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
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
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:
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