hermes-agent/agent
Honghua Yang 3128d9fcd2 fix(context_compressor): keep tool-call arguments JSON valid when shrinking
Pass 3 of `_prune_old_tool_results` previously shrunk long `function.arguments`
blobs by slicing the raw JSON string at byte 200 and appending the literal
text `...[truncated]`. That routinely produced payloads like::

    {"path": "/foo.md", "content": "# Long markdown
    ...[truncated]

— an unterminated string with no closing brace. Strict providers (observed
on MiniMax) reject this as `invalid function arguments json string` with a
non-retryable 400. Because the broken call survives in the session history,
every subsequent turn re-sends the same malformed payload and gets the same
400, locking the session into a re-send loop until the call falls out of
the window.

Fix: parse the arguments first, shrink long string leaves inside the parsed
structure, and re-serialise. Non-string values (paths, ints, booleans, lists)
pass through intact. Arguments that are not valid JSON to begin with (rare,
some backends use non-JSON tool args) are returned unchanged rather than
replaced with something neither we nor the provider can parse.

Observed in the wild: a `write_file` with ~800 chars of markdown `content`
triggered this on a real session against MiniMax-M2.7; every turn after
compression got rejected until the session was manually reset.

Tests:
- 7 direct tests of `_truncate_tool_call_args_json` covering valid-JSON
  output, non-JSON pass-through, nested structures, non-string leaves,
  scalar JSON, and Unicode preservation
- 1 end-to-end test through `_prune_old_tool_results` Pass 3 that
  reproduces the exact failure payload shape from the incident

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 12:40:56 -07:00
..
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
anthropic_adapter.py fix(agent): downgrade xhigh→max on Anthropic pre-4.7 adaptive models 2026-04-16 12:00:56 -07:00
auxiliary_client.py fix(kimi): force fixed temperature on kimi-k2.* models (k2.5, thinking, turbo) (#12144) 2026-04-18 09:35:51 -07:00
bedrock_adapter.py feat: native AWS Bedrock provider via Converse API 2026-04-15 16:17:17 -07:00
context_compressor.py fix(context_compressor): keep tool-call arguments JSON valid when shrinking 2026-04-18 12:40:56 -07:00
context_engine.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
context_references.py fix(agent): preserve quoted @file references with spaces 2026-04-10 13:05:01 -07:00
copilot_acp_client.py fix: handle httpx.Timeout object in CopilotACPClient (#11058) 2026-04-16 12:05:11 -07:00
credential_pool.py fix(auth): restore --label for hermes auth add nous --type oauth 2026-04-17 19:13:40 -07:00
display.py fix: remove context pressure warnings entirely (#11039) 2026-04-16 06:44:23 -07:00
error_classifier.py feat: native AWS Bedrock provider via Converse API 2026-04-15 16:17:17 -07:00
gemini_cloudcode_adapter.py fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833) 2026-04-17 15:34:12 -07:00
google_code_assist.py fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833) 2026-04-17 15:34:12 -07:00
google_oauth.py feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) 2026-04-16 16:49:00 -07:00
insights.py fix(insights): hide cache read/write and cost metrics from display (#11477) 2026-04-17 01:02:06 -07:00
manual_compression_feedback.py fix(gateway): make manual compression feedback truthful 2026-04-10 21:16:53 -07:00
memory_manager.py feat(honcho): context injection overhaul, 5-tool surface, cost safety, session isolation (#10619) 2026-04-15 19:12:19 -07:00
memory_provider.py refactor(memory): drop on_session_reset — commit-only is enough 2026-04-15 11:28:45 -07:00
model_metadata.py fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833) 2026-04-17 15:34:12 -07:00
models_dev.py feat: add Ollama Cloud as built-in provider 2026-04-16 02:22:09 -07:00
nous_rate_guard.py fix: Nous Portal rate limit guard — prevent retry amplification (#10568) 2026-04-15 16:31:48 -07:00
prompt_builder.py fix(skills): use frontmatter name in skills index instead of directory name 2026-04-17 18:56:37 -07:00
prompt_caching.py fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter 2026-03-21 16:54:43 -07:00
rate_limit_tracker.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
redact.py fix(security): add JWT token and Discord mention redaction (#10547) 2026-04-15 16:08:52 -07:00
retry_utils.py feat(agent): add jittered retry backoff 2026-04-08 00:41:36 -07:00
skill_commands.py fix: use absolute skill_dir for external skills (#10313) (#10587) 2026-04-15 17:22:55 -07:00
skill_utils.py feat(plugins): namespaced skill registration for plugin skill bundles 2026-04-14 10:42:58 -07:00
smart_model_routing.py fix: UTF-8 config encoding, pairing hint, credential_pool key, header normalization (#7174) 2026-04-10 05:33:48 -07:00
subdirectory_hints.py fix(agent): catch PermissionError in subdirectory hint discovery 2026-04-09 03:10:30 -07:00
title_generator.py fix: title_generator no longer logs as 'compression' task 2026-04-12 04:17:18 -07:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
usage_pricing.py feat: native AWS Bedrock provider via Converse API 2026-04-15 16:17:17 -07:00