`ToolOutput` pairs the model-facing text with the images a tool produced.
`ToolRegistry.execute` keeps its text-only contract; `execute_output` returns
the pair and the loop stores the images on the tool message, so a screenshot
tool can answer in pixels instead of a hex placeholder.
Only the text is capped by the tool-result limit; the char estimator now counts
a present image at its 1024-token ceiling, because the shrinkers never drop one.
A user turn's `content` may now be a part array (`ChatTextPart` +
`ChatImagePart`), which chat completions take as-is; the Anthropic and
Responses bridges translate it into `image` blocks and `input_image` parts.
A tool result keeps its text in `content` and carries `images` beside it:
Anthropic and Responses put them in the result item itself (a live probe reads
both back), while chat completions cannot, so
`compat.chat_messages_with_images` moves them into the user turn after the tool
run. Prose-only readers go through `content_to_text`, which renders an image as
`[image]`.
`agent.images` sniffs the real format from the bytes and builds the data URL,
capped at 8 MiB inline because every stored message is re-sent on each round.
ToolRegistry.prepare_batch_confirm pre-scans a round of tool calls, drops the ones that cannot run (unknown tool, undecodable arguments, missing required argument), and turns two or more soft reasons into a single ToolBatchConfirmHook prompt. The BatchConfirmDecision it returns is applied per call through execute(..., decision=...): allow, or deny with one comment shared by every call of that round.
_execute_tool_calls asks before it gathers, so a batch of moves or deletes no longer stacks one confirm box per call. A single request keeps the old one-call prompt, a host without a batch hook keeps the per-call behaviour, and the answer never outlives the round it was asked in.
Streaming is the default path: `thinking` fragments, a `server_tool_use`'s `partial_json` query and a `web_search_tool_result`'s entries arrive as separate SSE events, so the blocks the round has to hand back exist only as fragments. The dispatch rebuilds each one from its start payload (field for field, under the stream's own names) plus the fragments that follow, and passes it to the loop as a chunk; the loop copies it onto the round's message, where a round that kept only those blocks counts as payload rather than an empty completion.
The thinking text streams as reasoning as it arrives — the search query and the signature go back with the round only.
DeepSeek's Anthropic compat answers a hosted search inside the turn: the response carries the `thinking` that picked the query, the `server_tool_use`, and the `web_search_tool_result`. The response mapping kept text and tool_use only, so the round lost its evidence — and the `thinking` signature, which only the provider can verify, could not go back at all. `AssistantChatMessage.provider_blocks` carries those blocks as raw JSON now (`thinking` text *and* signature, the query, the result entries with an `encrypted_content` the API rejects when trimmed) and the assistant turn hands them back first, ahead of its text and tool_use blocks; `thinking` also lands in `reasoning_content`, so the chain of thought streams as reasoning like every other surface's.
`AnthropicRawContentBlock` names the provider fields a streamed block carries, and `AnthropicServerToolUseContent` keeps the `caller` metadata the wire sends.
DeepSeek's Responses stream sends ``response.reasoning_text.delta`` fragments and then ``response.reasoning_text.done`` carrying the whole chain of thought those fragments spelled out. The loop folded a full delta into the round — it replaces the fragments, and that is what the assistant message hands back to the API — but streamed every delta verbatim, so the chain of thought was printed twice: once as it arrived and again as the ``.done`` text.
A full delta now streams only a tail the fragments did not cover, and nothing at all when it merely repeats them; a round whose fragments never arrived still streams the full text once. The message keeps the complete text either way.
The compat opens with the question alone (``message_start`` reports 165 tokens)
and puts what the search then pulled in on ``message_delta`` (12468); merging
preferred the earlier value, so the CLI's context gauge and the auto-compact
threshold ran ~12k short of the request. The larger of the two wins now (output
tokens are the delta's cumulative count either way).
