big cli/tui gaps project

2026-07-05T22:23:49Z

Stage and apply event-field overrides at tool lifecycle boundaries

2026-07-03T18:10:09Z

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.

Load extensions via unified policy, entry/activate, rocks and paths

2026-07-01T21:37:04Z

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

ponytail simplifications to panto cli and lua extensiosn

2026-06-23T16:53:26Z

display fixes: markdown rendering, tool-specific components

2026-06-16T17:17:14Z

model registry sync via models.dev

2026-06-15T22:15:10Z

Add Codex Responses support and session debugging

2026-06-15T21:08:32Z

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.

auth: turn-time resolution in the TUI (inline login + 401 retry)

2026-06-15T21:08:32Z

Resolve the active provider's auth before each turn via the AuthManager, rendering an inline device-code prompt when login is needed, and force a single refresh/exchange retry on a provider auth failure. Wire the manager through RunOptions from main.zig.

auth: CLI auth manager + `panto auth` subcommands

2026-06-15T21:08:32Z

Add src/auth_manager.zig (turn-time resolution: load→login→refresh→exchange→ build credential, patch live config) and `panto auth status|login|logout` subcommands with a line-based device-code presenter. Add config_file.loadFromString.

fuzzy selectors for models and reasoning levels

2026-06-12T17:06:18Z

pantograph.git/src/main.zig, branch main

big cli/tui gaps project

Stage and apply event-field overrides at tool lifecycle boundaries

Load extensions via unified policy, entry/activate, rocks and paths

ponytail simplifications to panto cli and lua extensiosn

display fixes: markdown rendering, tool-specific components

model registry sync via models.dev

Add Codex Responses support and session debugging

auth: turn-time resolution in the TUI (inline login + 401 retry)

auth: CLI auth manager + `panto auth` subcommands

fuzzy selectors for models and reasoning levels