LLMRagent 0.8.2
LLMRagent requires LLMR 0.8.14 or later. An agent never runs a tool call whose arguments are not a JSON object, nor any call in a reply cut off by the output-token limit: the model receives an error result and can call the tool again, as with
LLMR::call_llm_tools(). Agents with a finite budget, tool guardrails, or an approval-gated tool used to run such a call with the tool’s default arguments, and the approval gate showed the reviewer an empty argument list that approving would run. A refused call appears in the tool view with status"refused", does not pause for approval, and does not count towardmax_tool_callsoragent$usage()$tool_calls; the calls LLMR’s own loop refused used to be counted. A checkpoint shows the argument text as the model sent it, andapprove_tool_call()raises an error when asked to approve a call, from a checkpoint saved by an earlier version, whose arguments do not parse.agent_experiment()refuses design columns namedrep,result,error, orduration, which it used to overwrite, and accepts only a positive whole number forreps, naming the value it refuses (“repsmust be one positive whole number, not 2.7.”). It used to runreps = 2.7as 2 replications andreps = 0or-2as 1, andreps = Inffailed with an unrelated error fromseq_len(). Converting an experiment withas_agent_run()records the status of every cell in acellsartifact and warns when cells contributed no events; failed cells and cells that returned plain values used to vanish from the converted run. The run’s design reports the number of converted cells asn_converted. The manifest hash leaves that count out, so an experiment’s hash is the one 0.8.1 computed for it.check_state_leakage()reportsclean = NA, with a warning and the list of unexamined cells, when no leak is found but some cells could not be examined. It used to reportclean = TRUE, including for experiments whose cells return reply text and therefore expose no agents at all.archive_agent_study()never copies a whole live audit log into an archive. It used to do so when the run had no request hashes or the log could not be read, which put other studies’ requests and replies intocalls.jsonl, even withinclude_messages = FALSE. Records are matched on response id as well as request hash, which keeps an earlier identical request out, and a privacy option that cannot be applied removes the copied records. When a response id is missing, or more records match than the run made calls, a warning says that an earlier identical request can be among the copied records; such duplicates used to be copied without notice.agent_robustness()counts a failed measurement (an error,NA, or a non-scalar value frommeasure) as a failed cell, records it inmeasure_error, and warns; such cells used to vanish while the failure rate stayed at zero. With nothing measured, the summary is one row withfragile = NA, and the dispersion isNA, where it used to be 0. Agreement across an axis now uses every replicate; with two or more axes it used only the first replicate of each unit and level. A paraphrase shortfall warns, and no usable paraphrase is an error.vary_option_order()hasseed = NULLby default. A"random"option order is then drawn from the session’s random number stream, soset.seed()beforeagent_robustness()makes the orders reproducible, and each cell and replicate gets its own permutation. A fixed seed of 110 used to be applied unless another was given, so every cell saw the same permutation whatever the session’s seed. A supplied seed still gives every cell the same permutation and leaves the session’s random number state as it was;seed = 110reproduces the orders of 0.8.1.A failed
agent_fanout_synthesis()worker becomes a failed call in the converted run, with its error and request hash; it used to have no call record, so diagnostics reported no failures. A strong-model call whose request hash cannot be computed is recorded without one, with a warning, instead of being dropped.replay_run()raisesllmragent_replay_mismatchwhen a replay finishes before reaching the end of the recorded run; such a replay used to pass. A recorded log line that is not valid JSON, or a missing input snapshot, now stops the replay; the line used to be dropped and the input replaced by an empty state.A completed conversation, preset, or pipeline records its agents’ tools, generation parameters, and memory when it closes. Its manifest and state view used to read them from the live agents, so changing or reusing an agent afterwards rewrote the earlier run’s record. A bare
Agentremains a live view.diagnostics()reportsNA, with a warning naming the level and the reason, for every figure that depends on a level of the run it cannot read, and it adds a columnn_unknown_tokens, the number of calls, failed ones included, whose sent, received, or total token count is missing. It used to report zeros in both cases, so a run whose call records could not be read showed no calls and no failures, and a provider that reported no usage showedtokens_total = 0. The count followsLLMR::llm_usage()in LLMR 0.8.14: a total counts as known when both parts are, and skipped rows and batch follow-on rows are not counted;agent_manifest(),report(), andview_run()use the same rule.duration_sisNA, where it used to be 0, when calls exist but none recorded a duration.agent_manifest()addsmodels_basis(whether the model list came from the call records or from the participating agents) andn_unknown_tokens, both outside the hash. When the call records cannot be read it warns and reportsn_callsand the token sums asNA; it used to report 0 calls and take the model list from the participants without saying so.The call level of a run (
