Teknium 03c0b00f45 fix(usage): read DeepSeek's native prompt_cache_hit_tokens cache field (#65678) ... DeepSeek's own API (api.deepseek.com) reports context-cache hits as top-level usage.prompt_cache_hit_tokens / prompt_cache_miss_tokens (prompt_tokens = hit + miss), not the OpenAI nested prompt_tokens_details.cached_tokens shape. Neither normalize_usage() nor the chat_completions transport's extract_cache_stats() read those fields, so direct DeepSeek sessions always showed 0 cache-hit tokens: invisible in accounting, mis-billed at the full input rate, and 0% cache display. Both layers now fall back to prompt_cache_hit_tokens when the nested shape is absent; the nested value wins when both are present (proxies). Fixes #61871.		2026-07-16 07:29:53 -07:00
..
lsp	…
pet	…
secret_sources	…
transports	fix(usage): read DeepSeek's native prompt_cache_hit_tokens cache field (#65678)	2026-07-16 07:29:53 -07:00
__init__.py	…
account_usage.py	…
agent_init.py	feat: add LM Studio JIT load mode	2026-07-16 15:23:14 +05:30
agent_runtime_helpers.py	chore(agent): tripwire — warn when a turn starts before the previous turn's persist	2026-07-16 04:56:10 -07:00
anthropic_adapter.py	fix(auxiliary): apply review fixes to #36043 — guard named-custom routing, drop dead key assignment, tighten Palantir host match	2026-07-16 07:28:07 -07:00
async_utils.py	…
aux_accounting.py	feat(analytics): record auxiliary model usage per task in session accounting (#65537)	2026-07-16 04:23:12 -07:00
auxiliary_client.py	fix(auxiliary): apply review fixes to #36043 — guard named-custom routing, drop dead key assignment, tighten Palantir host match	2026-07-16 07:28:07 -07:00
azure_identity_adapter.py	…
background_review.py	…
bedrock_adapter.py	fix(bedrock): streaming fallback to Converse API + image base64 decode + bearer token routing	2026-07-15 09:59:38 -07:00
billing_view.py	…
bounded_response.py	…
browser_provider.py	…
browser_registry.py	…
chat_completion_helpers.py	…
codex_responses_adapter.py	fix(agent): treat Codex incomplete content filter as refusal	2026-07-15 09:47:37 -07:00
codex_runtime.py	…
coding_context.py	…
context_breakdown.py	…
context_compressor.py	fix(context): harden compression failure feedback	2026-07-16 14:34:03 +05:30
context_engine.py	…
context_references.py	…
conversation_compression.py	…
conversation_loop.py	fix(bedrock): streaming fallback to Converse API + image base64 decode + bearer token routing	2026-07-15 09:59:38 -07:00
copilot_acp_client.py	…
credential_persistence.py	…
credential_pool.py	fix(auth): preserve fallback routes and OAuth state	2026-07-16 06:14:56 -07:00
credential_sources.py	…
credits_tracker.py	…
curator.py	…
curator_backup.py	…
display.py	…
error_classifier.py	fix(plugins): classify stale-call circuit breaker as failover, not retry	2026-07-16 00:27:39 +05:30
errors.py	…
file_safety.py	…
gemini_native_adapter.py	…
gemini_schema.py	…
i18n.py	…
image_gen_provider.py	…
image_gen_registry.py	…
image_routing.py	…
insights.py	fix(insights): include auxiliary usage in overview token totals (#65603)	2026-07-16 05:39:33 -07:00
iteration_budget.py	…
jiter_preload.py	…
kanban_stop.py	…
learn_prompt.py	…
learning_graph.py	…
learning_graph_render.py	…
learning_mutations.py	…
lmstudio_reasoning.py	…
manual_compression_feedback.py	fix(context): harden compression failure feedback	2026-07-16 14:34:03 +05:30
markdown_tables.py	…
memory_manager.py	…
memory_provider.py	…
message_content.py	…
message_sanitization.py	…
moa_loop.py	feat(portal): ambient conversation context entangles aux/MoA/delegate calls	2026-07-16 01:13:43 -07:00
moa_trace.py	…
model_metadata.py	…
models_dev.py	…
moonshot_schema.py	…
nous_rate_guard.py	…
onboarding.py	…
oneshot.py	…
plugin_llm.py	…
portal_tags.py	feat(portal): ambient conversation context entangles aux/MoA/delegate calls	2026-07-16 01:13:43 -07:00
process_bootstrap.py	…
prompt_builder.py	fix(agent): scope install-tree guard to fallback-picked cwds, allow cli/tui in-tree dev	2026-07-16 04:32:23 -07:00
prompt_caching.py	…
rate_limit_tracker.py	…
reactions.py	…
reasoning_timeouts.py	…
redact.py	…
replay_cleanup.py	…
retry_utils.py	…
runtime_cwd.py	fix(agent): scope install-tree guard to fallback-picked cwds, allow cli/tui in-tree dev	2026-07-16 04:32:23 -07:00
secret_scope.py	…
shell_hooks.py	…
skill_bundles.py	…
skill_commands.py	…
skill_preprocessing.py	…
skill_utils.py	…
ssl_guard.py	…
ssl_verify.py	…
stream_diag.py	…
subdirectory_hints.py	…
system_prompt.py	fix(agent): scope install-tree guard to fallback-picked cwds, allow cli/tui in-tree dev	2026-07-16 04:32:23 -07:00
think_scrubber.py	fix(agent): re-arm think scrubber boundary after stream flush	2026-07-16 01:07:29 +05:30
thinking_timeout_guidance.py	…
thread_scoped_output.py	…
title_generator.py	feat(analytics): record auxiliary model usage per task in session accounting (#65537)	2026-07-16 04:23:12 -07:00
tool_dispatch_helpers.py	fix(agent): canonicalise paths in parallel-batch planner to prevent same-file concurrent mutation	2026-07-16 04:26:32 -07:00
tool_executor.py	fix(agent): canonicalise paths in parallel-batch planner to prevent same-file concurrent mutation	2026-07-16 04:26:32 -07:00
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	chore(agent): tripwire — warn when a turn starts before the previous turn's persist	2026-07-16 04:56:10 -07:00
turn_finalizer.py	…
turn_retry_state.py	…
usage_pricing.py	fix(usage): read DeepSeek's native prompt_cache_hit_tokens cache field (#65678)	2026-07-16 07:29:53 -07:00
verification_evidence.py	…
verification_stop.py	…
verify_hooks.py	…
vertex_adapter.py	…
video_gen_provider.py	…
video_gen_registry.py	…
web_search_provider.py	…
web_search_registry.py	…