Greedy multiset match on chunk text decides which rows keep their embeddings,
which texts need embedding, and which rows are deleted. No DB, no embeddings;
fully unit-tested (reuse, head insert, middle edit, deletion, duplicates,
reorder, full rewrite).
The cached payload is the indexing pipeline's embeddings (markdown is
chunked then embedded), so "embedding cache" names the expensive output
directly and removes the "index" ambiguity (DB index vs vector index vs
indexing phase). Renames the service, settings, eligibility, eviction
task, metrics, config flags (INDEX_CACHE_* -> EMBEDDING_CACHE_*), object
prefix, and the table (index_cache_embedding_sets -> embedding_cache_sets)
with its constraint and indexes. Migration 161 renamed accordingly.
Pin AUTH_TYPE=LOCAL (and REGISTRATION_ENABLED=TRUE) in the test bootstrap so
the email/password auth routers mount during integration tests regardless of a
developer's .env=GOOGLE; without this the upload tests 404 on registration.
Also update three tests to the current QuotaInsufficientError signature
(balance_micros) after used_micros/limit_micros were removed.
- Introduced LLMErrorCategory and adapt_llm_exception to normalize LLM exceptions.
- Updated llm_retryable_message and llm_permanent_message to utilize the new adaptation logic.
- Enhanced classify_stream_exception to classify provider errors and return user-friendly messages.
- Added tests for error classification and adaptation to ensure robustness.
- Updated frontend error handling to display appropriate messages based on new classifications.
Move the lifecycle service, Celery task bodies, and mark_failed coverage out of
DB-faking unit tests and into integration tests against a real Postgres, faking
only true externals (broker, object store, TTS, ffmpeg, billing, LLM). Add HTTP
slices for cancel, voices, scoping, and public-chat streaming. The unit tier is
now fake-free pure logic with no session doubles.
- Updated environment variables and - configurations for credit purchases via Stripe, replacing legacy page pack system.
- Introduced auto-reload feature for credit top-ups and modified database models to track credit transactions.
- Updated notification system to handle insufficient credits and auto-reload failures.
- Adjusted API routes and schemas to reflect changes in credit management.
The knowledge_base subagent imported subagent_invoke_config + EXCLUDED_STATE_KEYS
from main_agent's checkpointed_subagent_middleware -- a subagent reaching into
main-agent internals. Both symbols (plus the recursion-limit constant they need)
are a subagent-invocation contract shared by the orchestrator's task middleware
and any nested-invoking subagent. Move them to subagents/shared/invocation.py;
config.py keeps the HITL resume side-channel and constants.py keeps the
main-agent tuning knobs. All consumers (task_tool, kb tool, tests) repointed.
The KB-persistence impl lived in shared/middleware/ but no subagent uses it --
consumers are the main_agent builder and the boundary event loop. Colocate with
its owner using the folder-per-middleware shape; __init__ re-exports the public
surface. Tests that reached module internals now alias the .middleware submodule.
main_agent/middleware/kb_persistence.py -> kb_persistence/builder.py
shared/middleware/kb_persistence.py -> kb_persistence/middleware.py
The busy-mutex impl (BusyMutexMiddleware + cancel/turn-lifecycle primitives)
lived in shared/middleware/ but no subagent uses it -- consumers are the
main_agent builder and the boundary (turn lifecycle). Colocate with its owner
using the folder-per-middleware shape; __init__ re-exports the public surface so
boundary import sites only change package path:
main_agent/middleware/busy_mutex.py -> busy_mutex/builder.py
shared/middleware/busy_mutex.py -> busy_mutex/middleware.py
Per-file verification of the slice-3 candidates showed receipts/ and
date_filters.py are shared contracts (consumed by shared/state + shared
middleware + subagents), so they correctly stay put.
permissions was the real misfit: the rule *model* lived at shared/permissions.py
while its enforcement lived at shared/middleware/permissions/. Unify them into a
single self-contained subsystem:
shared/permissions.py -> shared/permissions/model.py
shared/middleware/permissions/{deny,ask,middleware}
-> shared/permissions/{deny,ask,middleware}
The package __init__ re-exports the model API + build_permission_mw, so the 32
external model consumers keep importing `from ...shared.permissions import Rule`
unchanged; only the 8 internal files redirect to `.model` (cycle-safe, model
loaded before middleware).
