Repository navigation
Conversation
|
Two findings on exact head
The prompt change does remove the mounted argument value and retain the argument name in all five paired cases I ran, including real metadata parsing rather than stubbing AI-only verification on macOS arm64/Python 3.14.10. Only filesystem lookup and VLM responses were substituted; no real model, embedding, native-storage operation, or deployed server was exercised. Seven dependency warnings were present in both test runs. |
|
Both findings fixed on
Full affected suites: |
|
@lester076 Confirmed both fixes on I reran the same production file-summary path (real YAML metadata parsing and prompt rendering, offline VLM responses) against
All five probe cases now stay within the configured 256 characters. The short summary is unchanged; mounted argument values stay out of the prompt while their names remain present. The two focused modules now pass 16/16 (previous head: 11 passed, 1 failed). The existing AI-only verification on macOS arm64 / Python 3.14.10, using the same pinned dependencies and published 0.5.3 native component as the earlier review. Filesystem lookup and VLM responses were substituted; no real model, embedding, native-storage operation, deployed server, or full-suite run. Seven dependency warnings remain in each pytest run. |
Fixes #7692
Problem
A live-context node summary inlined the complete mounted-argument code into the abstract: the
live_context_summaryprompt demanded "Preserve every mounted argument name and value", so a node whoseargs.codecarries ~2 KB of JS produced a 2,536-character / 979-token summary. The recall assembler's default per-entry cap is 320 tokens, andresourcesentries have no fallback tier belowabstract— so every automatic recall silently degraded this node to<memory detail="uri" />: path only, no content. The agent gets a bare URI it cannot act on without a blindread, which executes the bound MCP tool (~13 s, 4–5 upstream calls in the reporter's setup). Raisingmax_tokensonly makes the 2.5 KB code land in context, which is not what a recall abstract is for.What changed
live_context_summary.yaml: the prompt now receives the mounted argument names and their total serialized size, and explicitly instructs the model to name the arguments without copying their values (values can carry kilobytes of code or data that belongs to the node file, not to a recall abstract). The full values remain available through the node file and the Tool definition attool_uri, which the summary already points to.semantic_processor.py: the file-level summary gate now enforcessemantic.abstract_max_chars(256 by default) via the existing_truncate_generated_text. This limit previously applied only to directory overviews and media parsers, so any oversized file summary could enter storage and only be dropped at injection time — the second gap the issue notes (same family as [Bug] Inconsistent abstract size limits: _enforce_size_limits caps at 256 chars but _truncate_abstract_bytes caps at 50,000 bytes #3005).Verification
New
tests/storage/test_live_context_summary.py:Mounted argument names: codeandMounted argument size:, and neither the mounted value nor any code fragment appears in the prompt (failed on main);abstract_max_charsis truncated at the semantic-processing gate (failed on main);tests/storage/test_semantic_processor_language.py: one fixture (_create_mock_config) now mirrors the real config'ssemantic.abstract_max_chars, which the new gate reads; suite result returns to itsmainbaseline (94 passed, the pre-existing timezone failure).