Teknium 227e6c0143 fix(moa): resolve context window from the aggregator, not the 256K default (#53780) ... A MoA session's model is the preset name (e.g. 'opus-gpt') and its base_url is the virtual local endpoint, so get_model_context_length() missed every probe and fell through to the 256K fallback — even when the aggregator is a 1M-context model. The acting model in MoA IS the aggregator, so resolve the context window from the aggregator slot's real provider+model. - model_metadata.get_model_context_length: when provider=='moa', resolve the preset's aggregator slot through resolve_runtime_provider and recurse with the aggregator's real provider/model/base_url. Explicit model.context_length still wins (checked first); falls through to the generic default if resolution fails. Tests: opus-gpt preset now reports 1M (the aggregator window), config override still honored.		2026-06-27 12:08:09 -07:00
..
lsp	fix: prevent TUI gateway stdin EOF crash across all TUI-context subprocess calls	2026-06-08 22:46:57 -07:00
pet	feat(pets): quality-first OpenRouter model chain + stronger atlas gates + global pet-gen notifications	2026-06-24 23:11:21 -05:00
secret_sources	fix: prevent TUI gateway stdin EOF crash across all TUI-context subprocess calls	2026-06-08 22:46:57 -07:00
transports	fix(cache): content-address prompt_cache_key so recurring cron jobs reuse the warm prefix (#52295)	2026-06-24 21:46:30 -07:00
__init__.py
account_usage.py	feat(billing): /credits command — balance + portal top-up handoff (#44776)	2026-06-12 08:51:10 +00:00
agent_init.py	fix(agent_init): correct misleading sub-64K context_length error message (#53569)	2026-06-27 03:56:25 -07:00
agent_runtime_helpers.py	fix(agent): reload credential pool on switch_model provider change (#52727)	2026-06-27 04:39:26 -07:00
anthropic_adapter.py	fix(anthropic): use platform.claude.com for OAuth token exchange	2026-06-23 23:59:40 -07:00
async_utils.py
auxiliary_client.py	fix(auxiliary): fallback on invalid provider responses	2026-06-26 13:49:46 +05:30
azure_identity_adapter.py
background_review.py	feat(background-review): aux-model selector for the self-improvement review (#49252)	2026-06-22 14:54:53 -07:00
bedrock_adapter.py	fix(bedrock): check boto3 version >= 1.34.59 before using converse_stream	2026-06-15 05:25:17 -07:00
billing_view.py	feat(billing): /billing terminal billing — interactive TUI + CLI client (#45449)	2026-06-19 01:53:32 +05:30
browser_provider.py
browser_registry.py
chat_completion_helpers.py	fix(agent): validate OpenRouter provider sort before request dispatch	2026-06-27 11:43:08 -07:00
codex_responses_adapter.py	fix(xai): OAuth Responses native web_search, incomplete guard, grok-composer context	2026-06-17 17:33:32 -07:00
codex_runtime.py	fix(codex): seed app-server sessions with configured cwd	2026-06-21 16:39:02 -07:00
coding_context.py	fix(agent): require code for coding posture	2026-06-25 16:40:27 -05:00
context_compressor.py	fix(compression): abort (preserve context) on transient network summary failure (#29559, #25585)	2026-06-24 18:31:51 +05:30
context_engine.py
context_references.py	fix(agent): make a binary @file: reference actionable instead of a dead end	2026-06-09 19:16:46 -05:00
conversation_compression.py	fix(agent): rebaseline in-place compression flushes	2026-06-27 03:04:26 -07:00
conversation_loop.py	fix(moa): call reference + aggregator models through their provider's real route (#53580)	2026-06-27 04:39:42 -07:00
copilot_acp_client.py	fix: make profile subprocess HOME policy explicit	2026-06-14 03:20:21 -07:00
credential_persistence.py
credential_pool.py	fix(auth): write rotated Codex/xAI pool grant through to global root (#48415) (#52760)	2026-06-25 19:14:06 -07:00
credential_sources.py
credits_tracker.py	feat(billing): /credits command — balance + portal top-up handoff (#44776)	2026-06-12 08:51:10 +00:00
curator.py	fix(curator): make external-skill write guard actually fire during curation	2026-06-25 22:03:02 -07:00
curator_backup.py	fix(curator): stop the rollback safety snapshot from pruning its target	2026-06-17 05:40:05 -07:00
display.py	fix(browser): force secret-pattern redaction on browser_type display	2026-06-25 22:02:22 -07:00
error_classifier.py	fix(agent): classify 429 'overloaded' bodies as overloaded, not rate_limit	2026-06-27 04:16:54 -07:00
errors.py	fix(agent,gateway,doctor): add SSL CA cert bundle fail-fast guard	2026-06-13 21:14:32 -07:00
file_safety.py	fix: use os.pathsep, add tests, update tips for multi-root support	2026-06-27 04:01:12 +05:30
gemini_native_adapter.py	fix(gemini): strip native self prefixes before generateContent (#36141)	2026-06-13 13:47:08 -07:00
gemini_schema.py