Move the lower-level runtime/infra modules out of multi_agent_chat/shared/
(they were never used by subagents, so they failed the shared-by-all-siblings
rule) and unify them with the already-relocated checkpointer:
agents/runtime/ -> agents/chat/runtime/
mac/shared/errors.py -> chat/runtime/errors.py
mac/shared/llm_config.py -> chat/runtime/llm_config.py
mac/shared/prompt_caching.py -> chat/runtime/prompt_caching.py
mac/shared/mention_resolver.py -> chat/runtime/mention_resolver.py
mac/shared/path_resolver.py -> chat/runtime/path_resolver.py
These sit below the agent packages: the boundary + agent factory + shared
middleware depend on them, and they import no agent code (acyclic).
Recursive shared-folder rule: a shared/ must be shared by ALL siblings at its
level. The kernel (context, compaction, retry_after, web_search) was shared by
only 2 of the agents -- anonymous_chat + multi_agent_chat -- never by podcaster
or video_presentation. Those 2 are the "chat" category, so their shared code
belongs in that category's shared/, not the top-level one.
app/agents/anonymous_chat/ -> app/agents/chat/anonymous_chat/
app/agents/multi_agent_chat/ -> app/agents/chat/multi_agent_chat/
app/agents/shared/ -> app/agents/chat/shared/ (anon<->mac kernel)
Top-level app/agents/shared/ is gone: nothing was shared across all three
categories (chat / podcaster / video_presentation).
~289 import sites rewritten (app.agents.{anonymous_chat,multi_agent_chat,shared}
-> app.agents.chat.*); all moves are git renames (history preserved).
app/agents/ now: chat/, podcaster/, video_presentation/, runtime/.
These were never shared with anonymous_chat (nor podcaster/video_presentation)
-- only multi_agent_chat (subagents/main agent) and the boundary use them:
shared/tools/mcp/ -> multi_agent_chat/shared/tools/mcp/
shared/tools/hitl.py -> multi_agent_chat/shared/tools/hitl.py
shared/tools/catalog.py -> multi_agent_chat/shared/tools/catalog.py
shared/middleware/dedup_tool_calls.py
-> multi_agent_chat/shared/middleware/dedup_tool_calls.py
app/agents/shared/ now holds only the genuine anon<->mac kernel:
context, middleware/{compaction,retry_after}, tools/web_search.
Neither module is imported by any sibling agent package, so neither belongs in
the cross-agent shared kernel:
- checkpointer.py -> app/agents/runtime/checkpointer.py
LangGraph Postgres checkpoint saver. It's cross-agent *runtime infra* wired by
the boundary (app lifespan + anonymous_chat & multi_agent_chat flows), not
agent code. New app/agents/runtime/ layer holds boundary-wired agent infra.
- shared/system_prompt.py + shared/prompts/ -> app/prompts/
The legacy single-agent prompt composer. The live agents don't use it
(main_agent has its own system_prompt/ builder; anonymous_chat builds inline);
its only consumer is new_llm_config_routes for displaying default instructions.
Moved to the existing non-agent prompt domain:
system_prompt.py -> app/prompts/default_system_instructions.py
prompts/ -> app/prompts/system_prompt_composer/
app/agents/shared/ now contains only genuinely cross-agent code: context,
middleware/{compaction,retry_after,dedup_tool_calls}, tools/.
NOTE: get_default_system_instructions() (LLM-config UI) composes from the legacy
library, which differs from what the live agents actually run -- pre-existing
latent staleness, not changed here.
