AutoCompact.prepare_session runs on the turn hot path
(AgentLoop._compact_session) and read the persisted _last_summary metadata
with an unguarded meta['text'] and datetime.fromisoformat(meta['last_active']).
A _last_summary dict that was hand-edited or written by another version
(missing text/last_active, or a non-ISO last_active) raised KeyError/ValueError
out of the turn.
Sibling readers already tolerate the same data: estimate_session_prompt_tokens
uses .get('text') and _archive parses inside try/except. Mirror that tolerance:
skip when text is unusable, and fall back to the session's own updated_at (the
value the writer persists) when last_active is missing or unparseable, so the
archived summary is preserved instead of crashing the turn.
When an LLM response arrives with finish_reason='length' and has_tool_calls
but blank text content (e.g. the model spent its whole output budget on a
tool call whose closing tag was truncated), the runner dropped the tool
calls and then misrouted the blank response into the empty-response retry
branch. Retrying the same prompt cannot recover from output-budget
exhaustion, so every retry hit the same length ceiling and the turn ended
in the generic apology.
The length-recovery branch was gated on 'finish_reason == length and not
is_blank_text(clean)', so a blank-but-truncated turn could never reach it.
- The empty-response retry branch now excludes finish_reason == 'length'
(in addition to 'error').
- The length-recovery branch no longer requires non-blank content, so a
blank-but-truncated turn enters recovery and appends
build_length_recovery_message (which handles a blank tail safely).
Adds a regression test asserting the length-recovery path is taken; it
fails on the unfixed code and passes with the fix.
Fixes#5133
_load() treated any OSError like corruption and returned an empty store. When pairing.json was transiently unreadable, an unapproved DM could deny the sender, generate a pairing code from the empty view, and overwrite the store without its approved senders.
Keep the existing JSONDecodeError reset behavior, but propagate OSError so mutations cannot persist unreadable state. Read-only checks fail closed without writing; mutating /pairing subcommands report temporary unavailability; and the DM pairing path skips one reply instead of crashing the handler.
This mirrors the refuse-to-overwrite strategy used by the cron and trigger stores.
normalize_token_usage_state only length-checked persisted day keys, so a
hand-edited or foreign 10-char key (e.g. "not-a-dat3" or "2026-13-01") in
token-usage.json survived reads and atomic rewrites. token_usage_payload
then parsed every day key with an unguarded datetime.fromisoformat, so one
such key failed every /api/settings and /api/settings/usage request until
the file was repaired by hand.
Validate day keys in normalize_token_usage_state, the shared boundary that
every read, record, and rewrite already funnels through. Malformed keys are
dropped like other malformed rows and scrubbed from the file on the next
write; valid state is unchanged.
`porcelain.commit()` and `repo.refs[...]` hand back object ids as a
40-character hex string that is already encoded to bytes. Calling `.hex()`
on that encodes the ASCII a second time, so every id GitStore produced or
displayed was double-encoded:
auto_commit() -> '62623234'
git log --abbrev=8 -> 'bb244606'
The module is self-consistently wrong, so `/dream-log` and `/dream-restore`
work as long as the id came from nanobot itself. What does not work is
crossing the boundary: ids in logs and commit output match nothing in
`git log`, and an id copied from `git log` cannot be resolved:
_resolve_sha(own id) -> b'bb244606d780...'
_resolve_sha(real git id) -> None
Use `.decode()` at the four sites that consume dulwich object ids. Nothing
persists an id — callers either display it or resolve it live — so there is
no stored state in the old format.
Adds two regression tests: the id returned by `auto_commit` must equal
`git log --abbrev=8`, and a real git id must resolve through `_resolve_sha`.
Co-Authored-By: Claude <noreply@anthropic.com>
Windows PowerShell 5.1 defaults $OutputEncoding to US-ASCII, corrupting non-ASCII strings piped to native commands. Set it from the console encoding only on legacy versions so PowerShell 7 keeps its defaults.
Address review feedback that the capability checks were broader than the
documented per-model matrix:
- Drop the extreme aspect ratios (1:4, 4:1, 1:8, 8:1) from the Flash
allow-list. They are only documented for 3.1 Flash / Flash Lite, so the
global set could send an unsupported ratio to 2.5 Flash Image or 3.1 Pro
Image. Keep the ratios common to every Flash image model.
- Identify imageSize support positively via "gemini-3" instead of excluding
"2.5". The old predicate also matched gemini-2.0-flash-preview-image-
generation, which (with the default 1K size) altered that model's request
shape even though only Gemini 3+ image models accept a configurable size.
Add tests for the gemini-2.0 image-size drop and the extreme-ratio drop.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
