briandevans cfc8befe65 fix(compressor): use text char sum for multimodal token estimation in _find_tail_cut_by_tokens ... _find_tail_cut_by_tokens called len(content) to estimate message tokens. When content is a list of blocks (multimodal: text + image_url), len() returns block count (e.g. 2) rather than character count, so a message with 500 chars of text was counted as ~10 tokens instead of ~135. This caused the backward walk to exhaust all messages before hitting the budget ceiling; the head_end safeguard then forced cut = n - min_tail, shrinking the protected tail to the bare minimum and preventing effective compression of long multimodal conversations. Fix mirrors the existing pattern in _prune_old_tool_results (line 487): sum(len(p.get("text", "")) for p in raw_content) if isinstance(raw_content, list) else len(raw_content) Tests: 3 new cases in TestTokenBudgetTailProtection — regression guard (confirms the test fails with the bug), plain-string regression guard, and image-only block edge case. Fixes #16087. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>		2026-04-26 21:48:09 -07:00
..
transports	fix(agent): preserve Codex message items for replay	2026-04-25 18:22:06 -07:00
__init__.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00
account_usage.py	feat(account-usage): add per-provider account limits module	2026-04-21 01:56:35 -07:00
anthropic_adapter.py	fix: pass api-version as default_query param, not in base_url — SDK was producing malformed URLs like /anthropic?api-version=.../v1/messages	2026-04-25 18:48:43 -07:00
auxiliary_client.py	fix: preserve URL query params for Azure OpenAI and custom endpoints	2026-04-25 18:48:43 -07:00
bedrock_adapter.py	fix(bedrock): evict cached boto3 client on stale-connection errors	2026-04-24 07:26:07 -07:00
codex_responses_adapter.py	fix(agent): preserve Codex message items for replay	2026-04-25 18:22:06 -07:00
context_compressor.py	fix(compressor): use text char sum for multimodal token estimation in _find_tail_cut_by_tokens	2026-04-26 21:48:09 -07:00
context_engine.py	fix(compress): don't reach into ContextCompressor privates from /compress (#15039)	2026-04-24 02:55:43 -07:00
context_references.py	fix(agent): fall back when rg is blocked for @folder references	2026-04-20 01:56:41 -07:00
copilot_acp_client.py	fix: set HOME for Copilot ACP subprocesses	2026-04-24 05:09:08 -07:00
credential_pool.py	fix(auth): hoist get_env_value import + strengthen .env fallback tests	2026-04-26 08:32:09 -07:00
credential_sources.py	fix(auth): unify credential source removal — every source sticks (#13427)	2026-04-21 01:52:49 -07:00
display.py	fix(display): render <missing old_text> in memory previews instead of empty quotes (#12852)	2026-04-19 22:45:47 -07:00
error_classifier.py	fix(agent): only set rate-limit cooldown when leaving primary; add tests	2026-04-24 05:35:43 -07:00
file_safety.py	fix(security): apply file safety to copilot acp fs	2026-04-21 01:31:58 -07:00
gemini_cloudcode_adapter.py	refactor: remove redundant local imports already available at module level	2026-04-21 00:50:58 -07:00
gemini_native_adapter.py	fix(gemini): fail fast on missing API key + surface it in hermes dump (#15133)	2026-04-24 05:35:17 -07:00
gemini_schema.py	fix(gemini): drop integer/number/boolean enums from tool schemas (#15082)	2026-04-24 03:40:00 -07:00
google_code_assist.py	fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833)	2026-04-17 15:34:12 -07:00
google_oauth.py	feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270)	2026-04-16 16:49:00 -07:00
image_gen_provider.py	feat(plugins): pluggable image_gen backends + OpenAI provider (#13799)	2026-04-21 21:30:10 -07:00
image_gen_registry.py	feat(plugins): pluggable image_gen backends + OpenAI provider (#13799)	2026-04-21 21:30:10 -07:00
insights.py	Merge branch 'main' into feat/dashboard-skill-analytics	2026-04-20 05:25:49 -07:00
manual_compression_feedback.py	fix(gateway): make manual compression feedback truthful	2026-04-10 21:16:53 -07:00
memory_manager.py	fix(memory): add write origin metadata	2026-04-24 14:37:55 -07:00
memory_provider.py	fix(memory): add write origin metadata	2026-04-24 14:37:55 -07:00
model_metadata.py	fix(cli): /model picker honors provider-specific context caps (#16030)	2026-04-26 05:43:31 -07:00
models_dev.py	fix: normalize provider in list_provider_models to support aliases	2026-04-23 01:59:20 -07:00
moonshot_schema.py	fix(kimi,mcp): Moonshot schema sanitizer + MCP schema robustness (#14805)	2026-04-23 16:11:57 -07:00
nous_rate_guard.py	fix(nous): don't trip cross-session rate breaker on upstream-capacity 429s (#15898)	2026-04-26 04:53:42 -07:00
onboarding.py	fix(openclaw-migration): case-preserving brand rewrite + one-time ~/.openclaw residue banner (#16327)	2026-04-26 20:57:26 -07:00
prompt_builder.py	improve(agent): guidance for plain-text URLs, subagent language/verification, hermes-config routing (#16325)	2026-04-26 20:57:19 -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
rate_limit_tracker.py	refactor: remove dead code — 1,784 lines across 77 files (#9180)	2026-04-13 16:32:04 -07:00
redact.py	feat: replace kimi-k2.5 with kimi-k2.6 on OpenRouter and Nous Portal (#13148)	2026-04-20 11:49:54 -07:00
retry_utils.py	feat(agent): add jittered retry backoff	2026-04-08 00:41:36 -07:00
shell_hooks.py	fix(shell_hooks): parse hooks_auto_accept as strict bool/string, not bool() (#16322)	2026-04-26 20:48:35 -07:00
skill_commands.py	fix(prompts): replace [SYSTEM: with [IMPORTANT: to avoid Azure content filter	2026-04-26 08:44:58 -07:00
skill_preprocessing.py	fix(skills): apply inline shell in skill_view	2026-04-24 15:15:07 -07:00
skill_utils.py	fix(skills): follow symlinks in iter_skill_index_files	2026-04-22 17:43:30 -07:00
subdirectory_hints.py	fix(agent): catch PermissionError in subdirectory hint discovery	2026-04-09 03:10:30 -07:00
title_generator.py	fix: increase max_tokens for GLM 5.1 reasoning headroom	2026-04-22 18:44:07 -07:00
trajectory.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00
usage_pricing.py	fix(usage): read top-level Anthropic cache fields from OAI-compatible proxies	2026-04-22 17:40:49 -07:00