 -07:00
file_safety.py	…
gemini_native_adapter.py	…
gemini_schema.py	…
i18n.py	…
image_gen_provider.py	feat(media): opt-in upscale pass for image_generate and video_generate across FAL and Krea	2026-08-08 14:49:28 -07:00
image_gen_registry.py	…
image_routing.py	…
insights.py	…
interrupt_compat.py	…
iteration_budget.py	…
jiter_preload.py	…
kanban_stop.py	…
learn_prompt.py	fix(learn): process large sources incrementally	2026-08-08 05:09:43 -07:00
learning_graph.py	…
learning_graph_render.py	…
learning_mutations.py	…
lmstudio_reasoning.py	…
manual_compression_feedback.py	…
markdown_tables.py	…
memory_manager.py	…
memory_provider.py	…
message_content.py	…
message_sanitization.py	…
moa_loop.py	…
moa_trace.py	…
model_metadata.py	…
models_dev.py	…
moonshot_schema.py	…
native_compaction.py	fix(compression): correct prune boundary + exempt native compaction checkpoints	2026-08-08 14:09:41 -07:00
nous_rate_guard.py	…
onboarding.py	…
oneshot.py	…
outbound_webhooks.py	…
plugin_llm.py	…
portal_tags.py	…
process_bootstrap.py	…
prompt_builder.py	style(hud): tighten the surface-note comments and test helper	2026-08-08 16:21:15 -05:00
prompt_caching.py	…
rate_limit_tracker.py	…
reactions.py	…
reasoning_summaries.py	…
reasoning_timeouts.py	…
redact.py	…
relay_llm.py	…
relay_runtime.py	…
relay_tools.py	…
replay_cleanup.py	…
retry_utils.py	…
runtime_cwd.py	…
secret_scope.py	…
session_activity.py	…
shell_hooks.py	fix: finish the missing-encoding sweep — BOM-tolerant reads for user-edited stores	2026-08-08 12:32:23 -07:00
skill_bundles.py	…
skill_commands.py	…
skill_preprocessing.py	…
skill_utils.py	…
ssl_guard.py	fix(ssl_guard): tolerate truststore SSLContext.get_ca_certs() NotImplementedError on Windows	2026-08-08 15:10:24 +05:30
ssl_verify.py	…
stream_diag.py	…
stream_single_writer.py	…
subagent_lifecycle.py	…
subdirectory_hints.py	…
subscription_view.py	…
system_prompt.py	fix: revert except ImportError back to except Exception	2026-08-08 13:57:44 +05:30
think_scrubber.py	…
thinking_timeout_guidance.py	…
thread_scoped_output.py	…
title_generator.py	feat(sessions): name a session the moment it starts	2026-08-08 17:07:21 -05:00
tool_dispatch_helpers.py	…
tool_executor.py	feat(agent): read_window_below tool — which OS window is underneath the desktop app	2026-08-08 12:17:50 -05:00
tool_guardrails.py	…
tool_result_classification.py	…
trace_upload.py	…
trajectory.py	…
transcription_provider.py	…
transcription_registry.py	…
tts_provider.py	…
tts_registry.py	…
turn_context.py	feat(sessions): name a session the moment it starts	2026-08-08 17:07:21 -05:00
turn_finalizer.py	fix(agent,gateway): class-level lone-surrogate chokepoints (#80366 #55143 #55309 #50959 #19819)	2026-08-08 12:31:19 -07:00
turn_retry_state.py	feat(compression): native OpenAI Responses server-side compaction for gpt-5.6	2026-08-08 11:24:45 -07:00
turn_summary.py	…
usage_pricing.py	…
verification_evidence.py	…
verification_stop.py	…
verify_hooks.py	…
vertex_adapter.py	…
video_gen_provider.py	feat(media): opt-in upscale pass for image_generate and video_generate across FAL and Krea	2026-08-08 14:49:28 -07:00
video_gen_registry.py	…
web_search_provider.py	…
web_search_registry.py	…