DeepSeek's Anthropic compat runs a hosted ``web_search`` itself and answers with
the blocks that search produced — ``thinking``, ``server_tool_use`` (the query)
and ``web_search_tool_result`` — so the content union that knew only text and
tool_use could not decode a live search turn. It carries them now, ``tools``
accepts the opaque server-tool dicts the surface declares, and
``web_search_tool_result.content`` stays loose on purpose: its
``web_search_result`` entries hold an ``encrypted_content`` the API demands back
unchanged (a trimmed result is answered with 422 "missing field
``encrypted_content``").
``provider_tools`` reached only the Responses surface, and the Anthropic one
wants its own definition of the same intent: a bare ``web_search`` becomes
``{type="web_search_20250305", name="web_search"}`` (the server tool Claude
declares and DeepSeek's compat reads, keeping a ``max_uses`` cap or any other
key), merged after the local function tools.
Such a tool is the server's: it streams ``input_json_delta`` fragments like a
call, and reading them as one asked the registry for a tool the server had
already run. Block types are now tracked, so only a ``tool_use`` block becomes a
tool call; the search blocks and ``thinking`` are skipped by the response
mapping (the answer the model wrote already used them) and never executed.
A request carrying `tools` must return every round's chain-of-thought — "必须完整
回传 `reasoning_content` … 即使该轮模型未实际进行工具调用" — and the API merges a
`reasoning` item into the assistant message its round forms: a missing item and
an empty `reasoning_text` are both answered with "The `reasoning_text` in the
thinking mode must be passed back to the API". Each round now goes back as its
reasoning, its text, then its calls, with a blank line standing in when the
round kept none (a `rollback_tail` carrier, a forged todo call, the seed a
compacted session starts with) — never words of the bridge's own for a round
that may genuinely have reasoned nothing. A round's calls stay contiguous ahead
of their outputs: an interleaved batch reads as a second round without
reasoning and is rejected the same way, and an output recorded after another
item moves up beside its own call.
The reasoning is read back from the item's `content` parts, the only part the
API documents for `reasoning` items (`summary` and `encrypted_content` are not
supported).
A failed turn keeps the calls that already ran as a bare pairing carrier, and
clipping the chain-of-thought off that carrier sent the call back to the API
with no reasoning at all — thinking mode refuses a call whose reasoning never
came back. The carrier keeps the reasoning and drops only the text.
DeepSeek dropped the `v4` prefix from its flash model, and the old id stays
valid only as a compatibility alias. Seed the default catalog with the current
name so a provider that omits `models` no longer offers a deprecated id, and
follow the rename in the wire fixtures and the minimal config template. An
explicit `deepseek-v4-flash` in TOML still passes through unchanged.
A caller that goes away mid-batch (cancel, display error) left the results of
tools that had already run out of history, so the retry ran them again. Append
the collected results first, then emit the events.
A tool batch counted as committed only once every call had its result, so a
batch cut short was dropped whole and the retry ran tools that had already
had effects. Keep the calls that did report a result: their assistant row
stays as the pairing carrier (a request must answer every tool_calls id),
without the text of the unfinished turn, and the calls without a result are
absent so the retry re-issues them instead of assuming they ran. The kept
rows go to the store right away, and a failed rollback write is not allowed
to mask the failure being rolled back.
/btw now defaults to --tools=read: the side turn gets only READ_ONLY
tools under a read-only context (fetch restricted to GET), with the main
session view so read-only reads (todo_list) see real state. --tools=full
keeps the previous whole-registry clone with a fresh session; --tools=no
turns tools off. When tools are off, the default read silently falls back
to no tools, while an explicit --tools read|full errors as before.
Adds 7 unit tests for _synthetic_todo_pair_after and committed_prefix_end
with synthetic todo nag pairs: survival across rollback, detection at
correct index, immunity to real tool calls, and multiple rollbacks.
These directly verify the guard that prevents duplicate turn-start
nag injection on /retry when a synthetic pair from a previous failed
attempt survived rollback (committed tool batch).
NCBM