tibble::as_tibble(run, "call")) raises an error naming the event when a call event has no readable response record; such events used to be left out, so the run seemed to have made fewer calls. Records written under different LLMR versions are bound by column name, a column missing from some records being filled with missing values of the type the others use; they used to fail to bind, and diagnostics then showed no calls. Column types that cannot be combined are an error.When a reply arrives but its call record cannot be built, an agent or
agent_fanout_synthesis()keeps the reply and its usage, warns (“The reply was received, but its call record could not be constructed.”), and records the exchange as an event with status"unrecorded"and the reason in its note. Such an exchange used to appear as a successful event without a call row, or, for fan-out workers and strong-model calls, to vanish from the converted run.agent$usage()addsn_unknown_usage, the number of model calls and embedding operations whose sent or received token count was not reported;save_agent()and approval checkpoints keep it. Unreported usage still adds nothing to the token totals, but it used to leave no trace. Once such a call has occurred, an agent with a finitemax_tokenswarns before each call that the limit is checked against recorded tokens only. Agents saved by earlier versions load withn_unknown_usage = NA.report()says in its text when the call records could not be read or some calls did not report their full usage, and warns when the methods paragraph or the claim-language check could not be produced. It used to print “Methods paragraph unavailable (no call records)” for every such failure and to skip a failed claim-language check without notice.view_run()shows the reason in place of a table it cannot build, where it used to show an empty table, and marks token totals that are unavailable or incomplete.-
archive_agent_study()reports the files it could not write: the result addswrite_failures, a table of file and error, and one warning (“Some archive files could not be produced.”) lists them. A failed file is removed rather than left in place. The function used to writemanifest.jsonas[]when the manifest could not be built, write an empty table for a level it could not read, drop a failedevents.jsonlwithout notice, and listhashes.sha256and print “sealed by hashes.sha256” even when the seal had not been written. The seal is now listed only when written, over the final bytes of every listed file;README-methods.mdsays when the call records could not be read; andn_callsisNAin that case, where it used to be- Two conditions are errors: a destination directory that cannot be created, and a failed output that cannot be removed.
In a workflow, an edge predicate that raises an error ends the run with status
"failed", records the error inrun.jsonl, and returns it in the run’serrorfield, naming the edge. Such a predicate used to count asFALSE, so a run could end"done"after a broken predicate with nothing recorded.resume_workflow()then retries the edge selection without running the completed node again. A predicate that returnsFALSEorNAstill leaves its edge untaken.resume_workflow(),fork_workflow(), andreplay_run()order state snapshots by step number; they used to sort the file names as text, which misplaced steps beyond 999.persona_audit()sends each persona brief to the judge. Its model layer used to send only the scoring instructions, so the caricature and essentialism scores did not depend on the brief being scored. A score the judge does not produce (the call failed, or the reply held no number in [0, 1]) isNAwith the reason innotes, and the function warns (“The model layer could not produce … score(s)”); such a failure used to leavenotesempty and read like a model layer that never ran. Scores outside [0, 1] are nowNA.diagnostics()of an audit addsn_model_failures.
LLMRagent 0.8.1
CRAN release: 2026-07-27
- Fixed archive privacy, pre-execution tool guardrails, per-round budgets, and governed-tool limits; kept only the supported user functions.
- Retrieval-memory embedding operations now pass the agent’s budget and are recorded in the trace as
embedevents; the model call is re-gated after any accounted work earlier in the same turn. -
save_agent()refuses a config carrying a literal API key instead of warning and writing the key to disk. - The
AgentR6 generator is internal; construct agents withagent().
LLMRagent 0.8.0
CRAN release: 2026-07-21
Initial CRAN release.
- Reproducible LLM agents built on ‘LLMR’: personas, native R tools, pluggable memory, and declared call, token, tool, and time budgets.
- Multi-agent conversations over a shared transcript, with turn-taking presets for debates, focus groups, interviews, and deliberations with votes; factorial experiments over those designs run in parallel and return tidy results.
- Provenance throughout: every run converts to one object with utterance, event, call, tool, and state views; a study manifest of content hashes; and a sealed replication archive whose call log reads back through ‘LLMR’.
- Governance: declared tool side effects, guardrails on inputs, outputs, and tool calls, human approval gates that pause and resume, and a governed Model Context Protocol client.
- A small workflow runtime with checkpoint, resume, fork, and hash-verified replay.
