7b04e6ac42
debug: add prefix template resolution logging
2026-01-14 23:15:46 -05:00
d0a4cce41e
feat: add dynamic template variables to messages.responsePrefix ( #923 )
...
Adds support for template variables in `messages.responsePrefix` that
resolve dynamically at runtime with the actual model used (including
after fallback).
Supported variables (case-insensitive):
- {model} - short model name (e.g., "claude-opus-4-5", "gpt-4o")
- {modelFull} - full model identifier (e.g., "anthropic/claude-opus-4-5")
- {provider} - provider name (e.g., "anthropic", "openai")
- {thinkingLevel} or {think} - thinking level ("high", "low", "off")
- {identity.name} or {identityName} - agent identity name
Example: "[{model} | think:{thinkingLevel}]" → "[claude-opus-4-5 | think:high]"
Variables show the actual model used after fallback, not the intended
model. Unresolved variables remain as literal text.
Implementation:
- New module: src/auto-reply/reply/response-prefix-template.ts
- Template interpolation in normalize-reply.ts via context provider
- onModelSelected callback in agent-runner-execution.ts
- Updated all 6 provider message handlers (web, signal, discord,
telegram, slack, imessage)
- 27 unit tests covering all variables and edge cases
- Documentation in docs/gateway/configuration.md and JSDoc
Fixes #923
2026-01-14 23:05:08 -05:00
fa8d9b9189
feat: add provider-specific tool policies
2026-01-15 03:55:20 +00:00
2b4a68e276
feat: load channel plugins
2026-01-15 02:42:44 +00:00
1b79730db8
style: apply oxfmt fixes
2026-01-15 01:53:14 +00:00
ad8799522c
feat(config): gate channel config writes
2026-01-15 01:41:15 +00:00
393d21d86c
Format: fix report + telegram formatting
2026-01-15 01:27:16 +00:00
232c512502
Format: apply oxfmt fixes
2026-01-15 01:27:16 +00:00
bcde09ae91
feat: add /context prompt breakdown
2026-01-15 01:06:35 +00:00
5894ffe82e
refactor(auth): streamline allowFrom normalization
2026-01-14 23:42:50 +00:00
57b4865ab3
fix(whatsapp): normalize user JIDs for group allowlists ( #838 )
...
Thanks @peschee.
Co-authored-by: Peter Siska <63866+peschee@users.noreply.github.com>
2026-01-14 23:25:42 +00:00
fd41000bc3
test(whatsapp): add context isolation coverage
...
Includes outbound gating, threading fallback, and web auto-reply context assertions.
2026-01-14 23:23:36 +00:00
e65e5f40c9
fix(whatsapp): use conversation id for context isolation ( #911 )
...
Thanks @tristanmanchester.
Co-authored-by: Tristan Manchester <tmanchester96@gmail.com>
2026-01-14 20:06:20 +00:00
c379191f80
chore: migrate to oxlint and oxfmt
...
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
2026-01-14 15:02:19 +00:00
ea018a68cc
refactor(auto-reply): split reply pipeline
2026-01-14 09:11:16 +00:00
350f4709b7
test(auto-reply): rename split suites
2026-01-14 05:40:39 +00:00
da6f07b7c1
refactor(auto-reply): split directive handling
2026-01-14 05:39:41 +00:00
bcbfb357be
refactor(src): split oversized modules
2026-01-14 01:17:56 +00:00
6fdfe8ea73
fix: finalize channels rename cleanup
2026-01-13 08:40:40 +00:00
84bfaad6e6
fix: finish channels rename sweep
2026-01-13 08:40:40 +00:00
993c1de361
fix: stabilize channel migration
2026-01-13 08:40:39 +00:00
90342a4f3a
refactor!: rename chat providers to channels
2026-01-13 08:40:39 +00:00
e8779ac329
fix: handle Anthropic overloaded_error gracefully ( #832 ) (thanks @danielz1z)
2026-01-13 08:32:06 +00:00
9faa95d558
fix: recover from compaction overflow
2026-01-13 08:03:11 +00:00
d5b17d344b
Merge pull request #722 from vrknetha/feat/slash-bash-command
...
feat(bash): add host-only /bash slash command
2026-01-13 07:18:35 +00:00
6db0201fcd
Merge pull request #583 from mitschabaude-bot/feat/agent-model-fallbacks
...