i18n.py	fix(packaging): ship locales/ i18n catalogs in wheel, sdist, and Nix (#38383)	2026-06-03 12:00:27 -07:00
image_gen_provider.py	feat(image-gen): add image-to-image / editing to image_generate (#48705)	2026-06-18 22:13:07 -07:00
image_gen_registry.py
image_routing.py	fix(vision): honor custom_providers per-model supports_vision (#41036)	2026-06-07 21:50:57 -07:00
insights.py	refactor(insights): drop dead pricing/duration wrappers, call usage_pricing directly (#40618)	2026-06-07 18:33:20 -07:00
iteration_budget.py
jiter_preload.py
learn_prompt.py	fix(learn): name distilled skills as author Hermes, not the host OS user (#52388)	2026-06-25 12:48:08 -07:00
lmstudio_reasoning.py
manual_compression_feedback.py
markdown_tables.py
memory_manager.py	fix(agent): validate context/memory tool schemas before wrapping	2026-06-25 02:17:29 +05:30
memory_provider.py	fix(backup): capture memory-provider state stored outside HERMES_HOME (#50325)	2026-06-21 12:03:46 -07:00
message_content.py	fix(openviking): preserve structured sync attribution	2026-06-19 15:23:41 +08:00
message_sanitization.py	fix(agent): close tool-call sequence on all interrupt aborts, not just finalize_turn	2026-06-25 12:24:34 -05:00
moa_loop.py	fix(moa): call reference + aggregator models through their provider's real route (#53580)	2026-06-27 04:39:42 -07:00
model_metadata.py	fix(moa): resolve context window from the aggregator, not the 256K default (#53780)	2026-06-27 12:08:09 -07:00
models_dev.py
moonshot_schema.py	fix(moonshot): handle union type arrays in tool schemas	2026-06-13 05:51:41 -07:00
nous_rate_guard.py
onboarding.py	feat(onboarding): opt-in structured profile-build path on first contact (#41114)	2026-06-07 08:36:48 -07:00
oneshot.py	feat(agent): one-shot LLM helper + llm.oneshot gateway RPC (#51261)	2026-06-23 08:01:50 +00:00
plugin_llm.py
portal_tags.py
process_bootstrap.py
prompt_builder.py	fix(gateway): WhatsApp/Signal hints affirm markdown instead of forbidding it (#53564)	2026-06-27 03:46:41 -07:00
prompt_caching.py
rate_limit_tracker.py
reasoning_timeouts.py	fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice	2026-06-25 19:00:48 -07:00
redact.py	fix(redact): mask passwords in lowercase/dotted config keys (#53590)	2026-06-27 04:43:28 -07:00
retry_utils.py	fix: handle named custom providers and Z.AI overload retries	2026-06-25 00:17:17 -07:00
runtime_cwd.py	fix(desktop): stabilize project folder sessions (#37586)	2026-06-02 20:23:09 +00:00
secret_scope.py	feat(gateway): multiplex phase 2 — fail-closed profile credential isolation (Workstream A)	2026-06-19 07:34:15 -07:00
shell_hooks.py	docs: document per-event extra keys in shell-hook wire protocol	2026-06-20 23:23:47 -07:00
skill_bundles.py
skill_commands.py	fix(memory): strip skill scaffolding for all providers, not just openviking	2026-06-16 10:37:37 -07:00
skill_preprocessing.py	fix: prevent TUI gateway stdin EOF crash across all TUI-context subprocess calls	2026-06-08 22:46:57 -07:00
skill_utils.py	fix(curator): protect external skills from background curation	2026-06-25 22:03:02 -07:00
ssl_guard.py	fix(ssl): align guard docs and escape hatch	2026-06-13 21:14:32 -07:00
stream_diag.py
subdirectory_hints.py
system_prompt.py	feat(computer_use): cross-platform cua-driver (macOS/Windows/Linux)	2026-06-22 06:42:30 -07:00
think_scrubber.py
thinking_timeout_guidance.py	fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice	2026-06-25 19:00:48 -07:00
title_generator.py	feat(titles): support language-aware title generation (#45296)	2026-06-19 17:15:52 -07:00
tool_dispatch_helpers.py	feat(agent): require verification before finishing edits	2026-06-24 23:02:48 -05:00
tool_executor.py	fix: redact browser typed text surfaces	2026-06-25 22:02:22 -07:00
tool_guardrails.py
tool_result_classification.py
trajectory.py
transcription_provider.py
transcription_registry.py
tts_provider.py
tts_registry.py
turn_context.py	fix(agent): rebaseline in-place compression flushes	2026-06-27 03:04:26 -07:00
turn_finalizer.py	fix(agent): close tool-call sequence on all interrupt aborts, not just finalize_turn	2026-06-25 12:24:34 -05:00
turn_retry_state.py	fix(agent): fail over to fallback provider on persistent auth failure (401/403)	2026-06-20 11:38:01 -07:00
usage_pricing.py	fix(bedrock): price Claude prompt-cache tokens in /usage (#50307)	2026-06-21 11:48:43 -07:00
verification_evidence.py	feat(agent): recognize focused ad-hoc verification scripts	2026-06-24 23:03:45 -05:00
verification_stop.py	feat(verify-on-stop): default OFF, one-time migration, skip doc-only edits (#53552)	2026-06-27 03:23:22 -07:00
video_gen_provider.py
video_gen_registry.py
web_search_provider.py
web_search_registry.py