SHL0MS 8567031433 fix: improve context compression quality — named constants, tool tracking, degradation warning ...

Three targeted improvements to the compression system:

1. Replace hardcoded truncation limits with named class constants
   (_CONTENT_MAX=6000, _CONTENT_HEAD=4000, _CONTENT_TAIL=1500,
   _TOOL_ARGS_MAX=1500, _TOOL_ARGS_HEAD=1200). Previous limits
   (3000/500) heavily truncated the summarizer's input — a 200-line
   edit got cut to 3000 chars before the summarizer ever saw it.

2. Add '## Tools & Patterns' section to both compression prompt
   templates (first-pass and iterative). Preserves working tool
   invocations, preferred flags, and tool-specific discoveries
   across compaction boundaries.

3. Warn users on 2nd+ compression: 'Session compressed N times —
   accuracy may degrade. Consider /new to start fresh.'

Ref #499

2026-04-08 20:54:23 -07:00

..

__init__.py

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

anthropic_adapter.py

fix: normalize httpx.URL base_url + strip thinking signatures for third-party endpoints

2026-04-08 16:39:29 -07:00

auxiliary_client.py

fix: CI test failures — metadata key, cli console, docker env, vision order (#6294)

2026-04-08 16:37:05 -07:00

builtin_memory_provider.py

refactor: add tool_error/tool_result helpers + read_raw_config, migrate 129 callsites

2026-04-07 13:36:38 -07:00

context_compressor.py

fix: improve context compression quality — named constants, tool tracking, degradation warning

2026-04-08 20:54:23 -07:00

context_references.py

refactor: replace inline HERMES_HOME re-implementations with get_hermes_home()

2026-04-07 10:40:34 -07:00

copilot_acp_client.py

fix: bridge tool-calls in copilot-acp adapter

2026-04-06 01:47:57 -07:00

credential_pool.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821)

2026-04-07 10:25:31 -07:00

display.py

refactor: remove 24 confirmed dead functions — 432 lines of unused code

2026-04-07 11:41:26 -07:00

insights.py

fix(insights): show cache tokens in overview so total adds up (#4428)

2026-04-01 03:06:47 -07:00

memory_manager.py

refactor: add tool_error/tool_result helpers + read_raw_config, migrate 129 callsites

2026-04-07 13:36:38 -07:00

memory_provider.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821)

2026-04-07 10:25:31 -07:00

model_metadata.py

fix: CI test failures — metadata key, cli console, docker env, vision order (#6294)

2026-04-08 16:37:05 -07:00

models_dev.py

feat(qwen): add Qwen OAuth provider with portal request support

2026-04-08 13:46:30 -07:00

prompt_builder.py

feat(prompting): self-optimized GPT/Codex tool-use guidance via automated behavioral benchmarking (#6120)

2026-04-08 04:06:42 -07:00

prompt_caching.py

fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter

2026-03-21 16:54:43 -07:00

redact.py

fix: mem0 API v2 compat, prefetch context fencing, secret redaction (#5423)

2026-04-05 22:43:33 -07:00

retry_utils.py

feat(agent): add jittered retry backoff

2026-04-08 00:41:36 -07:00

skill_commands.py

feat(skills): add skill config interface + llm-wiki skill (#5635)

2026-04-06 13:49:13 -07:00

skill_utils.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821)

2026-04-07 10:25:31 -07:00

smart_model_routing.py

Merge branch 'main' into rewbs/tool-use-charge-to-subscription

2026-04-02 11:00:35 +11:00

subdirectory_hints.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821)

2026-04-07 10:25:31 -07:00

title_generator.py

feat(agent): configurable timeouts for auxiliary LLM calls via config.yaml (#3597)

2026-03-28 14:35:28 -07:00

trajectory.py

Refactor Terminal and AIAgent cleanup

2026-02-21 22:31:43 -08:00

usage_pricing.py

fix: status bar shows 26K instead of 260K for token counts with trailing zeros (#3024)

2026-03-25 12:45:58 -07:00