Config: per-agent model fallbacks
2026-01-13 06:54:00 +00:00
3368284b2a
fix: per-agent model fallbacks ( #583 ) (thanks @mitschabaude-bot)
2026-01-13 06:50:41 +00:00
6729637f61
Config: support per-agent model fallbacks
2026-01-13 06:50:20 +00:00
18d22aa426
fix: gate xhigh by model ( #444 ) (thanks @grp06)
2026-01-13 06:48:41 +00:00
a3641526ab
Thinking: gate xhigh by model
2026-01-13 06:48:26 +00:00
25a5f1cb96
Auto-reply: add host-only /bash + ! bash command
2026-01-13 11:54:34 +05:30
d4c205f8e1
fix: start typing on message start
2026-01-13 04:33:24 +00:00
b41e75a15d
feat: cron agent binding + doctor UI refresh
2026-01-13 04:25:41 +00:00
da95b58a2a
Typing: keep indicators active during tool runs
...
Closes #450
Closes #447
2026-01-12 22:20:29 -06:00
980f274fc9
fix: stabilize docs and tests after system event timestamps
2026-01-13 03:51:34 +00:00
d45915d39f
fix: refine group intro prompt guidance
2026-01-13 03:40:27 +00:00
fcc814accd
System events: add local timestamps in prompt injection
...
Closes #245
2026-01-12 21:38:56 -06:00
8b5cd97ceb
Add Synthetic provider support
2026-01-13 03:36:53 +00:00
c1f82d9ec1
refactor: dedupe enforceFinalTag resolution
2026-01-13 02:38:07 +00:00
4f1c6e76fd
fix: gate inline /status stripping
2026-01-13 01:53:40 +00:00
88716d8d2a
fix: harden inline /status stripping ( #766 )
2026-01-13 01:53:40 +00:00
c2e37c78ff
fix: trim sender ids before auth fallback
2026-01-13 01:53:40 +00:00
c012019a8a
fix: enforce reasoning tags on fallback providers ( #810 ) (thanks @mcinteerj)
2026-01-13 01:46:21 +00:00
7896b30489
fix(auto-reply): enforce reasoning tags on fallback providers
2026-01-13 01:40:55 +00:00
dd8f7552ad
refactor: reuse dispatcher helper for native commands
2026-01-13 01:07:59 +00:00
6f75feaeb8
refactor: reuse model selection assertions
2026-01-13 00:20:08 +00:00
3636a2bf51
refactor: unify message tool + CLI
2026-01-13 00:12:57 +00:00
ce23c70855
fix: validate Anthropic turn order ( #804 ) (thanks @ThomsenDrake)
2026-01-12 23:43:25 +00:00
bb9a9633a8
fix: align reply threading refs
2026-01-12 23:41:40 +00:00
df64771ecf
test: cover fuzzy model selection
2026-01-12 23:16:54 +00:00
daa753112c
fix: unblock auto-reply lint/typecheck
2026-01-12 23:13:39 +00:00
cf92099d40
test(auto-reply): fix heartbeat typing block reply assertions
2026-01-12 23:01:53 +00:00
a8680f9a09
fix(auto-reply): fix streaming block reply media handling
2026-01-12 22:59:36 +00:00
2e08a868a7
style: format native commands bits
2026-01-12 22:59:36 +00:00
ec5099db89
fix: pick best fuzzy model match
2026-01-12 22:59:35 +00:00
209380edf8
Merge pull request #801 from mcinteerj/fix/restore-reasoning-tag-check
...
fix(agent): restore reasoning tag enforcement for non-ollama providers
2026-01-12 22:59:13 +00:00
cf8251bb81
test: cover typing signals from block and tool streams
2026-01-12 22:55:17 +00:00
fd768334a9
refactor: fast-lane directives helpers
2026-01-12 22:34:13 +00:00
27d940f5b6
refactor: reuse streaming text normalizer across callbacks
2026-01-12 22:27:56 +00:00
7ba72aeb6c
fix: make pw download tests platform-safe
2026-01-12 22:27:19 +00:00
29b7b2068a
refactor: centralize streaming text normalization
2026-01-12 22:17:14 +00:00
f4ab057807
fix: start typing on partial deltas
2026-01-12 22:16:29 +00:00
5d83be76c9
test: cover mixed directive fast-lane
2026-01-12 21:57:10 +00:00
99fea64823
fix: fast-lane directives bypass queue dedupe
2026-01-12 21:44:19 +00:00
490cb834e5
style: italicize reasoning output
2026-01-12 21:24:36 +00:00
eceb41f6f7
fix(agent): restore reasoning tag enforcement for non-ollama providers
...
