- Increased ACCESS_TOKEN_LIFETIME_SECONDS from 30 minutes to 60 minutes for improved session duration.
- Introduced getRequestHeadersWithCurrentDesktopAuth function to streamline authorization header management across fetch requests in the chat page.
- Introduced fetchSession function to streamline session fetching logic.
- Updated useSession to handle 401 errors by refreshing the session when necessary.
- Modified getDesktopAccessToken to accept options for forced token refresh, improving desktop authentication flow.
- Refactored fetchZeroContext to include a buildHeaders function for better header management.
- Added a request function to handle 401 errors and refresh sessions as needed.
- Improved overall session management for desktop authentication.
- Implemented session refresh logic in the fetchWithTurnCancellingRetry function to handle 401 errors more gracefully.
- Added a new import for refreshSession utility to facilitate session renewal.
- Changed default AUTH_TYPE in backend configuration to "LOCAL".
- Updated frontend environment configuration to reflect the new default for packaged clients.
- Adjusted runtime authentication resolution to use "LOCAL" as the fallback value.
- Added logging for JSON parsing failures in structured output to aid in debugging.
- Updated the TranscriptTurn model to ignore unknown keys, improving flexibility for future model variations.
- Updated main-agent middleware to clarify that both filesystem reads/writes and knowledge-base retrieval are handled by the `knowledge_base` subagent.
- Introduced `_forward_mention_pins` function to carry `@`-mention pins into subagent state.
- Revised system prompts to reflect the new retrieval method and ensure proper citation handling.
- Removed the `search_knowledge_base` tool and its related tests, consolidating functionality under the `task` tool.
- Enhanced documentation to guide usage of the new retrieval approach and citation practices.
When the Unstructured API returns a Table element without text_as_html
in its metadata (e.g. local install or free-tier API), the lambda was
raising KeyError: 'text_as_html', crashing the entire document
indexing pipeline for any file containing tables.
Guard the key access with .get() and fall back to the plain extracted
text content (x) so the pipeline continues and the table content is
still indexed, just without HTML formatting.
The RAG/citation/context redesign in ADR 0001 is implemented and validated
(KB + web on the unified [n] citation spine, pull-based retrieval, eager path
retired). Drop the ADR and the one stale docstring reference to it.
The pull-based KB design (on-demand search_knowledge_base tool + pre-injected
workspace tree) fully replaced the old eager retrieval path. Remove its last
remnants:
- Delete KnowledgePriorityMiddleware (knowledge_search.py) and its tests.
- Drop the kb_priority state field + reducer default; trim
KbContextProjectionMiddleware to project only workspace_tree_text.
- Remove the now-dead feature flags enable_kb_priority_preinjection and
enable_kb_planner_runnable across backend (flags, route schema, tests,
env examples) and frontend (settings toggle, zod schema).
- Scrub <priority_documents> and stale KnowledgePriorityMiddleware references
from prompts, docstrings, and the ADR.
No functional change: nothing wrote kb_priority and neither flag gated live
behavior after the cutover. Full backend suite green (pre-existing unrelated
failures aside).
The legacy system_prompt_composer fragments and its default_system_instructions
wrapper were no longer referenced by any live code path (the main-agent prompt
builder owns composition now). Delete the whole orphaned tree and its test.
The model frequently writes citations glued to the preceding word
(docs[17]); the (?<!\w) lookbehind (added to dodge arr[1] array indexing)
silently skipped these, leaving raw [n] that fails to render and reads
like array access. Drop the lookbehind so glued citations resolve; genuine
code/array syntax stays protected by the existing code-region carve-out and
unresolved ordinals still drop harmlessly.
Rewrite the main-agent citation contract to a single [n] channel and sync
the orphaned system_prompt_composer surface to match; drop stale
[citation:chunk_id] / <chunk_index> references from dynamic_context and
provider hints. Reuse the shared hybrid search in the deliverables report
(citations omitted for now) and delete the orphaned report KB helper.
Remove the dead eager KnowledgePriorityMiddleware wiring (knowledge_priority
+ stack) and its legacy browse test. Update ADR 0001 to reflect the cutover.
web_search now registers each result as a WEB_RESULT (locator {url}) and
renders a <web_results> block of <document view="excerpt"> [n] passages,
returning Command(update={messages, citation_registry}) like
search_knowledge_base. Collapse the duplicate research-subagent web_search
into the shared tool and teach the prompts to cite web hits with [n].
The main agent's search_knowledge_base tool runs the hybrid spine, renders
a <retrieved_context> of numbered [n] passages, and persists the registry.
KB subagent prompts teach citing [n] from <document view="full"> reads
(evidence.chunk_ids -> evidence.citations). Delete the now-unused
search->read highlighting hand-off: the kb_matched_chunk_ids state field,
its reducer default, the tool's _matched_chunk_ids writer, and the dead
KnowledgePriorityMiddleware writes.
Add the checkpointed CitationRegistry (load/merge helpers + state field)
and a lightweight CitationStateMiddleware so subagents can register into
the same conversation registry. Resolve [n] -> [citation:<payload>] at
stream finalize from the registry, polymorphically by source type.
Add a shared document_render package that renders sources as
<document view="excerpt|full"> blocks with server-assigned [n] passage
labels (KB locator {document_id, chunk_id}, web locator {url}). Wire the
KB read backend (kb_postgres) and read_file to the new renderer and drop
the legacy per-document XML renderer (document_xml, retrieved_context) and
the old chunk_index / matched="true" / <chunk id> read format.
