teknium1 5311d9959e refactor(run_agent): extract context compression to agent/conversation_compression.py ...

Move four compression-related methods to a dedicated module:

* check_compression_model_feasibility — startup probe + auto-lowered threshold + hard floor
* replay_compression_warning — re-emit stored warning through gateway status_callback
* compress_context — run compressor, split SQLite session, notify plugins+memory
* try_shrink_image_parts_in_messages — image-too-large recovery via re-encode

AIAgent keeps thin forwarder methods so existing call sites and tests
that patch run_agent.AIAgent methods keep working.

tests/run_agent/ + tests/agent/: 4313 passed (same pre-existing
test_auxiliary_client failure as before).

run_agent.py: 15013 -> 14535 lines (-478).

2026-05-16 18:09:33 -07:00

..

lsp

fix(lsp): shift baseline diagnostics into post-edit coordinates (#25978)

2026-05-14 15:56:07 -07:00

transports

fix(codex-app-server): attach redacted stderr tail to generic failures (#25929)

2026-05-14 14:55:23 -07:00

__init__.py

…

account_usage.py

…

anthropic_adapter.py

fix(cache): kill long-lived prefix layout — system prompt is now byte-static within a session (#24778)

2026-05-12 20:46:04 -07:00

auxiliary_client.py

fix(aux): surface Nous auth-unavailable warning in auxiliary client

2026-05-14 20:15:29 -07:00

background_review.py

refactor(run_agent): extract background memory/skill review to agent/background_review.py

2026-05-16 18:05:01 -07:00

bedrock_adapter.py

…

codex_responses_adapter.py

…

context_compressor.py

fix(ci): stabilize shared test state after 21012

2026-05-14 14:28:14 -07:00

context_engine.py

fix(compression): keep default protect_first_n at 3 + align ABC

2026-05-13 22:25:16 -07:00

context_references.py

…

conversation_compression.py

refactor(run_agent): extract context compression to agent/conversation_compression.py

2026-05-16 18:09:33 -07:00

copilot_acp_client.py

…

credential_pool.py

…

credential_sources.py

…

curator_backup.py

…

curator.py

…

display.py

chore: remove Atropos RL environments and tinker-atropos integration (#26106)

2026-05-15 10:36:38 +05:30

error_classifier.py

…

file_safety.py

…

gemini_cloudcode_adapter.py

fix(agent/gemini-cloudcode): seed delta defaults for reasoning-only stream chunks

2026-05-14 08:03:56 -07:00

gemini_native_adapter.py

…

gemini_schema.py

…

google_code_assist.py

…

google_oauth.py

…

i18n.py

…

image_gen_provider.py

…

image_gen_registry.py

fix(plugins): filter resolution by is_available() in web + image_gen registries

2026-05-13 22:31:28 -07:00

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

fix(cli): vertical fallback for markdown tables wider than terminal (#23948)

2026-05-11 16:49:13 -07:00

memory_manager.py

…

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

feat: add NovitaAI as LLM provider

2026-05-13 23:51:15 -07:00

models_dev.py

feat: add NovitaAI as LLM provider

2026-05-13 23:51:15 -07:00

moonshot_schema.py

…

nous_rate_guard.py

…

onboarding.py

…

plugin_llm.py

…

portal_tags.py

feat(nous): unified client=hermes-client-v<version> tag on every Portal request (#24779)

2026-05-12 20:49:20 -07:00

process_bootstrap.py

refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget

2026-05-16 17:59:32 -07:00

prompt_builder.py

fix(prompt_builder): inject tool-use enforcement for GLM models

2026-05-12 18:46:28 -07:00

prompt_caching.py

fix(cache): kill long-lived prefix layout — system prompt is now byte-static within a session (#24778)

2026-05-12 20:46:04 -07:00

rate_limit_tracker.py

…

redact.py

…

retry_utils.py

…

shell_hooks.py

…

skill_commands.py

…

skill_preprocessing.py

…

skill_utils.py

…

subdirectory_hints.py

…

think_scrubber.py

…

title_generator.py

…

tool_dispatch_helpers.py

refactor(run_agent): extract tool-dispatch helpers to agent/tool_dispatch_helpers.py

2026-05-16 17:54:26 -07:00

tool_guardrails.py

fix: classify landed file mutations with diagnostics

2026-05-13 06:46:23 -07:00

tool_result_classification.py

fix: classify landed file mutations with diagnostics

2026-05-13 06:46:23 -07:00

trajectory.py

…

usage_pricing.py

fix(pricing): add deepseek-v4-pro to official docs pricing table

2026-05-12 16:32:57 -07:00

video_gen_provider.py

feat(video_gen): unified video_generate tool with pluggable provider backends (#25126)

2026-05-13 16:39:41 -07:00

video_gen_registry.py

feat(video_gen): unified video_generate tool with pluggable provider backends (#25126)

2026-05-13 16:39:41 -07:00

web_search_provider.py

fix(web): align _LEGACY_PREFERENCE with legacy 7-provider order + doc cleanup

2026-05-13 22:31:28 -07:00

web_search_registry.py

fix(web): align _LEGACY_PREFERENCE with legacy 7-provider order + doc cleanup

2026-05-13 22:31:28 -07:00