task_logs truncates at 50KB with no pagination, so full logs are unreachable #1632

Closed
opened 2026-10-27 13:41:10 +00:00 by sam · 0 comments
Owner

The task_logs chat tool caps its response at 50 KB and offers no way to fetch the rest. An operator asking the agent to retrieve or archive a task's logs gets a silently clipped window, and the agent has no mechanism to page past it. Observed 2026-08-24: asked to save a full transcript and agent logs, the agent could only produce a partial archive and had to document the truncation as a limitation rather than satisfy the request.

The failure compounds with archie-core-p1bl (errors logging as {}): a truncated log of uninformative errors leaves an operator with nothing at all, precisely when a task is stuck.

What is needed

Truncation itself is legitimate -- a tool result must be bounded, and unbounded log text would blow the model's context. The defect is that truncation is TERMINAL: there is no continuation, no offset/cursor, no way to narrow the window, and the caller cannot tell how much was lost.

Establish first where the cap is applied (the task_logs tool in internal/gateway/task_tools.go and whatever log reader it calls in internal/logging -- note internal/logging owns the on-disk format end to end and internal/webui parses nothing, per CLAUDE.md, so the reader is the right place for range support).

Design points to decide:

  • A cursor or offset so successive calls walk the whole log, rather than always returning the same head or tail.
  • Filters that make bounded retrieval useful rather than merely possible: by level (errors only), by time range, by stage.
  • The response must state explicitly that it was truncated and how much remains, so the agent can report honestly instead of implying completeness.
  • Consider whether bulk retrieval belongs in a tool result at all, or whether the right answer for "save the full logs" is to write the file and deliver it via the new send_file path (archie-core-absb), keeping the tool result small.

Acceptance Criteria

An operator can obtain a task's complete logs through the agent, by paging or by file delivery; a truncated response says so and reports what remains rather than ending silently; level and time-range filtering exist so a bounded call can still answer a specific question; the cap remains enforced so no single response can exhaust the model's context; tests cover a log larger than the cap and assert that repeated calls retrieve all of it without gaps or duplication.

Close reason

task_logs cursor pagination, level/time filters, and honest truncation reporting


Imported from beads archie-core-vq92 · GitHub #625 · type bug · priority P1 · created 2026-08-24 · closed 2026-08-25

The task_logs chat tool caps its response at 50 KB and offers no way to fetch the rest. An operator asking the agent to retrieve or archive a task's logs gets a silently clipped window, and the agent has no mechanism to page past it. Observed 2026-08-24: asked to save a full transcript and agent logs, the agent could only produce a partial archive and had to document the truncation as a limitation rather than satisfy the request. The failure compounds with archie-core-p1bl (errors logging as `{}`): a truncated log of uninformative errors leaves an operator with nothing at all, precisely when a task is stuck. ## What is needed Truncation itself is legitimate -- a tool result must be bounded, and unbounded log text would blow the model's context. The defect is that truncation is TERMINAL: there is no continuation, no offset/cursor, no way to narrow the window, and the caller cannot tell how much was lost. Establish first where the cap is applied (the task_logs tool in internal/gateway/task_tools.go and whatever log reader it calls in internal/logging -- note internal/logging owns the on-disk format end to end and internal/webui parses nothing, per CLAUDE.md, so the reader is the right place for range support). Design points to decide: - A cursor or offset so successive calls walk the whole log, rather than always returning the same head or tail. - Filters that make bounded retrieval useful rather than merely possible: by level (errors only), by time range, by stage. - The response must state explicitly that it was truncated and how much remains, so the agent can report honestly instead of implying completeness. - Consider whether bulk retrieval belongs in a tool result at all, or whether the right answer for "save the full logs" is to write the file and deliver it via the new send_file path (archie-core-absb), keeping the tool result small. ## Acceptance Criteria An operator can obtain a task's complete logs through the agent, by paging or by file delivery; a truncated response says so and reports what remains rather than ending silently; level and time-range filtering exist so a bounded call can still answer a specific question; the cap remains enforced so no single response can exhaust the model's context; tests cover a log larger than the cap and assert that repeated calls retrieve all of it without gaps or duplication. ### Close reason task_logs cursor pagination, level/time filters, and honest truncation reporting --- _Imported from beads `archie-core-vq92` · GitHub #625 · type bug · priority P1 · created 2026-08-24 · closed 2026-08-25_
sam added the highbug labels 2026-10-27 13:41:10 +00:00
sam self-assigned this 2026-10-27 13:41:10 +00:00
sam closed this issue 2026-10-27 13:41:10 +00:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: sam/archie#1632