| Age | Commit message (Collapse) | Author |
|---|
|
Stage writable event-field overrides by tool call id so they can be applied at the correct point in the turn lifecycle. Capture input overrides from tool_call_complete, capture output overrides from tool_result, and clear staged overrides defensively at turn start and shutdown.
Also honor user_message text overrides when starting a turn, add the helper that applies staged overrides to the agent at dispatch boundaries, and cover the behavior with tests for staged input/output overrides.
|
|
Replace the split [tools]/[extensions] config sections and the two-stage
load gate with a single model:
- [extensions] is now one policy resolved across all layers. Rules from
every layer are kept (not clobbered) and resolved by last-match-wins
after sorting by (layer, glob specificity, deny-last), so a base layer
can carve one name out of an otherwise-denied group and a higher layer's
broad rule still wins. Default is allow; whitelist via deny=["**"].
- Registration is deferred: a source returns an entry {name, activate}
(or a list, or the sugar tool table), is always eval'd side-effect-free,
and only permitted names get activate()d. Identity is the declared name,
not the filename. Collapses the old pre/post-load two-stage gate.
- The loader runs two passes (eval -> shadow -> filter -> activate) with
precedence project>user>base and, within a layer, rocks<paths<dir.
- extensions.paths adds extra scan dirs; extensions.rocks loads luarocks
packages as extension sources (require-as-entries). Startup installs
only missing rocks (no per-launch network hit); panto update force-
(re)installs every configured rock.
deny is a feature toggle, not a security boundary: rocks is where registry
code enters, so the pin list is the trust boundary. Rock integrity
(first-party GPG signing + --verify) is designed but not yet wired; until
then rocks pins which version, not which bytes.
Breaking: [tools] is removed; extensions must return entries. Built-in
tools and the wc example keep working via the sugar tool form.
|
|
|
|
Teach provider config and auth resolution about the Codex Responses
dialect, including user-facing `style = "openai_responses"` with
`dialect = "codex"`. Serialize and parse Responses traffic with
provider-specific reasoning replay, assistant phase metadata, and robust
function-call assembly keyed by `output_index` so streamed tool inputs
survive proxy quirks and empty terminal payloads.
Also persist thinking origins and message metadata across sessions, add
the Anthropic interleaved-thinking header switch, write per-session
debug logs, and improve the TUI and scripts for inspecting tool output
and session costs.
|
|
Conversation.addUserMessage now takes a []ContentBlock (symmetric with
addAssistantMessage). Introduce a thin addUserText wrapper in agent.zig
for the plain-text case and update every call site in agent.zig and
anthropic_messages_json.zig accordingly.
|
|
|
|
|
|
|
|
Move the CLI off the internal libpanto module namespaces onto the curated
public API: data-type aliases (Config family, Message/MessageRole/
effectiveSystemBlocks, Event, Pricing/PricingRegistry, the session seam,
FileSystemJSONLStore, ContentBlockType), process lifecycle (panto.init/
deinit), and ResultParts.fromText/fromTextOwned/deinit in place of the
freestanding textResult/ownedTextResult/freeResultParts.
The CLI remains on two flagged internal namespaces, panto.agent and
panto.conversation: it is a deep embedder that drives the loop below the
curated Agent/Conversation facades (system-prompt seeding through the
agent, compaction_system_prompt, the open_stream_fn test seam, standalone
Conversation values, compactAndPersist). These stay re-exported from
public.zig as a documented deep-embedder escape hatch; trimming the
transitional block removed every other internal re-export.
|
|
|
|
|
|
|
|
Replace all references to the "system" layer with "base" to better reflect
its role as the foundational extension/tool layer in panto's hierarchy.
The layer hierarchy now consistently uses: project > user > base.
Includes:
- Update agent README and build.zig documentation
- Refactor tool registry and config module to support layered lookups
- Add TestHarness abstraction for cleaner test setup
- Improve JSON serialization with wire-encoded tool names
- Add glob pattern matching for tool/extension discovery
|
|
|
|
- bundle luarocks source in the panto binary
- bootstrap process (intended for first `panto` run):
- make ~/.local/share/panto/...
- write out luarocks sources into it
- run luarocks to install luv
- new `panto bootstrap` command just runs the bootstrap
- `panto bootstrap --force` removes everything and re-bootstraps
- new `panto lua` command just runs panto's embedded lua
|
|
|
|
- new multi-tool registration via ToolSource
- thread per source-or-standalone-tool
- switched to zig 0.16 Io threading interface
- cli: include `luv` package and run concurrent lua tools via libuv
- one single long-lived lua_State for the whole cli program
|