This restores the fix from PR #754 which was accidentally reverted in bf11a42c3
2026-01-13 09:47:04 +13:00
7dc44b04c1
fix: close memory index and refresh protocol outputs
2026-01-12 18:49:24 +00:00
ffbcd83d1e
chore: log elevated and reasoning toggles
2026-01-12 18:37:44 +00:00
355c13564c
fix: restore heartbeat defaults and model listing
2026-01-12 17:17:54 +00:00
f1dd59bf82
test: update heartbeat and agent list thresholds
2026-01-12 17:14:04 +00:00
bf11a42c37
feat: add memory vector search
2026-01-12 11:23:44 +00:00
a3938d62f6
chore: raise heartbeat ack window
2026-01-12 11:06:46 +00:00
562d0e3b5f
fix: avoid duplicate status replies
2026-01-12 11:04:03 +00:00
a8f67f0be6
fix: only strip inline /status for allowlisted senders
2026-01-12 08:55:02 +00:00
252841ab13
fix: enforce final tag gating ( #754 ) (thanks @mcinteerj)
2026-01-12 08:45:23 +00:00
efdf874407
fix(agent): correctly strip <final> tags from reasoning providers
...
- Added src/utils/provider-utils.ts to track reasoning provider logic
- Updated isReasoningTagProvider to loosely match 'google-antigravity' (fixes sub-models)
- Enabled enforceFinalTag in reply.ts when provider matches
- Verified <final> tag stripping logic in pi-embedded-subscribe.ts
- Updated pi-embedded-runner to use consistent provider check for prompt hints
2026-01-12 08:34:06 +00:00
3fba8ceb97
test(model): cover provider-less id fuzzy match
2026-01-12 08:02:55 +00:00
60823fd9bd
feat(model): fuzzy /model matching
2026-01-12 07:57:53 +00:00
e1150f1b93
test: expand memory flush coverage
2026-01-12 07:42:03 +00:00
d17fc7e448
fix(auto-reply): preserve inline /status text for unauthorized senders
2026-01-12 07:42:03 +00:00
097e66391f
fix(auto-reply): show config models in /model
2026-01-12 07:31:20 +00:00
7466575120
fix: ignore inline status directives
2026-01-12 07:13:08 +00:00
e19a5dc2b1
feat(control-ui): add model presets
2026-01-12 07:09:58 +00:00
1a89a5dd14
test(model): expand /model picker coverage
2026-01-12 06:34:33 +00:00
5b44825cb3
fix: skip memory flush on read-only workspace
2026-01-12 06:33:27 +00:00
1ffb0fe787
fix: handle inline status for allowlisted senders
2026-01-12 06:33:27 +00:00
46a6d79784
fix: sender fallback for command auth ( #755 ) (thanks @juanpablodlc)
2026-01-12 06:28:53 +00:00
20d606c4c4
fix: use logical OR for sender ID fallback in command auth
...
The nullish coalescing operator (??) only skips null/undefined, not
empty strings. For direct WhatsApp messages, ctx.SenderId was an empty
string, causing senderRaw to be "" instead of falling through to the
valid ctx.SenderE164 value.
This caused commands like /status to be rejected with "unauthorized
sender" for self-chat WhatsApp messages.
Tested: Verified /status command now works correctly for self-chat
WhatsApp messages after the fix.
2026-01-12 06:20:51 +00:00
c9f2358769
test: clean unused var
2026-01-12 06:14:45 +00:00
4044957819
test: fix lint warning
2026-01-12 06:14:45 +00:00
b185d130ba
test: cover inline slash command fast-path
2026-01-12 06:14:45 +00:00
0f257f792a
fix: fast-path slash commands
2026-01-12 06:10:17 +00:00
2da2057a37
feat(model): add /model picker
2026-01-12 06:02:39 +00:00
7dbb21be8e
feat: add pre-compaction memory flush
2026-01-12 05:29:18 +00:00
6a012fd625
refactor: reuse resolved think default
2026-01-12 03:00:30 +00:00
c64bcd047b
fix: flush block reply coalescer on tool boundaries
...
When block streaming is enabled with verbose=off, tool blocks are hidden
but their boundary information was lost. Text segments before and after
tool execution would get coalesced into a single message because the
coalescer had no signal that a tool had executed between them.
This adds an onBlockReplyFlush callback that fires on tool_execution_start,
allowing the block reply pipeline to flush pending text before the tool
runs. This preserves natural message boundaries even when tools are hidden.
Fixes the issue where:
text → [hidden tool] → text → rendered as one merged message
Now correctly renders as:
text → [hidden tool] → text → two separate messages
Co-diagnosed-by: Krill (Discord assistant)
2026-01-12 02:52:48 +00:00
99877e8e63
fix: align /think default with model reasoning
2026-01-12 02:50:13 +00:00
58a12a757e
fix(sandbox): avoid sandboxing main DM sessions
2026-01-12 01:24:44 +00:00
9c8967ef5d
style: biome fixes
2026-01-12 00:32:47 +00:00
67743325ee
fix: reset session after compaction overflow
2026-01-12 00:28:16 +00:00
Sebastian
Peter Steinberger
George Pickett
Gregor's Bot
vrknetha
Shadow
Travis Hinton
Keith the Silly Goose
Jake
juanpablodlc
The Admiral
Gabriel Trigo