ciregenz and Claude Fable 5.1
383c04b0e2
[eric] agents: the rebuild recap's tool trail is bounded, so a 766-call chat restarts at 78K tokens instead of 192K and the CLI stops compacting on its first step
...
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_012G8kyALnPjsA7aJFmMBq3R
2026-09-01 18:14:32 -07:00
ciregenz and Claude Opus 5
b133ef7a1a
[eric] agents: a pruned recap says it is partial, and the prune that reclaimed the history is counted
...
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01U6zrBsUCNzpMBnov3rTVYV
2026-08-29 11:17:38 -07:00
ciregenz and Claude Opus 5
2e8d431118
[eric] agents: a run's result is not a replay, so the final answer survives the trail (ENG-396)
...
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_018foyDoK19jjbYdudfzQVkZ
2026-08-24 11:16:06 -07:00
ciregenz and Claude Opus 5
5d3eb5cc52
[eric] agents: no renderer bound for a model replays another agent's turns (ENG-396)
...
Four paths still emitted the USER:/ASSISTANT: shape ENG-358 removed from the recap, because they were tool results and aux calls rather than the recap.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_018foyDoK19jjbYdudfzQVkZ
2026-08-24 10:30:36 -07:00
ciregenz and Claude Opus 5
626d9ea4dd
[eric] agents: bound what one tool result costs the model, without ever deleting the answer (ENG-385)
...
The 50KB cap shaped our own transcript copy, never the model's context, so it could not have cut a token at any threshold.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_018foyDoK19jjbYdudfzQVkZ
2026-08-24 00:45:37 -07:00
ciregenz and Claude Fable 5
a4be8c469f
[eric] agents: the recap carries no model text, nudges are short and unlabeled (ENG-358)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01En8dRGsJPLrJCQBEkTH4Mp
2026-08-21 00:20:04 -07:00
ciregenz and Claude Fable 5
295a7b52e2
[eric] agents: a policy block ratchets the recap down instead of bricking the chat (ENG-358)
...
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01En8dRGsJPLrJCQBEkTH4Mp
2026-08-20 23:44:44 -07:00
ciregenz
108287eda4
[eric] agents: provider content-policy blocks are terminal (no snag flicker), recap-bearing sessions get ONE recap-free retry, and the recap reads first-person instead of a User:/Assistant: transcript that trips distillation filters (Alex's bricked chats)
2026-08-19 14:07:29 -07:00
ciregenz
6a1dbc4212
[eric] agents: recap ages history hermes-style instead of dropping it; stubs keep the re-runnable command, duplicates collapse, newest results survive verbatim (ENG-354 endgame)
2026-08-19 13:40:47 -07:00
ciregenz
b29c75d5e0
[eric] agents: crossing the compact threshold now actually trims next turn, and a pasted log can't ride the recap back over the wall
2026-08-03 15:47:18 -07:00
ciregenz
e10bd2ed9d
[eric] tool-results: middle-elide oversized spills so the tail (where the verdict lives) survives
2026-07-31 01:17:14 -07:00
ciregenz
9da027a948
[eric] context: distill dropped history via aux LLM on rebuild + model-aware compaction threshold
2026-07-06 15:25:58 -07:00
ciregenz
d5cd4db026
[eric] agents: one-line every comment + collapse 3+ blank runs across manager/ surface (33 files, -550 lines, code byte-identical)
2026-06-25 02:16:14 -07:00
ciregenz
dc53394e55
[eric] agents: drop dead typing.Dict imports + dangling _conns ref (caught by ruff/pyright audit, behavior-preserving)
2026-06-24 23:26:37 -07:00
ciregenz
0f4dbd5769
[eric] agents: @typechecked the 4 history_compaction helpers (close audit gap, surface 90->93%)
2026-06-24 22:59:06 -07:00
ciregenz
6561dd6743
[eric] agents: convention fixes on merge surface (public cross-file helpers, pydantic approval memory, resolve_ask @typechecked)
2026-06-24 22:36:17 -07:00
ab6037267c
[aidan] fix/agent-chat: stop agents reading the recap as spoofed tool output ( #104 )
...
* [aidan] fix/agent-chat: ground fresh-session recap and label platform notes as trusted
* [aidan] fix/mcp-activate: fork on activate instead of fresh-session restart
* [eric] agents: add strip_forged_sentinels, defang spoofed platform-note/recap tags in untrusted text
* [eric] agents: sanitize untrusted tool output in post_tool_hook before trusted notes append
---------
Co-authored-by: cire <134991075+ciregenz@users.noreply.github.com >
2026-06-24 18:40:15 -07:00
ciregenz
027c6ac311
[eric] agents: history_compaction convention-clean (4 funcs off leading-_, typing, @typechecked)
2026-06-23 12:08:05 -07:00
Aidan
7b88be7003
[aidan] ui/ux: hide noisy memory/mode from chat title, fix token bug
...
Drop the inline 'Memory N% full' pill from AgentChat and the mode label from AgentCard so the chat header stays quiet until tools are connected. Backend now emits agent:context_update after compact and clear so the session token counters reflect the trimmed history instead of stale pre-compact totals, with a new _estimate_post_compact_input helper and matching invariants in test_v2_invariants.
2026-06-13 00:40:19 -07:00
eric
ecf348f9cb
[eric] fix: autocompact now actually trims the model's history instead of just showing a marker
2026-05-31 18:00:39 -07:00
ciregenz
4e9f5ceb07
[eric] tree: group agent_manager helpers under agents/manager session and prompt
2026-05-23 13:08:01 -07:00
