feat: tool truncation + auto-compaction to bash harness

[mikasenghaas]

Summary

• add an optional CompactionConfig to the bash harness: compact into a handoff summary at summarize_at_tokens, or when 16k tokens remain below the model context window
• the program discovers the window itself from the provider's /models card (via models.list()), so the interception server gains a stateless GET /v1/models relay (one route serves every dialect)
• truncate a tool result over 20KB to its head and tail with a warning naming the original size
• compact reactively on an attributed 400/413 overflow error, from the current state; a rejected checkpoint falls back to the last state that passed a threshold check (which holds a full reserve of room by definition), and an empty or tool-calling reply is resampled
• after three failed checkpoint attempts the program ends the run cleanly — still a trainable sample
• an overflow with no history beyond the task propagates: nothing to reclaim

The RLM harness gets the same policy in #2459, stacked on this PR so this one can merge before nano-rlm does. Together with #2453 (merged) and #2459 this supersedes #2448.

Breaking

• None on its own: compaction is a new optional field, unset by default.

Verification

• uv run pytest -q tests/v1 — passed; live E2E tests skipped without PRIME_API_KEY

• Tool truncation checked by exact match: a synthetic 55KB output produces the byte-identical expected head/tail + warning header; short outputs pass through untouched.
  Terminal-Bench 2 e2e: 8 tasks, local vLLM poolside/Laguna-XS-2.1 at 32k (glm45 reasoning + glm47 tool parsers), compaction = {} so the threshold auto-discovers to 32768 − 16384 = 16384. Trace analysis:

• 8/8 rollouts end ok=true with scoring run (1 solved); no harness errors, no truncation stops.

• The threshold triggers exactly where designed: 7/8 episodes compacted with peak contexts of 17.0k-23.4k tokens; the one episode that stayed at 15.4k never compacted.

• 20KB tool truncation visible in 3 episodes' traces (Warning: truncated output with original size).

• Laguna puts its entire checkpoint reply in the reasoning channel, so under the summaries-are-content-only rule every compaction on this model exercises the failure path end to end: three resampled checkpoint attempts, then the program ends the run cleanly - the rollout stays a trainable sample. Summary carry-over itself was demonstrated on models that answer in the content channel (Qwen3-0.6B at 4k/8k, deepseek-v4-flash on tb2): every non-final branch ends with the checkpoint prompt followed by the summary, and the next branch opens with [system, framed summary].

• A final combined verification run on a content-channel model is pending.

🤖 Generated with Claude Code

---

Note

Medium Risk
The shared agent loop now permanently truncates large tool outputs and, when compaction is enabled, replaces long histories with model-generated summaries—both can change task outcomes; the new models relay is ancillary and failures only disable auto-thresholds.

Overview
Adds an opt-in context compaction path for the bash agent: BashHarnessConfig gains CompactionConfig (summarize_at_tokens optional), which forwards --compaction / --summarize-at-tokens into the shared minimal/bash chat program.

When compaction is on, the program uses a new Compactor to compact before context blows up: it can trigger on usage crossing a threshold (explicit token limit, or auto from the model card with a 16k reserve), on finish_reason=length, on post-tool estimated token growth, or reactively on provider 400/413 overflow. Compaction asks the model for a plain-text handoff summary (tool_choice=none), rebuilds history as system + framed summary user message, falls back to the last “good” checkpoint on overflow, and ends the loop cleanly on CompactionFailed instead of crashing. Threshold discovery calls models.list() against the intercepted base URL.

Tool results are always middle-truncated at ~20KB (head/tail + warning) via bound_tool_message before they enter the transcript, including interception rewrites.

The interception server adds GET /v1/models as an authenticated upstream relay (30s timeout) so the in-container SDK can read provider context-window fields without recording a model turn.

^{Reviewed by Cursor Bugbot for commit e1c80ac. Bugbot is set up for automated code reviews on this repo. Configure here.}

Note

Add tool truncation and auto-compaction to BashHarness agent loop

• Adds CompactionConfig to BashHarnessConfig and passes --compaction and --summarize-at-tokens flags to the spawned program in harness.py
• Introduces the Compactor class in program.py that detects context exhaustion, builds a summary checkpoint, and rebuilds the conversation; auto-discovers a token threshold from the provider's /v1/models endpoint when none is given
• Truncates large tool outputs to TOOL_OUTPUT_MAX_BYTES (20,000) with head/tail preservation via truncate_tool_output before they enter the conversation
• Proxies GET /v1/models through the interception server in server.py so the program can query the provider for context window size
• chat() now returns the full completion object instead of the first message, and the main loop ends cleanly on CompactionFailed
• Risk: chat() signature and return type changed in program.py; any callers expecting the first message instead of the full completion will break. Tool outputs over 20,000 bytes are silently truncated mid-conversation.

^{Macroscope summarized 27e1c91.}

[macroscopeapp]

Approvability

Verdict: Not approved

Macroscope's review found this PR not approvable — This PR adds a stateful context-compaction workflow and a new provider-model relay, while unconditionally truncating large tool results in the shared Bash/Null loop. These changes can alter rollout context and completion behavior across production paths, so human review is appropriate.

^{You can add or adjust custom eligibility rules. Learn more.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

Want reviews to match your repository better? Bugbot Learning can learn team-specific rules from PR activity. A team admin can enable Learning in the Cursor dashboard.

^{Reviewed by Cursor Bugbot for commit 994a146. Configure here.}

[hallerite]

mostly lgtm, small nit